Course Number: AAOC ZC111

Course Title : Probability and Statistics

Instructor: Dr. K VENKATA RATNAM
BITS-PILANI HYDERABAD CAMPUS
BITS Pilani
Hyderabad Campus
 BITS Pilani
Hyderabad Campus

CONTACT HOUR (CH):1

CH1.1 = Introduction and Announcements

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Text book and Reference Books

T1 Richard A., Miller & Freund’s Probability and

Statistics for Engineers, PHI, 8th Ed., 2011
R1 Paul L. Meyer, Introductory Probability and Statistical Appl., Second
Edition. Addison-Wesley, 1970.

R2 Murray R Spiegel. Theory and problems of probability and statistics,

Schaums Outline Series. McGraw-Hill, New York, 1975

R3 Beaver Beaver, Introduction to Probability and Statistics, Thomson,

12th Ed., 2007.
R4 M.S. Radhakrishnan, Probability & Statistics, DLPD Notes.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Course Objectives

No Course objectives
CO1 Study of descriptive statistics.
CO2 Study of the fundamentals of probability and probability
distributions.
CO3 Applications of statistics. Sampling theory and statistical
inference. Correlation and Regression analysis.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Evaluation Scheme:

Legend: EC = Evaluation Component; AN = After Noon Session; FN = Fore Noon Session

No Name Type Durati Weig Day, Date, Session, Time

on ht
EC-1 Quiz-I Online - 5% February 1 to 10, 2017

Quiz-II Online 5% March 1 to 10, 2017

Quiz-III Online 5% March 24 to April 2, 2017
EC-2 Mid-Semester Closed 2 35% 26/02/2017 (AN) 2 PM TO 4
Test Book hours PM
EC-3 Comprehensive Open 3 50% 09/04/2017 (AN) 2 PM TO 5
Exam Book hours PM

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 GOAL

Whenever the complex systems are in uncertainty

state then how to make decisions/conclusions.

Statistics: Drawing inferences from valid statements. (Data)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Input:

1. Collection of data
2. Processing of data
3. Analysis of data
4. Interpretation of the data

Output: (Why study statistics)

Drawing inferences/conclusions from the above analysis : To

take decisions accordingly- useful for Future Prediction.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Further Study leads to
Decision support system
Set Theory Operations Research
Permutations and Combinations

Basic Statistics

Probability Data Base management

Systems
Distributions

Statistical Inferences -
Hypothesis. Testing
Decision Support
Correlation and Regression
Systems
BITS Pilani, Pilani Campus
Chapters 1 and 2

• Introduction

• Organization and Description of Data

(Home work: Additional reading material)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
CH1.2 = Need for statistics and its Applications

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 FOR MAKING DECISIONS
OR
CHOOSING ACTIONS

To do the above task, we will follow the following steps:

1. Set clearly defined goals for the investigation.

2. Make a plan of what data to collect and how to collect it.

3. Apply appropriate statistical methods to extract information form

the data.

4. Interpret the information and draw conclusions.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Modern Statistics ( Games of Chance)

Terms to be used in this article :

1. Descriptive Statistics

2. Statistical inference

3. Classical approach or frequency based approch

4. Bread and Butter approach.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Statistics and Engineering
IMPACT OF STATISTICS CHANGES THE GLOBAL DYNAMICS
IN MANY FIELDS.

SCIENCE AND ENGINEERING

INDUSTIRAL MANAGEMENT

PRODUCTION MANAGEMENT

MAN POWER

DEVELOPMENT OF NEW PRODUCTS

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Basic Terminology:

1. Unit: A single entity, usually an object or person, whose

characteristics are of interest.

2. Population of units: The complete collection of units about

which information is sought.

3. Statistical Population : It is the set of all measurements

corresponding to each unit in the entire population of units
about which information sought.

4. Sample: From a statistical population is subset of

measurements that are actually collected in the course of an
investigation.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Problem: 1.5 ( page 10, ch.1)
Example : For hard drives to operate properly, the distance
between read/write head and the disk must remain
between tight limits. From each hours production 40 drives
are selected and the distance is measured.

Identify the population unit, variable of interest, statistical

population and sample.

Unit : hard drive

Variable: distance
Population : distances for drives made in hour
Sample: distances for the 40 dirves.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem: 1.6 ( Page 10, Ch.1)

Ten seniors have applied to be on the team that will

build a high mileage car to compete against teams
from other universities. Use random digits ( Table 7
from T1) to select 6 of the 10 seniors to form the
team.
Solution :
Step 1: Number the seniors from 0 to 9.
Step 2 : Go to random digit table : Select any row or
column.
Step 3: Write the digit then assign that to the senior
number, continue and finally select first six students.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
CHAPTER-2

CH1.3 = Diagrammatic Representation of Data

(ORGANIZATION AND DESCRIPTION OF DATA)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Sources of data :

1. Conducting surveys.

2. Conducting Experiments.

3. Any series of Measurements.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Compact way of representation of collected data: (Overview)

1) Pareto diagrams and dot diagrams

2) Histograms, Pie diagrams

3) Stem and Leaf displays.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
CH1.4 = Frequency distribution of grouped data

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Frequency Distribution: It is a table that divides a set of data
into suitable number of classes (categories) showing also
the number of items belongs to each class.

General number of classes : 5<x<15 ( appropriate)

( no overlap, all the data points should be included, length of

the class interval is same)

Range = largest data – smallest data

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Cumulative distribution : sum of the Less than or equal to a
particular class.
29 44 12 53 21 34 39 25 48 23 Class frequency: Number
of observations in each
17 24 27 32 34 15 42 21 28 37
class.
Class Interval Frequency CF
. 10-19 3 3
Class mark : Mid point of
20-29 8 11 the class interval
30-39 5 16
40-49 3 19 Class interval : Successive
50-59 1 20 class marks

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 CH1.5= Central tendency and Dispersion

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Descriptive Measures
Numerical measure of collected data sets : Observation of
data variation
x1  x2  ......  xn
Mean = x
n
Median :
Order n data points in ascending order

n 1
n is odd : median = 2 position in the data

n n  2
and
n is even : average of two observations 2 2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Deviations from the mean : xi  x

Sample variance : s 
2
i n
x  x
i
2

i 1 n 1

Standard deviation :
s
x  x 
i
2
Same unit as the
n 1
observation
( s, S2 are absolute variation)
s
Coefficient of Variation (relative variation): * 100%
x
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Quartiles :

Median describes data sets into halves, more detail information

can be obtained by calculating quartiles. ( division of data
sets into quarters)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Descriptive Measures
i k

xii n x f i i
x  ,x  i 1

i 1 n n

2 2
 
i n
 i k

i n
  xi  i k
  f i xi 
 i 1  f i x 2 i   i 1 
 x 2
i 
n
 n
s 2  i 1 , S2  i 1
n 1 n 1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
PROBLEM 2.39-2.40 Page : 37

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
i n
xi
1. Mean = x  8
i 1 n

2. Median : Arrange the data in ascending order take the middle term
value which is ‘9’.
(1 2 2 3 5 6 8 9 9 10 10 10 13 15 17)

3. Q1 =n/4= 15/4=3.75( position) value=3

Q3 = 15*3/4=45/4=11.25 ( position) value=10
Inter quartile range = Q3 - Q1 =10-3=7,

2
 i n 
  xi 
i n
s2  
x  x 
i
2


(10  8) 2
 (1  8) 2
 ...  (15  8) 2

328
i n

 x 2 i   i 1 
n
n 1 14 14 s 2  i 1  4.84
i 1 n 1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
ANY DOUBTS

NEXT CONTACT HOUR

PROBABILITY

THANK YOU
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Course Number: AAOC ZC111 Course
Title : Probability and Statistics
Instructor: Dr. K VENKATA RATNAM
BITS-PILANI HYDERABAD CAMPUS
BITS Pilani
Hyderabad Campus
 BITS Pilani
Hyderabad Campus

CONTACT HOUR (CH):2

Todays Lecture

Probability theory makes predictions about experiments whose

outcomes depend upon chance.

Probability theory deals with many real-life problems, which

either inherently involve the chance phenomena or describing
the behaviour of the system explicitly with statistical
properties.

How to state the three axioms of probability and use them to

derive basic facts about a probability function. Learn about
three approaches of defining probabilities and their
interpretations.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Chapter-3

Probability

Sample spaces & events

Counting

Probability

Axioms of Probability

Theorems of Probability
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL1.1.1= Sample spaces and events

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions
Experiment : A simple process – output oriented.

Sample Space : Set of all possible outcomes of an experiment.

Event : Subset of the sample space

Discrete Sample Space : It has finitely many or a countable

infinity of elements.

Continuous Sample Space : Elements of the sample space

constitute a continuum

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL1.1.2 = Counting and probability

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions

Sample spaces are generally represented by sets.

Sets are represented graphically by Venn Diagrams.

Operations on Sets : Union, Intersection, Complement.

Empty set is represented as an impossible event represented by Φ

Sure events is represented by S – Sample space

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions
Probability measure uses counting principles.

Counting process can be represented by tree diagrams.

A permutation is an arrangement of objects in a definite order.

A combination is a selection of objects without regard to order

Multiplication Rule: If sets A1,A2,….,Ak contain, respectively,

n1,n2,….nk elements, there are n1.n2…nk ways of choosing
first an element of A1,then an element of A2,…, and finally of
Ak.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions
Another form of multiplication rule : Consider an experiment
taking place in k stages. Let ni denote the number of ways in
which stage i can occur for i=1,2,..k. Altogether the
experiment can occur in n1 . n2 . … nk ways.

The number of permutations of n distinct objects used r at a time

𝑛 𝑛!
denoted by 𝑟𝑃 =
𝑛−𝑟 !
The number of combinations of n distinct objects selected r at a
𝑛 𝑛!
time denoted by 𝑟𝐶 = .
𝑟! 𝑛−𝑟 !
n!
Permutations of Indistinguishable objects are , where
n1! .n2! .n3!... nk
n = n1+ n2+ n3+... +nk
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions
Approaches used to measure the probability:

Personal approach : Anyone can have a personal opinion about

anything - always applicable – accuracy depends on
information

Relative frequency approach: Experiment repeated many times

𝑓 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡𝑖𝑚𝑒𝑠 𝑒𝑣𝑒𝑛𝑡 𝐴 𝑜𝑐𝑐𝑢𝑟𝑠

𝑃 𝐴 = =
𝑛 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡𝑖𝑚𝑒𝑠 𝑒𝑥𝑝𝑒𝑟𝑖𝑚𝑒𝑛𝑡 𝑤𝑎𝑠 𝑟𝑢𝑛

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions

Classical approach: Possible outcomes of the experiment are

equally likely.

𝑛(𝐴) 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑤𝑎𝑦𝑠 𝐴 𝑐𝑎𝑛 𝑜𝑐𝑐𝑢𝑟

𝑃 𝐴 = =
𝑛(𝑆) 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑤𝑎𝑦𝑠 𝑡ℎ𝑒 𝑒𝑥𝑝𝑒𝑟𝑖𝑚𝑒𝑛𝑡 𝑐𝑎𝑛 𝑝𝑟𝑜𝑐𝑒𝑒𝑑

Mutually Exclusive events: Two events A and B are said to be

mutually exclusive then 𝐴 ∩ 𝐵 = ∅ or no elements are in
common.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL 1.2.1 = Axioms of Probability

1. 0 ≤ 𝑃 𝐴 ≤ 1 for each event A in the sample space S

2. P(S)=1

3. If A and B are mutually exclusive events in S then

𝑃 𝐴∪𝐵 =𝑃 𝐴 +𝑃 𝐵 .

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL 1.2.2= Theorems on Probability
1. Prove that probability of impossible event is 0.

Proof :
Let S be the sample space and 𝜙 be any impossible event, these are
mutually exclusive , then
SU 𝜙=S, P(SU 𝜙)=P(S) implies P(𝜙)=0 by axiom 3.

2. Prove that if A is any event in sample space then

P(A’ )= 1-P(A)

Let S be the sample space and A be any event, then A and A’ are are
mutually exclusive.
AU A’=S, P(AU A’)=P(S) implies P(A’)=P(S)-P(A)=1-(A) by axiom 3.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Theorem: If 𝐴1 , 𝐴2 , … , 𝐴𝑛 are mutually exclusive
events in a sample space S, then
P  A1  A2  ...  An 
 P  A1   P  A2   ...  P ( An )

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Theorem: If A is an event in the finite sample space S,
then P(A) equals the sum of the probabilities of the
individual outcomes comprising A.
Proof: Suppose 𝐸1 , 𝐸2 , … , 𝐸𝑛 be the n outcomes
comprising event A. Now, we have
𝐴 = 𝐸1 ∪ 𝐸2 ∪ ⋯ ∪ 𝐸𝑛
As, E’s are individual outcomes and mutually
exclusive, therefore
𝑃(𝐴) = 𝑃(𝐸1 ) ∪ 𝑃(𝐸2 ) ∪ ⋯ ∪ 𝑃(𝐸𝑛 ) = 𝑃(𝐸1 ) + 𝑃(𝐸2 ) + ⋯ + 𝑃(𝐸𝑛 )

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
General addition rule for probability

If A and B are any events in S, then

P( A B)  P( A)  P( B)  P( A B)

A B

AB AB AB

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Proof:
P( A B)  P( A B)  P( A B)  P( A B)
 [ P( A B)  P( A B)]  [ P( A B)  P( A B)]  P( A B)
 P( A)  P( B)  P( A B)

When A and B are mutually exclusive events

P ( A B)  0

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem 3.17: Counting
principle

In an optics kit there are 6 concave lenses, 4 convex lenses and

3 prisms. In how many ways can one choose one of the
concave lenses, one of the convex lenses and one of the
prisms.

Solution : 6X4X3

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems : 3.20, 3.24

If there are 9 cars in a race, in how many

different ways can they place first, second and
third?
Solution : 9𝑃 3
If the order does not matter, in how many
different ways can 4 of 18 robotic arms be
chosen for a special welding job?
Solution :18𝐶 4

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Combinations : Problem 3.25
A carton of 12 rechargeable batteries contains one that is
defective. In how many ways can an inspector choose 3 of the
batteries and
a) Get the one that is defective

b) Not get the one that is defective

c) Suppose two of the batteries are defective in how many ways

can an inspector choose 3 of the batteries and
1)none of the defective batteries
2) one of the defective batteries
3) both of the defective batteries.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

There are 12𝐶 3 = 220 ways to draw the three rechargeable

batteries.
There are 11𝐶 3 = 165 ways to draw none are defective.
(a) The number of ways to get the one that is defective is
220 − 165 = 55.
(b) There are 165 ways not to get the one that is defective

1)10C3 2)1C1* 10C2+1C1*10C2 3) 2C2*10C1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Probability Problems : 3.39
Page : 65
1. Prove that 𝑃 𝐴 ∩ 𝐵 ≤ 𝑃 𝐴 𝑎𝑛𝑑 𝑃(𝐴𝑈𝐵) ≥ 𝑃(𝐴).
A B

A𝐵ത AB ҧ
𝐴B

Solution :
ത
𝑃 𝐴 = 𝑃(𝐴 ∩ 𝐵)+𝑃 ത
𝐴 ∩ 𝐵 implies 𝑃 𝐴 ∩ 𝐵 = 𝑃 𝐴 − 𝑃(𝐴 ∩ 𝐵)

𝑃 𝐴∩𝐵 ≤𝑃 𝐴

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

𝑃 𝐴∪𝐵 =𝑃 𝐴 +𝑃 𝐵 −𝑃 𝐴∩𝐵

From the above diagram we have

𝑃 𝐵 = 𝑃 𝐴ҧ ∩ 𝐵 + 𝑃 𝐴 ∩ 𝐵

Substituting this in the above equation we have

𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐴ҧ ∩ 𝐵 which implies

𝑃(𝐴𝑈𝐵) ≥ 𝑃(𝐴).

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Problem 3.47

The probability that a new airport will get an award for its
design is 0.16, the probability that it will get an award for
the efficient use of materials is 0.24 and the probability
that it will get both awards is 0.11.

a) What is the probability that it will get at least one of the

two awards.

b) What is the probability that it will get only one of the two
awards

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution: Let A be the event that it will get an award for its
design, 𝑃 𝐴 = 0.16.

Let B be the event that it will get award for efficient use of
material, 𝑃 𝐵 = 0.24.

Now, 𝑃 𝐴 ∩ 𝐵 = 0.11

(a) 𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐵 − 𝑃 𝐴 ∩ 𝐵 = 0.29

(b) P(only one award)= P(at least one award)-P(both awards)=

0.29-0.11=0.18
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.31
A car rental agency has 18 compact cars and 12
intermediate size cars. If four cars are randomly selected
for a safety check, what is the probability of getting two
of each kind.
Solution: There are 18+12=30 cars. So, there are 30C4
ways to choose the cars for inspection. There are 18C2
ways to get the compact and 12C2 ways to get the
intermediate size cars. Thus the probability is
18𝐶2 12𝐶2
30𝐶4
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems 3.16 Page : 55 : Tree
diagram

A biomechanical device for medical emergencies can operate for

0,1 or 2 times a night. Construct a tree diagram to show that
there are 10 different ways that it can be operated for a total of
6 times over four nights.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Any questions…….

Thank you

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Course Number: PERL ZC113
Course Title : Probability and Statistics
Instructor: Dr. K VENKATA RATNAM
BITS-PILANI HYDERABAD CAMPUS
BITS Pilani
Hyderabad Campus
 BITS Pilani
Hyderabad Campus

Contact Hour(CH):3
 Problems

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem 3.17: Counting
principle
In an optics kit there are 6 concave lenses, 4 convex lenses and 3
prisms. In how many ways can one choose one of the concave
lenses, one of the convex lenses and one of the prisms.

Solution : the number of ways to select one concave lenses : 6 ( any

one)

the number of ways to select one convex lenses : 4( any one)

the number of ways to select one prism : 3( any one)

Solution : 6X4X3
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems : 3.20

If there are 9 cars in a race, in how many

different ways can they place first, second and
third?

Solution : The number of ways to select first car

is 9 and second car is 8 and the third car is 7
total number of ways to select is 9*8*7= 9𝑃 3
here order is important.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Problem : 3.24

If the order does not matter, in how many different ways

can 4 of 18 robotic arms be chosen for a special welding
job?
Solution : The number of ways to select 4 arms out of 18
are 18𝐶 4

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Combinations : Problem 3.25
A carton of 12 rechargeable batteries contains one that is
defective. In how many ways can an inspector choose 3 of the
batteries and
a) Get the one that is defective

b) Not get the one that is defective

c) Suppose two of the batteries are defective in how many ways

can an inspector choose 3 of the batteries and
1)none of the defective batteries
2) one of the defective batteries
3) both of the defective batteries.
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

There are 12𝐶 3 = 220 ways to draw the three rechargeable

batteries.
There are 11𝐶 3 = 165 ways to draw none are defective.
(a) The number of ways to get the one that is defective is
220 − 165 = 55.
(b) There are 165 ways not to get the one that is defective

1)10C3 2)1C1* 10C2+1C1*10C2 3) 2C2*10C1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Probability Problems : 3.39
Page : 65
1. Prove that 𝑃 𝐴 ∩ 𝐵 ≤ 𝑃 𝐴 𝑎𝑛𝑑 𝑃(𝐴𝑈𝐵) ≥ 𝑃(𝐴).
A B

A𝐵ത AB ҧ
𝐴B

Solution :
ത
𝑃 𝐴 = 𝑃(𝐴 ∩ 𝐵)+𝑃 ത
𝐴 ∩ 𝐵 implies 𝑃 𝐴 ∩ 𝐵 = 𝑃 𝐴 − 𝑃(𝐴 ∩ 𝐵)

𝑃 𝐴∩𝐵 ≤𝑃 𝐴

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

𝑃 𝐴∪𝐵 =𝑃 𝐴 +𝑃 𝐵 −𝑃 𝐴∩𝐵

From the above diagram we have

𝑃 𝐵 = 𝑃 𝐴ҧ ∩ 𝐵 + 𝑃 𝐴 ∩ 𝐵

Substituting this in the above equation we have

𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐴ҧ ∩ 𝐵 which implies

𝑃(𝐴𝑈𝐵) ≥ 𝑃(𝐴).

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Problem 3.47

The probability that a new airport will get an award for its
design is 0.16, the probability that it will get an award for
the efficient use of materials is 0.24 and the probability
that it will get both awards is 0.11.

a) What is the probability that it will get at least one of the

two awards.

b) What is the probability that it will get only one of the two
awards

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution: Let A be the event that it will get an award for its
design, 𝑃 𝐴 = 0.16.

Let B be the event that it will get award for efficient use of
material, 𝑃 𝐵 = 0.24.

Now, 𝑃 𝐴 ∩ 𝐵 = 0.11

(a) 𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐵 − 𝑃 𝐴 ∩ 𝐵 = 0.29

(b) P(only one award)= P(at least one award)-P(both awards)=

0.29-0.11=0.18
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.31
A car rental agency has 18 compact cars and 12
intermediate size cars. If four cars are randomly selected
for a safety check, what is the probability of getting two
of each kind.
Solution: There are 18+12=30 cars. So, there are 30C4
ways to choose the cars for inspection. There are 18C2
ways to get the compact and 12C2 ways to get the
intermediate size cars. Thus the probability is
18𝐶2 12𝐶2
30𝐶4
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Addition theorem 3.46

The probability that an integrated circuit chip will have defective

etching is 0.06, the probability that it will have a crack defect is
0.03, and the probability that it has both defects is 0.02.

a) What is the probability that a newly manufactured chip will

have either an etching or crack defect?

b) What is the probability that a newly manufactured chip will

have neither defect?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

The probability that a newly manufactured chip will have

either an etching or crack defect is

P(AUB)= 0.06+0.03-0.02=0.07

The probability that a newly manufactured chip will have

neither defect

P((AUB)’ )=1-P(AUB)=1-.07

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems 3.16 Page : 55 : Tree
diagram ( Home work)

A biomechanical device for medical emergencies can operate for

0,1 or 2 times a night. Construct a tree diagram to show that
there are 10 different ways that it can be operated for a total of
6 times over four nights.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL1.3.1 = Conditional Probability

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Conditional Probability
Probability of an event A given that the event B has happened,
we are talking of the probability in relation to the “reduced
sample space”.
If A, B are two events associated with a random experiment,
then we define the conditional probability of the event A given
that B has happened as

P  B  A
P  A B  if P  B   0
P  B

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
General Multiplication Rule for Probability

If A, B are two events in S, then

P  A  B   P  A . P  B | A ; P ( A)  0
P  A  B   P  B . P  A | B ; P( B)  0
Two events are called independent if

P  A  B   P  A .P  B 

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.62

If the probabilities are 0.98, 0.96 and 0.95 that a newly

manufactured bottle of soap will be free of major defects,
free of minor blemishes, and free of major defects and
minor blemishes, find the probability that a bottle
(a) that is free of major defects will also be free of minor
blemishes
(b) that is free of minor blemishes will also be free of major
defects.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let A be the event that a bottle is free of major

defects and B be the event that it is free of minor
blemishes.
Now, 𝑃 𝐴 = 0.98; 𝑃 𝐵 = 0.96; 𝑃 𝐴 ∩ 𝐵 = 0.95
𝑃 𝐵∩𝐴 0.95
(a) 𝑃 𝐵 𝐴 = = = 0.969
𝑃(𝐴) 0.98
𝑃 𝐴∩𝐵 0.95
(b) 𝑃 𝐴 𝐵 = = = 0.990
𝑃(𝐵) 0.96

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.70
(Challenging problem)
In a certain city during the month of May, the probability that a
rainy day will be followed by another rainy day is 0.80 and the
probability that a sunny day will be followed by rainy day is
0.60.

Assuming that each day is classified as being either rainy or

sunny and that the weather on any given day depends only on
the weather the day before.

Find the probability that in the given city a rainy day in May is
followed by two more rainy days, then a sunny day, and finally
another rainy day.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

P(R1 R2 R3 S R4 / R1 )=
P(𝑹𝟏 ∩ 𝑹𝟐 ∩ 𝑹𝟑 ∩ 𝑺 ∩ 𝑹𝟒 / 𝑹𝟏 )=
P(𝑹𝟏 ∩𝑹𝟐 ∩𝑹𝟑 ∩𝑺∩𝑹𝟒 ∩𝑹𝟏 ) P(𝑹𝟏 ∩𝑹𝟐 ∩𝑹𝟑 ∩𝑺∩𝑹𝟒 )
=
𝑷(𝑹𝟏 ) 𝑷(𝑹𝟏 )
P(𝑹𝟏 )∩𝑷(𝑹𝟐 )∩𝑷(𝑹𝟑 )∩𝑷(𝑺)∩𝑷(𝑹𝟒 )
= 𝑷(𝑹𝟏 )

= 𝑷(𝑹𝟐 ) ∩ 𝑷(𝑹𝟑 ) ∩ 𝑷(𝑺) ∩ 𝑷(𝑹𝟒 )

=0.8 * 0.8*(1-0.8)*0.6

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Independent events 3.68

If the odds are 5 to 3 that an event M will not occur, 2

to 1 that event N will occur and 4 to 1 that they will
not both occur, are the events M and N are
independent.
Solution : P(M)=1-5/8=3/8, P(N)=2/3

P((M∩N)’)=4/5 P((M∩N)=1-4/5=1/5

Independent events : 3/8 * 2/3 ≠ 1/5

Hence M and N are not independent
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Total probability rule

If B1, B2 , …, Bn are mutually exclusively events of which

one must occur

𝑃 𝐴 = ෍ 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )
𝑖=1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Proof

Let S be the sample space and if B1, B2 , …, Bn are mutually

exclusively events of the sample space then

𝑆 = ‫=𝑖𝑛ڂ‬1 𝐵𝑖

Let A be any event which comprising all the events of Bi and

S∩A= A implies

P(A)=P(S ∩A)=P(A ∩ ‫=𝑖𝑛ڂ‬1 𝐵𝑖 )=P(A ∩(B1 U B2 , …,U Bn )=

P((A ∩B1 )U(A ∩B2 ) U…U A ∩Bn ) ) =σ𝑛𝑖=1 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )

By conditional probability definition.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes' Rule

If B1, B2 , …, Bn are mutually exclusively events of which one

must occur
𝐴
𝑃 𝐵𝑟 . 𝑃(𝐵 )
𝑟
𝑃 𝐵𝑟 /𝐴 = 𝑛
σ𝑖=1 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Proof: P( A  Br )
P( Br | A) 
P( A)
Now, by the theorem on total probability,

P  A  P  B1   P  A B1   P  B2   P  A B2   ...

 P Bn  P A Bn 

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Total theorem : 3.71

At an electronics plant, it is known from past experience that the

probability is 0.86 that a new worker who has attended the
company's training program will meet the production quota,
and that the corresponding probability is 0.35 for a new worker
who has not attended the company’s training program.

If 80% of all new workers attend the training program, what is the
probability that a new worker will meet the production
quota.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
Let M = event that work meets production quota.

Let T = event that worker attended the training program.

We need to find P(T | M) = probability that the worker has attended

training program given he/she met quota.

From the problem statement we deduce:

P(M | T) = 0.86, P(M | T ‘) = 0.35, P(T) = 0.8, P(T ‘) = 0.2.

To find P(M) we use the law of total probability

P(M) = P(M | T) P(T) + P(M | T’) P(T’) = 0.86 × 0.8 + 0.35 × 0.2 = .758

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.73

A consulting firm rents cars from three agencies D, E, F.

20% of the cars are rented from D, 20% from E and the
remaining 60% from F. If 10% of cars rented from D,
12% of cars rented from E, 4% of cars rented from F have
bad tires, find the probability that a car rented from the
consulting firm will have bad tires.
Solution: 𝑃 𝐷 = 0.20, 𝑃 𝐸 = 0.20, 𝑃 𝐹 = 0.60
Let A be the event that it has bad tires, then
𝑃 𝐴 𝐷 = 0.10, 𝑃 𝐴 𝐸 = 12, 𝑃 𝐴 𝐹 = 0.04
Ans. P(A)= (0.2) (0.10) + (0.2) (0.12) + (0.6) (0.04)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes rule 3.79 (Home work)
Engineers in charge of maintaining our nuclear fleet must continually
check for corrosion inside the pipes that are part of the cooling
systems. The inside condition of the pipes cannot be observed
directly but a nondestructive test can give an indication of possible
corrosion. This test is not infallible.

The test has probability 0.7 of detecting corrosion when it is present

but it also has probability of 0.2 of falsely indicating internal
corrosion. Suppose the probability that any section of pipe has
internal corrosion is 0.1.

a) Determine the probability that a section of pipe has internal

corrosion, given that the test indicates its presence.

b) Determine the probability that a section of pipe has internal

corrosion given that the test is negative?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let C = internal corrosion exists and let D = "internal

corrosion detected".

P(C) = 0.1, P(D | C) = 0.7, and P(D | C′) = 0.2.

P(D | C) P(C)
P(C | D) = by Bayes′s Rule
P(D | C′) P(C′) +P(D | C) P(C)
= (0.7) (0.1) / (0.2) (0.9)+ (0.7) (0.1) = 0.28

𝑃(𝐷′ | 𝐶) 𝑃(𝐶)
P(C | D’) =
P(D′ | C′) P(C′) +P(D′ | C) P(C)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes rule: 3.99 (Home Work)

Amy commutes to work by two different routes A and B. If she

comes home by route A, then she will be home no later than 6
P.M with probability 0.8, but if she comes home by route B,
then she will be home no later than 6 P.M with probability 0.7.
In the past, the proportion of times that Amy chose route A is
0.4.
a. What proportion of times is Amy home no later than 6 P.M

a. If Amy is home after 6 P.M, what is the probability that she

too route B?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let C be the event that amy comes home no later than 6 p.m.
( she arrives on or before 6 pm)

P(C) = P(C| A)P(A) +P(C/B) P(B)

Given that p(A) =.4, P(B)1-0.4=0.6 P(C | A)= 0.8, P(C | B)=0.7
Amy arrives after 6 pm from route B is
P(B/C’)= P(C | B)*P(B) / P(C’)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Course Number: PERL ZC113
Course Title : Probability and Statistics
Instructor: Dr. K VENKATA RATNAM
BITS-PILANI HYDERABAD CAMPUS
BITS Pilani
Hyderabad Campus
 BITS Pilani
Hyderabad Campus

Contact Hour(CH): 4
 Problem:3.62

If the probabilities are 0.98, 0.96 and 0.95 that a newly

manufactured bottle of soap will be free of major defects,
free of minor blemishes, and free of major defects and
minor blemishes, find the probability that a bottle
(a) that is free of major defects will also be free of minor
blemishes
(b) that is free of minor blemishes will also be free of major
defects.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let A be the event that a bottle is free of major

defects and B be the event that it is free of minor
blemishes.
Now, 𝑃 𝐴 = 0.98; 𝑃 𝐵 = 0.96; 𝑃 𝐴 ∩ 𝐵 = 0.95
𝑃 𝐵∩𝐴 0.95
(a) 𝑃 𝐵 𝐴 = = = 0.969
𝑃(𝐴) 0.98
𝑃 𝐴∩𝐵 0.95
(b) 𝑃 𝐴 𝐵 = = = 0.990
𝑃(𝐵) 0.96

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Total probability rule

If B1, B2 , …, Bn are mutually exclusively events of which

one must occur

𝑃 𝐴 = ෍ 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )
𝑖=1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Proof

Let S be the sample space and if B1, B2 , …, Bn are mutually

exclusively events of the sample space then

𝑆 = ‫=𝑖𝑛ڂ‬1 𝐵𝑖

Let A be any event which comprising all the events of Bi and

S∩A= A implies

P(A)=P(S ∩A)=P(A ∩ ‫=𝑖𝑛ڂ‬1 𝐵𝑖 )=P(A ∩(B1 U B2 , …,U Bn )=

P((A ∩B1 )U(A ∩B2 ) U…U A ∩Bn ) ) =σ𝑛𝑖=1 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )

By conditional probability definition.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes' Rule

If B1, B2 , …, Bn are mutually exclusively events of which one

must occur
𝐴
𝑃 𝐵𝑟 . 𝑃(𝐵 )
𝑟
𝑃 𝐵𝑟 /𝐴 = 𝑛
σ𝑖=1 𝑃 𝐵𝑖 . 𝑃(𝐴/𝐵𝑖 )

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Proof: P( A  Br )
P( Br | A) 
P( A)
Now, by the theorem on total probability,

P  A  P  B1   P  A B1   P  B2   P  A B2   ...

 P Bn  P A Bn 

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Total theorem : 3.71

At an electronics plant, it is known from past experience that the

probability is 0.86 that a new worker who has attended the
company's training program will meet the production quota,
and that the corresponding probability is 0.35 for a new worker
who has not attended the company’s training program.

If 80% of all new workers attend the training program, what is the
probability that a new worker will meet the production
quota.

Find the probability that the worker has attended training

program given he/she met quota.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
Let M = event that work meets production quota.

Let T = event that worker attended the training program.

From the problem statement we deduce:

P(M | T) = 0.86, P(M | T ‘) = 0.35, P(T) = 0.8, P(T ‘) = 0.2.

Probability of New worker will meet the production quota= P(M) ( we use the law of total probability)

P(M) = P(M | T) P(T) + P(M | T’) P(T’) = 0.86 × 0.8 + 0.35 × 0.2 = .758

We need to find P(T | M) = probability that the worker has attended training program
given he/she met quota. (Bayes theorem )

P(T | M)= P(M |T) * P(T) / P(M) ;

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes rule: 3.99 (Home Work)

Amy commutes to work by two different routes A and B. If she

comes home by route A, then she will be home no later than 6
P.M with probability 0.8, but if she comes home by route B,
then she will be home no later than 6 P.M with probability 0.7.
In the past, the proportion of times that Amy chose route A is
0.4.
a. What proportion of times is Amy home no later than 6 P.M

a. If Amy is home after 6 P.M, what is the probability that she

too route B?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let C be the event that amy comes home no later than 6 p.m.
( she arrives on or before 6 pm)

P(C) = P(C| A)P(A) +P(C/B) P(B)

Given that p(A) =.4, P(B)1-0.4=0.6 P(C | A)= 0.8, P(C | B)=0.7
Amy arrives after 6 pm from route B is
P(B/C’)= P(C | B)*P(B) / P(C’)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:3.73(Home work)

A consulting firm rents cars from three agencies D, E, F.

20% of the cars are rented from D, 20% from E and the
remaining 60% from F. If 10% of cars rented from D,
12% of cars rented from E, 4% of cars rented from F have
bad tires, find the probability that a car rented from the
consulting firm will have bad tires.
Solution: 𝑃 𝐷 = 0.20, 𝑃 𝐸 = 0.20, 𝑃 𝐹 = 0.60
Let A be the event that it has bad tires, then
𝑃 𝐴 𝐷 = 0.10, 𝑃 𝐴 𝐸 = 12, 𝑃 𝐴 𝐹 = 0.04
Ans. P(A)= (0.2) (0.10) + (0.2) (0.12) + (0.6) (0.04)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Bayes rule 3.79 (Home work)
Engineers in charge of maintaining our nuclear fleet must continually
check for corrosion inside the pipes that are part of the cooling
systems. The inside condition of the pipes cannot be observed
directly but a nondestructive test can give an indication of possible
corrosion. This test is not infallible.

The test has probability 0.7 of detecting corrosion when it is present

but it also has probability of 0.2 of falsely indicating internal
corrosion. Suppose the probability that any section of pipe has
internal corrosion is 0.1.

a) Determine the probability that a section of pipe has internal

corrosion, given that the test indicates its presence.

b) Determine the probability that a section of pipe has internal

corrosion given that the test is negative?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Let C = internal corrosion exists and let D = "internal

corrosion detected".

P(C) = 0.1, P(D | C) = 0.7, and P(D | C′) = 0.2.

P(D | C) P(C)
P(C | D) = by Bayes′s Rule
P(D | C′) P(C′) +P(D | C) P(C)
= (0.7) (0.1) / (0.2) (0.9)+ (0.7) (0.1) = 0.28

𝑃(𝐷′ | 𝐶) 𝑃(𝐶)
P(C | D’) =
P(D′ | C′) P(C′) +P(D′ | C) P(C)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Chapter-4

RL2.1.1 = Discrete random variables

RL2.1.2 = PDF and CDF

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions

Random variables : Any function that assigns a numerical value

to each possible outcome.

Classification :

Discrete random variables : Counting the events

Continues random variables : Measurable

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions

Probability Distribution : The probability distribution of a discrete

random variable X is a list of the possible values of X together
with their probabilities

f(x)= P[X=x]

The probability distribution always satisfies the conditions

𝑓 𝑥 ≥ 0, 𝑎𝑛𝑑 ෍𝑓 𝑥 = 1
∀𝑥

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions

The probability of a random variable is less than or equal to x is

represented by Cumulative distribution function

𝐹 𝑥 = 𝑃 𝑋 ≤ 𝑥 𝑓𝑜𝑟 𝑎𝑙𝑙 − ∞ < 𝑥 < ∞

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problems: 4.5

𝑘
Given that 𝑓 𝑥 = is a probability distribution for a random
2𝑥
variable that can take on the values x=0,1,2,3 and 4, find k,
also find an expression for the distribution function F(x) of the
random variable.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
Step1 :
Probability Distribution : (x, P(x))
Step 2: Use discrete density property to find k: σ∀𝑥 𝑓 𝑥 = 1
Step 3: Find the CDF of the given pdf.

X X=0 X=1 X=2 X=3 X=4

P(X) P(X=0)=k/20 =k P(X=1)=k/2 P(x=2)=k/4 P(x=3)=k/8 P(x=4)k/16

𝑘 𝑘 𝑘 𝑘 31𝑘
𝑘 + + + + = 1implies = 1 implies k=16/31
2 4 8 16 16

1
𝑥+1 −1
𝑘 16 (2)
CDF:𝐹 𝑥 = 𝑃 𝑋 ≤ 𝑥 =σ𝑥𝑖=0 𝑃 𝑥 = 𝑥
= σ𝑖=0 𝑥 =
2 31 1 −1
2
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 RL 2.2.1 :Bernoulli Trials

There are only two possible outcomes for each trail

– Success or failure

The probability of success is same for each trail.

The outcomes from different trials are independent.

There are fixed number n of Bernoulli's trials conducted .

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 RL 2.2.2 :Binomial Distribution
(sampling with replacement)
X is a random variable that equals the number of success in n
trails.

A random variable X has a binomial distribution with parameters

n and p if its density is given by

𝑏 𝑥; 𝑛, 𝑝 = 𝑛𝑥𝑐 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥 , 𝑥 = 0,1,2, … , 𝑛,

0 < 𝑝 < 1, n is a positive integer.

(Success occurs at the x trail after n-x failures)

𝑏 𝑥; 𝑛, 𝑝 = 1 − 𝐵(𝑛 − 𝑥 − 1; 𝑛, 1 − 𝑝)
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem :4.19

An agriculture cooperative claims that 90% of the watermelons

shipped out are ripe and ready to eat. Find the probability that
among 18 watermelons shipped out

a) All 18 are ripe and ready to eat.

b) At least 16 are ripe and ready to eat
c) At most 14 are ripe and ready to eat

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Given data: n=18, p=0.9, q=0.1

Formula : P X = x = 𝑏 𝑥; 𝑛, 𝑝 = 𝑛𝑥𝑐 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥

a) x=18, P(x=18)= 18
18 𝐶(0.9)18 (0.1)0 = (0.9)18

b) P( X≥ 16) = 𝑃(𝑋 = 16) + 𝑃(𝑋 = 17) + 𝑃(𝑋 = 18)

C) P(X≤ 14) = 𝑃(𝑋 = 0) + ⋯ + 𝑃(𝑋 = 14) =

1 − 𝑃(𝑥 = 15) − 𝑃(𝑋 = 16) − 𝑃(𝑋 = 17) − 𝑃(𝑋 = 18).

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 RL 2.2.3 = Hypergeometric
Properties

1. The experiment consists of drawing a random sample of size

n without replacement and without regard to order from a
collection of N objects.

2. Of the N objects, a have a trait of interest to us, the other N-a

do not have the trait.

3. The random variable X is the number of objects in the

sample with the trait.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Hypergeometric distribution
(Sampling without replacement)
A random variable X has a hypergeometric distribution with
parameters N, n and a if its density is given by

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 ,
𝑛

𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

BD can be approximated to HD if n ≤N/10.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:4.23

Four emergency radios are available for rescue workers but one
does not work properly. Two randomly selected radios are
taken on a rescue mission. Lex X be the number that work
properly between the two.

a) Determine the probability distribution f(x) of X.

b) Determine the cumulative probability distribution F(x) of X.
c) Graph f(x) as a bar chart and below its graph F(x).

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution:

Given data : N=4, n=2, a=3;

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
Formula : ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 , 𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.
𝑛

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

3 4−3𝐶
𝑥𝐶 𝑋 2−𝑥
P((X=x)=ℎ 𝑥; 2,3,4 = 4𝐶 ,
2

Max[0, 2−(4−3)]≤ x ≤ min(2,3)]=x=1,2.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Probability distribution : Density function P(x)
X=x X=1 X=2
P(x) 0.5 0.5

CDF : F(X) = 0, X<1

= 0.5, 1≤x<2
= 1, x≥2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem: 4.26

If 6 of 18 new buildings in a city violate the building code what is

the probability that a building inspector, who randomly selects
4 of the new buildings for inspection, will catch,

a) None of the building that violate the building code?

b) 1 of the new buildings that violate the building code?
c) At least 3 of the new buildings that violate the building code?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution:

Given data : N=18, n=3, a=6;

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
Formula : ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 ,
𝑛

𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

6
𝑥𝐶 𝑋 18−6
3−𝑥𝐶
P((X=x)=ℎ 𝑥; 3,6,18 = 18𝐶 , Max[0, 3−(18−6)]≤ x ≤
3
min(3,6)]=x=0,1,2,3.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

a) None of them violate : x=0 in the above formula;

b) X=1; in the above formula;

c) P(X≥3)=1-P(X=0)-P(X=1)-P(X=2) in the above formula;

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem

A shipment of 120 burglar alarms contains 5 that are defective. If

3 of these alarms are randomly selected and shipped to a
customer, find the probability that the customer will get one
bad unit by using

a) Using hypergeometric distribution

b) Using binomial distribution as an approximation.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Hypergeometric distribution : Given data : N=120, n=3,

a=5, x= 1, substitute the values in the formula
𝑎𝐶 𝑋 𝑁−𝑎𝐶
𝑥 𝑛−𝑥
ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁
𝑛𝐶

5 115
Binomial distribution : Given data : n=3, p= , q= ,, x=1,
120 120
use the formula :
𝑛𝑐 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥
𝑥

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Course Number: PERL ZC113
Course Title : Probability and Statistics
Instructor: Dr. K VENKATA RATNAM
BITS-PILANI HYDERABAD CAMPUS
BITS Pilani
Hyderabad Campus
 BITS Pilani
Hyderabad Campus

CONTACT HOUR (CH): 5

 RL 2.2.2 :Binomial Distribution
(sampling with replacement)
X is a random variable that equals the number of success in n
trails.

A random variable X has a binomial distribution with parameters

n and p if its density is given by

𝑏 𝑥; 𝑛, 𝑝 = 𝑛𝑥𝑐 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥 , 𝑥 = 0,1,2, … , 𝑛,

0 < 𝑝 < 1, n is a positive integer.

(Success occurs at the x trail after n-x failures)

𝑏 𝑥; 𝑛, 𝑝 = 1 − 𝐵(𝑛 − 𝑥 − 1; 𝑛, 1 − 𝑝)

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 RL 2.2.3 = Hypergeometric
Properties

1. The experiment consists of drawing a random sample of size

n without replacement and without regard to order from a
collection of N objects.

2. Of the N objects, a have a trait of interest to us, the other N-a

do not have the trait.

3. The random variable X is the number of objects in the

sample with the trait.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Hypergeometric distribution
(Sampling without replacement)
A random variable X has a hypergeometric distribution with
parameters N, n and a if its density is given by

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 ,
𝑛

𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

BD can be approximated to HD if n ≤N/10.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem:4.23

Four emergency radios are available for rescue workers but one
does not work properly. Two randomly selected radios are
taken on a rescue mission. Lex X be the number that work
properly between the two.

a) Determine the probability distribution f(x) of X.

b) Determine the cumulative probability distribution F(x) of X.
c) Graph f(x) as a bar chart and below its graph F(x).

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution:

Given data : N=4, n=2, a=3;

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
Formula : ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 , 𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.
𝑛

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

3 4−3𝐶
𝑥𝐶 𝑋 2−𝑥
P((X=x)=ℎ 𝑥; 2,3,4 = 4𝐶 ,
2

Max[0, 2−(4−3)]≤ x ≤ min(2,3)]=x=1,2.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Probability distribution : Density function P(x)
X=x X=1 X=2
P(x) 0.5 0.5

CDF : F(X) = 0, X<1

= 0.5, 1≤x<2
= 1, x≥2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem: 4.26

If 6 of 18 new buildings in a city violate the building code what is

the probability that a building inspector, who randomly selects
4 of the new buildings for inspection, will catch,

a) None of the building that violate the building code?

b) 1 of the new buildings that violate the building code?
c) At least 3 of the new buildings that violate the building code?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution:

Given data : N=18, n=3, a=6;

𝑎𝐶 𝑋 𝑁−𝑎
𝑥 𝑛−𝑥𝐶
Formula : ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁𝐶 ,
𝑛

𝑓𝑜𝑟 𝑥 = 0,1,2, … , 𝑛.

Max[0, n−(N−a)]≤ x ≤ min(𝑛, 𝑎)

6
𝑥𝐶 𝑋 18−6
3−𝑥𝐶
P((X=x)=ℎ 𝑥; 3,6,18 = 18𝐶 , Max[0, 3−(18−6)]≤ x ≤
3
min(3,6)]=x=0,1,2,3.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

a) None of them violate : x=0 in the above formula;

b) X=1; in the above formula;

c) P(X≥3)=1-P(X=0)-P(X=1)-P(X=2) in the above formula;

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem

A shipment of 120 burglar alarms contains 5 that are defective. If

3 of these alarms are randomly selected and shipped to a
customer, find the probability that the customer will get one
bad unit by using

a) Using hypergeometric distribution

b) Using binomial distribution as an approximation.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution

Hypergeometric distribution : Given data : N=120, n=3,

a=5, x= 1, substitute the values in the formula
𝑎𝐶 𝑋 𝑁−𝑎𝐶
𝑥 𝑛−𝑥
ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑁
𝑛𝐶

5 115
Binomial distribution : Given data : n=3, p= , q= ,, x=1,
120 120
use the formula :
𝑛𝑐 𝑝 𝑥 (1 − 𝑝)𝑛−𝑥
𝑥

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Chapter- 4

RL2.3.1 = Mean and Variance of probability

distributions

RL2.3.2 =Mean and Variance of binomial and

hypergeometric distributions

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Definitions
Symmetry: Symmetry is an attribute used to describe the shape of a data distribution.
When it is graphed, a symmetric distribution can be divided at the center so that
each half is a mirror image of the other. A non-symmetric distribution cannot.

Skewness: When they are displayed graphically, some distributions of data have
many more observations on one side of the graph than the other. Distributions with
fewer observations on the right (toward higher values) are said to be skewed
right; and distributions with fewer observations on the left (toward lower values)
are said to be skewed left.

Location: A fundamental task in many statistical analyses is to estimate a location

parameter for the distribution; i.e., to find a typical or central value that best
describes the data. We are interested in mean only.

Variation: The variance is a numerical value used to indicate how widely individuals in
a group vary. If individual observations vary greatly from the group mean, the
variance is big; and vice versa.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Mean and Variance

Mathematical expectation of a random variable X :

E(X)= 𝜇 = σ∀𝑥 𝑥 𝑓(𝑥) = Mean = First moment about the origin .

The variance of a probability distribution f(x) or that of the

random variable X which has that probability distribution as

𝜎 2 = ෍(𝑥 − 𝜇)2 𝑓(𝑥) = 𝐸 𝑋 2 − 𝐸(𝑋) 2

∀𝑥
Standard Deviation : σ = σ∀𝑥 𝑥 − 𝜇 2 𝑓 𝑥

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Example of mean and
Variance
Binomial distribution Mean : 𝜇 =n.p

𝑎
Hypergeometric Mean :𝜇 = n.
𝑁

Binomial distribution variance : 𝑛 𝑝 (1 − 𝑝)

𝑎 𝑎 𝑁−𝑛
Hypergeometric distribution variance : 𝑛 (1 − )( )
𝑁 𝑁 𝑁−1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Problems

Find the mean and variation of the uniform probability

1
distribution given by 𝑓 𝑥 = , 𝑓𝑜𝑟 𝑥 = 1,2, … , 𝑛.
𝑛

1
Solution : Mean = E(X)= 𝜇 = σ∀𝑥 𝑥 𝑓(𝑥)= σ𝑛𝑥=1 𝑥
𝑛

1 1 1 1 1 𝑛(𝑛+1)
=1 ∗ + 2 ∗ + ⋯ + 𝑛 ∗ = 1 + 2 + 3 + ⋯+ 𝑛 = ∗
𝑛 𝑛 𝑛 𝑛 𝑛 2

𝑛+1
=
2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution:

Variance:𝜎 2 = σ∀𝑥(𝑥 − 𝜇)2 𝑓(𝑥)

=𝐸 𝑋 2 − 𝐸(𝑋) 2

2 1 2 1 2 1 𝑛+1 2
=1 ∗ + 2 ∗ + ⋯ + 𝑛 ∗ −
𝑛 𝑛 𝑛 2
1 𝑛+1 2 1 𝑛(𝑛+1)(2𝑛+1) 𝑛+1 2
= (12 +22 +…𝑛2 ) − = ∗ −
𝑛 2 𝑛 6 2

𝑛2 −1
=
12

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Mean of Hypergeometric
distribution
𝑛 𝑛 𝑎 𝑁−𝑎
𝑥 𝑛−𝑥
𝑀𝑒𝑎𝑛 = 𝐸 𝑥 = ෍ 𝑥 𝑓 𝑥 = ෍ 𝑥 𝑁
𝑥=0 𝑥=0 𝑛
𝑥𝑎! 𝑁−𝑎 !
𝑛 𝑎 𝑁−𝑎 𝑛 𝑋
𝑥 𝑛−𝑥
𝑎 − 𝑥 ! 𝑥! 𝑁−𝑎− 𝑛−𝑥 ! 𝑛−𝑥 !
= ෍𝑥 𝑁 =෍
𝑁!
𝑥=0 𝑛 𝑥=1
𝑁 − 𝑛 ! 𝑛!
𝑎(𝑎 − 1)! 𝑁 − 1 − (𝑎 − 1 )!
𝑛 𝑋
𝑎 − 1 − 𝑥 − 1 ! (𝑥 − 1)! 𝑁 − 1 − (𝑎 − 1) − 𝑛 − 1 − (𝑥 − 1 ! 𝑛 − 1 − (𝑥 − 1) !
=෍
𝑁(𝑁 − 1)!
𝑥=1
𝑁 − 1 − (𝑛 − 1) ! 𝑛 (𝑛 − 1)!

𝑎−1 𝑁−𝑎
𝑎𝑛 𝑛 𝑎𝑛
Mean = E(X)= σ𝑥=1 𝑥−1𝑁−1𝑛−𝑥 = , [ put x-1=y, then summation varies from0 to n-1]
𝑁 ( 𝑛−1 ) 𝑁

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Moments

kth moment about the origin : 𝜇′𝑘 = σ∀𝑥 𝑥 𝑘 𝑓(𝑥)

kth moment about the mean : 𝜇𝑘 = σ∀𝑥(𝑥 − 𝜇)𝑘 𝑓(𝑥)

First moment about the origin is mean = 𝜇

Second moment about the mean is variance 𝜎 2 = 𝜇′2 − 𝜇2

Third and fourth moments about the mean describes the

skewness and kurtosis.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem
If 95% of certain high performance radial tires last at lest 30,000
miles, find the mean and standard deviation of the distribution
of the number of these tires among 20 selected at random that
last atleast 30,000 miles using
1) table 1, the formula which defines mean and the computing
formula for variance.
2) The special formulas for the mean and the variance of a
binomial distribution.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
𝑛
Binomial distribution : b( x; n , p)=𝑓 𝑥 = 𝑥
𝑝 𝑥 (1 − 𝑝)𝑛−𝑥

Given data : p=0.95, 1-p = 0.05, n= 20

1) Table:
x 0 1 2 3 4 5 6 7------13 14 ------ 20
f(x) 0 0 0 0 0 0 0 0-------0 0.0003 ----- 0.3585

Mean = 𝜇 = 𝐸 𝑋 = σ 𝑥𝑓 𝑥 = 0 ∗ 0 + 1 ∗ 0 + 2 ∗ 0 + ⋯ . +20 ∗ 0.3585=19

Variance = E(X2)- [E(X)]2

E(X2)= E 𝑋 2 = σ 𝑥 2 𝑓 𝑥 = 02 ∗ 0 + 12 ∗ 0 + 22 ∗ 0 + ⋯ . +202 ∗ 0.3585 = 361.9496

Variance = 361.9496-(19)2= .9496

2) Using formulas : 𝜇 = 𝑛. 𝑝 = 20 ∗ 0.95 = 19

variance = 𝜎 2 = 𝑛𝑝 1 − 𝑝 = 20 ∗ 0.95 ∗ 0.05 = .95

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem

Find the mean and the standard deviation of the hypergeometric

distribution with the parameters n=3, a=4, and N=8.
a) By first calculating the necessary probabilities and then using
the formulas which define mean and variance.
b)By using the special formulas for the mean and the variance of
𝑎 𝑎 𝑁−𝑛
a hypergeometric distribution. 𝑛 (1 − )( )
𝑁 𝑁 𝑁−1

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution

Given distribution is hypergeometric; its distribution function is

𝑎 𝑁−𝑎
𝑥 𝑛−𝑥
ℎ 𝑥; 𝑛, 𝑎, 𝑁 = 𝑓(𝑥) = 𝑁
𝑛

1) Given that n=3, a=4, and N=8;

Table : x 0 1 2 3
f(x) 4/56 24/56 24/56 4/56

Mean = 𝜇 = 𝐸 𝑋 =
4 24 24
σ 𝑥𝑓 𝑥 = 0 ∗ + 1 ∗ + 2 ∗ + 3 ∗ 4/56=1.5
56 56 56

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
RL2.3.3 = Chebyshev's theorem

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Chebyshev’s theorem

If a probability distribution has mean 𝜇 and standard

deviation 𝜎 the probability of getting a value which
1
deviates from 𝜇 by atleast k𝜎 is atmost 2 .
𝑘

1
𝑃( 𝑥 − 𝜇 ≥ 𝑘𝜎) ≤
𝑘2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Chebyshev’s theorem
Breaking real line into 3 parts :
i ) (-,( μ-k )  ] ii ) [( μ-k ), ( μ  k )] iii ) [( μ  k )  , )
Making use of the definition of Variance :

V (X )   2
  ( x   ) 2 f ( x) 


( μ-k ) ( μ  k ) 

 (x  )

2
f ( x)   ( x   ) 2
f ( x)   (x  ) 
2
f ( x)
( μ-k ) ( μ  k )

In Region i ) : x     k  ( x   ) 2  k 2 2
In Region iii ) : x    k  ( x   ) 2  k 2 2
( μ  k )
 2
 k  P ( X    k ) 
2 2
 ( x   )
( μ-k )
2
f ( x )  k 2 2 P ( X    k )

  2  k 2 2 P ( X    k )  k 2 2 P ( X    k ) 
 k 2 2 1  P (   k  X    k )
2
 2 2  2  1  P (   k  X    k )  P (   k  X    k )  1  2
1 1
k  k k
Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem

Over the range of cylindrical parts manufactured on a computer

controlled lathe, the standard deviation of the diameters is
0.002 millimeter. What does Chebyshev’s theorem tell us
about the probability that a new part will be within 0.006 unit
of the mean 𝜇 for that run?

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
1
By Chebyshev’s theorem we have 𝑃 𝑥 − 𝜇 ≥ 𝑘𝜎 ≤ −− −1
𝑘2

Given that σ = 0.002, 𝑃( 𝑥 − 𝜇 ≤ 0.06) ----2

By comparing 1and 2 we get 𝑘𝜎 = 0.006 , σ = 0.002 then

K=3.

1 1 8
Required probability is 𝑃 𝑥 − 𝜇 ≤ 0.006 ≥ 1 − =1− =
𝑘2 32 9

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Problem

If 1out of 6 cases material for bulletproof vests fails to meet

puncture standards. If 405 specimens are tested what does
Chebyshev’s theorem tell us about the probability of getting at
most 30 or more than 105 cases that do not meet puncture
standards.

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
 Solution
Given information is the product is meet the requirement or not
meet the requirement ----- Binomial distribution;

Given that n=405, p= 1/6, 1-p =1-1/6 = 5/6.

Mean = n. p= 405* 1/6= 67.5

Variance = n *P*(1-p)= 405*1/6*5/6= 56.25.

Standard deviation= sqrt ( 56.25) = 7.5

1
By Chebyshev’s theorem we have 𝑃 𝑥 − 𝜇 ≥ 𝑘𝜎 ≤
𝑘2

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
Solution
1
𝑃 𝑥 − 67.5 ≥ 𝑘 ∗ 7.5 ≤ 2
𝑘

−𝑘 ∗ 7.5 ≥ 𝑥 − 67.5 𝑜𝑟 𝑥 − 67.5 ≥ 𝑘 ∗ 7.5

𝑥 − 67.5 ≤ −𝑘 ∗ 7.5 𝑎𝑛𝑑 𝑥 − 67.5 ≥ 𝑘 ∗ 7.5

Probability of getting at most 30 or more than 105 is

P(X≤ 30) or P(X≥105) is obtained by choosing k is 5

According to Chebyshev’s theorem

1
𝑃 𝑥 − 67.5 ≥ 5 ∗ 7.5 ≤ 2
5

Course Number: AAOC ZC111, Course Title : Probability and Statistics , Dr. KVR , BITS Pilani, Hyderabad Campus
1
6
7
/
2
5

Probability & Statistics

BITS Pilani, Hyderabad Campus

Lecture - 06
Course Number: AAOC ZC111
[email protected]

January 28, 2017

1Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
6
8
/
2
5

Outline
Chebyshev’s Theorem

The Poisson Distribution

Poisson Processes

Geometric Distribution

Simulation
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Theorem
Chebyshev’s Theorem
If a probability distribution has mean µ and standard deviation σ, the
probability of getting a value which deviates from µ by at least kσ is at
most k12
• The above theorem gives bounds on the probability of getting a
value that deviates from mean

3/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Theorem
Chebyshev’s Theorem
If a probability distribution has mean µ and standard deviation σ, the
probability of getting a value which deviates from µ by at least kσ is at
most 1

• k2

• The above theorem gives bounds on the probability of getting a value that de
• Mathematically, it can be written as
P(|X − µ| ≥ kσ) ≤ 2
1
k

3/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Theorem
Chebyshev’s Theorem
If a probability distribution has mean µ and standard deviation σ, the
probability of getting a value which deviates from µ by at least kσ is at
most 1

• k2

• The above theorem gives bounds on the probability of getting a value that de
• Mathematically, it can be written as
P(|X − µ| ≥ kσ) ≤ 2
1
k

• Alternatively, we can also write it as

1
P(|X − µ| < kσ) ≥ 1 − 2
k
• The above expression gives the probability of getting a value that
deviates from µ by at most kσ is at least 1 − k21
3/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Chebyshev’s Theorem
Example
The number of customers who visit a car dealer’s showroom on a Sunday
morning is a random variable with µ = 18 and σ = 2.5. What is the
probability that there will be more than 8 but fewer than 28 customers ?

4/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Chebyshev’s Theorem
Example
The number of customers who visit a car dealer’s showroom on a Sunday
morning is a random variable with µ = 18 and σ = 2.5. What is the
probability that there will be more than 8 but fewer than 28 customers ?

Example
On a multiple choice test given to 200 psychology students the TA notes
a class average of 75 percent and a standard deviation of 2.0 percent.
Based on Chebyshev’s rule find the minimum number of students who
could have received marks between 70 and 80.

4/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Some times an event can occur 0, 1, 2, . . . times in an interval

The
•
Poisson Distribution
• That is there is no upper bound on the number possibilities
• Note that the interval can be time/distance/area/volume

5/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Some times an event can occur 0, 1, 2, . . . times in an interval

The
•
Poisson Distribution
• That is there is no upper bound on the number possibilities
• Note that the interval can be time/distance/area/volume
Examples
• The number of phone calls received by a call centre per hour
• The number of misprints of words in a standard text book
• River overflow floods in a 100 year interval
• The number of patients arriving to the emergency ward of a
hospital between 6pm and 6am
• The number of large meteors hitting the earth over 100 years

5/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Some times an event can occur 0, 1, 2, . . . times in an interval

The
•
Poisson Distribution
• That is there is no upper bound on the number possibilities
• Note that the interval can be time/distance/area/volume
Examples
• The number of phone calls received by a call centre per hour
• The number of misprints of words in a standard text book
• River overflow floods in a 100 year interval
• The number of patients arriving to the emergency ward of a
hospital between 6pm and 6am
• The number of large meteors hitting the earth over 100 years

The Poisson distribution function precisely finds the probability of

number of times an event occurs in a given interval 5/25
6Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
/
2
5

Definition of the Poisson Distributio

The formula for the Poisson probability distribution function is given by

λ x e− λ
P( X = x) = f (x; λ) =
x!
• x is the number of successes in the given interval

• λ = np - is the mean (the average number of events in the given

interval)

• Here n is the number of trials and p is the probability of success

• The mean of this distribution function is given by µ = λ

√
• The standard deviation is given by σ = λ
7Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
/
2
5

Definition of the Poisson Cumulativ

The formula for the Poisson cumulative probability distribution function
is given by
x k −λ
. λ e
P( X ≤ x) = F (x; λ) =
k!
k=0

• The respective values of F (x; λ) can be obtained from the Tables

8Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
/
2
5

The Poisson Distribution

• It was originally derived as an approximation to the Binomial
distribution

• Events that are rather rare and don’t happen that often follow a
Poisson distribution

• It was derived by the French mathematician Simeon Poisson in 1837

• First application was the description of the number of deaths by

horse kicking in the Prussian army
9Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
/
2
5

Characteristics of the Poisson Distr

• The number of outcomes of interest is random

• The occurrence of one outcome does not influence the chances of

another outcome of interest

• The probability of an outcome of interest in a given interval is the

same for all intervals
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Connection between Binomial and P

• When there is a large number of trials, but the probability of

success is small, Binomial probabilities are often approximated by
Poisson distribution

• That is when n → ∞ , p → 0 and np remains constant, the limiting

form of the Binomial distribution is the Poisson distribution

10/25
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
1
/
2
5

Poisson Distribution: Example prob

Example
It is known that 5% of the books bound at a certain bindery have
defective bindings. Find the probability that 2 of 200 books bound by
this bindery will have defective bindings.
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
2
/
2
5

Poisson
• Processes
The Poisson process
in probability theory
is one of the most important random processes

• Widely used to model random points in a given interval

• Example: The arrival times of customers at a restaurant are random

• Example: The timings of earthquakes seem to be completely random

• Example: The location of users in a wireless network;

• In the cases, the randomness can be modelled by Poisson process

• Several important probability distributions arise naturally from the

Poisson process

• Examples: Poisson, Exponential and Gamma distributions

1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
3
/
2
5

Let X be a Poisson random variable. Our objective is to find the

Poisson Processes
probability P ( X = x) of x successes during a time interval of length T
• Divide the interval into n equal parts of length ∆ t
• We then have T = n ∆ t
We assume that
• The probability of success during a very small interval of time ∆ t is
given by p = α ∆ t
• Here α is the average number of successes per unit time
• The probability of more than one success during such a small time
interval ∆ t is negligible
• The probability of success during such a time interval does not
depend on what happened prior to that time
This imply that the assumptions underlying the binomial distribution
function are satisfied.
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
4
/
2
5

Poisson Processes
Then the probability of x successes during the time interval T is given by
the binomial probability b(x; n, p) with

T
n= and p = α ∆ t
∆t
• When n → ∞ the probability of x successes during the interval T is
given by Poisson probability with the parameter λ, given by
T
λ = np = α ∆ t = αT
∆t

• Note: The Poisson distribution may be used to model a binomial

distribution provided that n is large, p is small
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
5
/
2
5

Poisson Processes: Example proble

Example
Suppose if a bank receives on the average 6 bad cheques per day.
What are the possibilities that it will receive

• 3 bad cheques on any given day

• 5 bad cheques over any 2 consecutive days ?
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
6
/
2
5

Poisson Processes: Example proble

Example
In the inspection of tin plate produced by a continuous electrolytic
process, 0.2 imperfection is spotted per minute, on average. Find the
probabilities of spotting

• Two imperfections in 4 minutes

• At least two imperfections in 5 minutes
• At least one imperfection in 15 minutes
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
7
/
2
5

Geometric Distribution
Consider a sequence of
• Function
Bernoulli trials. We are interested in the
number of the trial at which the first success occurs.
• We want to find the probability of getting the first success on the
x th trial
• It is clear that we have failures in x − 1 trials
• Let p be the probability of a success
• Then the probability of failure is p − 1
• The probability of x − 1 failures in x − 1 trials is (1 − p) (x−1).
• Then the probability of getting the first success on the x th trial is
given by
g(x; p) = p(1 − p) (x−1), x = 1, 2, 3, . . .

• The above distribution function is called geometric distribution

1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
8
/
2
5

Geometric Distribution Function

• The mean of a random variable following the geometric distribution
function is
1
µ=
p
• The variance of the geometric distribution function is
1− p
σ2 =
p2

• Note: In a geometric distribution, we do not know the total number

of trials a priori
1 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
9
/
2
5

Comparison: Binomial and Geomet

• For a random variable with a Binomial distribution, we know the
number of trials, i.e., n

• For a random variable with a Geometric distribution we do not know

the number of trials

• The trials are to be performed until we get a success

Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Example
Example
Problems: Geometric Dist
Let X be a geometric random variable with p = 0.25. What is the
probability that X = 4 (that is the first success occurs on the fourth
trial) ?

20/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Example
Example
Problems: Geometric Dist
Let X be a geometric random variable with p = 0.25. What is the
probability that X = 4 (that is the first success occurs on the fourth
trial) ?

Example
Products produced by a machine has a 3% defective rate.
• What is the probability that the first defective occurs in the fifth
item inspected ?

• What is the probability that the first defective occurs in the first five
inspections ?

20/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Example Problems: Geometric Dist

Example
If a production line has a 20% defective rate, then what is the average
number of inspections to obtain the first defective ?

21/25
Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation

Example Problems: Geometric Dist

Example
If a production line has a 20% defective rate, then what is the average
number of inspections to obtain the first defective ?

Example
I am new to basketball and so I am practising to shoot the ball through
the basket. If the probability of success at each throw is 0.2, how many
times would I fail on average before a success occurs.

21/25
2 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
2
/
2
5

Example Problems: Geometric Dist

Example
Products are inspected until first defective is found. X is a geometric
random variable with parameter p. The first 10 trials have been found to
be free of defectives. What is the probability that the first defective will
occur in the 15th trial ?
2 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
3
/
2
5

Example Problems: Geometric Dist

Example
A test of weld strength involves loading welded joints until a fracture
occurs. For a certain type of weld, 80% of the fractures occur in the weld
itself, while the other 20% occur in the beam. A number of welds are
tested and the tests are independent.
• What the probability that the first beam fracture happens on the
third trial or later.
2 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
4
/
2
5

Simulation
• Central to the idea of simulation is a numerical scheme
• Some times it is also referred as simulation techniques
• Typically a computer program is written to for the numerical
solution of processes
• The program is executed on
laptop/desktop/workstation/cluster/supercomputer
• Over the decades a large number of numerical schemes have been
developed and applied to a large number of problems in several
streams of Engineering and Sciences
2 Chebyshev’s TheoremThe Poisson DistributionPoisson ProcessesGeometric DistributionSimulation
5
/
2
5

Simulation
• A numerical scheme that is used to simulate processes that involve
an element of chance is of particular interest to us
• Such schemes are called as Monte Carlo Methods
• Example: Monte Carlo methods are used to determine the value of π
• These methods are used to measure the risk in quantitative analysis
and decision making
• Widely used in the fields of finance, project management, energy,
manufacturing, insurance, oil & gas exploration, transportation, etc
1Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
9
9
/
2
7

Probability & Statistics

BITS Pilani, Hyderabad Campus

Lecture - 07
Course Number: AAOC ZC111
[email protected]

January 29, 2017

2Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
0
0
/
2
7

Outline
Geometric Distribution

Simulation

Continuous Random Variable

Probability Density Function

Cumulative Distribution Function

Mean and Variance

2Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
0
1
/
2
7

Geometric Distribution Function

• Consider a sequence of Bernoulli trials. We are interested in the number of th

• We want to find the probability of getting the first success on the
• x th trial
• It is clear that we have failures in x − 1 trials
• Let p be the probability of a success
• Then the probability of failure is p − 1
• The probability of x − 1 failures in x − 1 trials is (1 − p) (x−1) .
• Then the probability of getting the first success on the x th trial is given by
• g(x; p) = p(1 − p) (x−1) , x = 1, 2, 3, . . .
2Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
0
2
/
2
7

Geometric Distribution Function

• The mean of a random variable following the geometric distribution
function is
1
µ=
p
• The variance of the geometric distribution function is
1 −p
σ2 =
p2

• Note: In a geometric distribution, we do not know the total number

of trials a priori
2Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
0
3
/
2
7

Comparison: Binomial and Geomet

• For a random variable with a Binomial distribution, we know the
number of trials, i.e., n

• For a random variable with a Geometric distribution we do not know

the number of trials

• The trials are to be performed until we get a success

Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Example
Example
Problems: Geometric Dist
Let X be a geometric random variable with p = 0.25. What is the
probability that X = 4 (that is the first success occurs on the fourth
trial) ?

6/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Example
Example
Problems: Geometric Dist
Let X be a geometric random variable with p = 0.25. What is the
probability that X = 4 (that is the first success occurs on the fourth
trial) ?

Example
Products produced by a machine has a 3% defective rate.
• What is the probability that the first defective occurs in the fifth
item inspected ?

• What is the probability that the first defective occurs in the first five
inspections ?

6/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Example Problems: Geometric Dist

Example
If a production line has a 20% defective rate, then what is the average
number of inspections to obtain the first defective ?

7/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Example Problems: Geometric Dist

Example
If a production line has a 20% defective rate, then what is the average
number of inspections to obtain the first defective ?

Example
I am new to basketball and so I am practising to shoot the ball through
the basket. If the probability of success at each throw is 0.2, how many
times would I fail on average before a success occurs.

7/27
8Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
/
2
7

Example Problems: Geometric Dist

Example
Products are inspected until first defective is found. X is a geometric
random variable with parameter p. The first 10 trials have been found to
be free of defectives. What is the probability that the first defective will
occur in the 15th trial ?
9Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
/
2
7

Example Problems: Geometric Dist

Example
A test of weld strength involves loading welded joints until a fracture
occurs. For a certain type of weld, 80% of the fractures occur in the weld
itself, while the other 20% occur in the beam. A number of welds are
tested and the tests are independent.
• What the probability that the first beam fracture happens on the
third trial or later.
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Simulation

• Central to the idea of simulation is a numerical scheme

• Some times it is also referred as simulation techniques
• Typically a computer program is written to for the numerical solution of proce
• The program is executed on laptop/desktop/workstation/cluster/supercompu
• Over the decades a large number of numerical schemes have been developed
and Sciences

10/27
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
1
/
2
7

Simulation
• A numerical scheme that is used to simulate processes that involve
an element of chance is of particular interest to us
• Such schemes are called as Monte Carlo Methods
• Example: Monte Carlo methods are used to determine the value of π
• These methods are used to measure the risk in quantitative analysis
and decision making
• Widely used in the fields of finance, project management, energy,
manufacturing, insurance, oil & gas exploration, transportation, etc
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
2
/
2
7

Continuous Random Variable

Definition
A random variable X is said to be continuous if its set of possible values
is infinite and uncountable.

• That is the range of a continuous random variable is infinite

• This implies that the continuous random variable can assume any
value in an interval (or in a collection of intervals) on the real line
• For example, if we consider the range of X as [a, b], then X can
take any value between a and b. That is a ≤ x ≤ b
• On the contrary, for a discrete random variable, the range is a finite
and countable set
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Continuous Random Variable: Exam

• We are interested in measuring the depth of a lake at a randomly
selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L

13/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Continuous Random Variable: Exam

• We are interested in measuring the depth of a lake at a randomly
selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph

13/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Continuous Random Variable: Exam

• We are interested in measuring the depth of a lake at a randomly
selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph
• Let X be the blood sugar level of a given person. Then the values
of X are continuous in nature

13/27
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Continuous Random Variable: Exam

• We are interested in measuring the depth of a lake at a randomly
selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph
• Let X be the blood sugar level of a given person. Then the values
of X are continuous in nature
• Let the random variable X be the temperature of Hyderabad in one
day. Then X can take any value between maximum and minimum
temperatures

13/27
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
4
/
2
7

Definition
Continuous Density Function
Let X be a continuous random variable. Then the probability distribution
function of X is a function f (x) such that for any two numbers a and b
with a ≤ b, we have
b
¸
P(a ≤ X ≤ b) = f (x)dx
a

• The probability that X takes on a value in the interval [a, b] is the

area above this interval and below the curve f (x)
• The graph of f (x) is often referred to as the density curve
• Due to this, the probability distribution function is also called as the
probability density function(pdf)
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
5
/
2
7

Definition
Continuous Density Function
Let X be a continuous random variable. Then the probability distribution
function of X is a function f (x) such that for any two numbers a and b
with a ≤ b, we have
b
¸
P(a ≤ X ≤ b) = f (x)dx
a

• This formula gives us an idea about the distribution of probability

density instead of probability itself
• For any c ∈ [a, b], P (X = c) = 0. This implies that the probability
that X takes any specific value is 0 (Obvious from P (a ≤ X ≤ b),
with a = b)
• Instead of a point value, we always compute the probability of an
interval
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
6
/
2
7

Probability Density Function

Remarks: For the function f (x) to be a legitimate probability function,
it must satisfy the following conditions

• f (x) ≥ 0, for all x

¸∞
• f (x)dx = 1
−∞

• The above definite integral gives the area under the entire graph of
f (x)
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
7
/
2
7

Probability Density Function

Note: For any two numbers a and b with a ≤ b, we have the following
b
¸
f (x)dx =P (a ≤ X ≤ b)
a
=P (a < X ≤ b)
=P (a ≤ X < b)
=P (a < X < b)
1 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
8
/
2
7

Cumulative Distribution Function

Definition
The cumulative distribution function cdf F (x) for a continuous random
variable X is defined for every number x by
x
¸
F (x) = P(X ≤ x) = f (s)ds
−∞

• F (x) gives the area under f (x) to the left of x

• 0 ≤ F (x) ≤ 1
• Note that the function F (x) is non-decreasing
Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean

Definition
Cumulative Distribution Function
The cumulative distribution function cdf F (x) for a continuous random
variable X is defined for every number x by
x
¸
F (x) = P(X ≤ x) = f (s)ds
−∞

From the definition of cdf, we have the following results

• f (x) = F r (x)
¸ b
• For a < b, P(a ≤ X ≤ b) = f (x)dx = F (b) − F (a)
a
¸a
• P ( X ≤ a) = f (x)dx = F (a)
−∞
¸∞
• P ( X > a) = f (x)dx = 1 − F (a)
a 19/27
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
0
/
2
7

Mean of a Continuous Random Vari

Definition
The expectation or the mean of a continuous random variable X with the
probability density function f (x) is givenby
¸∞
µ= x f (x)dx
−∞

• Mean gives a measure of the centre of the distribution

• On the contrary, in the discrete case mean is given by the
summation
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
1
/
2
7

Variance of a Continuous Random V

Definition
The variance of a continuous random variable X with the probability
density function f (x) and mean µ is given by
¸∞ ¸∞
σ2 = (x − µ) 2 f (x)dx = x 2 f (x)dx − µ2
−∞ −∞

• Variance is a measure of the spreadness of the distribution

√
• The standard deviation of X is given by σ
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
2
/
2
7

Example Problems
Example
If a random variable has the probability density given by
.
2e− 2x , x > 0
f (x) =
0, x ≤0

Find the probabilities that it will take on a value

• Between −1 and 3
• Greater than 0.5
• Less than or equal to 1
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
3
/
2
7

Example Problems
Example
If a random variable has the probability density given by
.
2e− 2x , x > 0
f (x) =
0, x ≤0

• Find the mean of the random variable

• Find the variance of the random variable
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
4
/
2
7

Example Problems
Example
The probability of a random variable taking values between −∞ and ∞ is
given as 1. For the given probability density function f (x), find the
value of k. .
0, x ≤0
f (x) = 2
kxe −4x , x > 0
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
5
/
2
7

Example Problems
Example
In a certain city, the daily consumption of electric power is a random
variable having the probability density
.
1 − x3 ,
9 xe x >0
f (x) =
0, x ≤0

If the city’s power plant has a daily capacity of 12 million kilowatt-hours,

what is the probability that this power supply will be inadequate on any
given day ?
2 Geometric DistributionSimulationContinuous Random VariableProbability Density FunctionCumulative Distribution FunctionMean
6
/
2
7

Example Problems
Example
The phase error in a tracking device has probability density given by
.
cos(x), 0 < x < π2
f (x) =
0, elsewhere

Find the probability that the phase error is

• Between 0 and π
4

• Greater than π
4
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Probability & Statistics

BITS Pilani, Hyderabad Campus

Lecture - 08
Course Number: AAOC ZC111
[email protected]

February 5, 2017

1 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Outline

Continuous Random Variables and Properties

Uniform Distribution

Exponential Distribution

Gamma Distribution

2 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Random Variable

Definition
A random variable X is said to be continuous if its set of possible values
is infinite and uncountable.
• That is the range of a continuous random variable is infinite
• This implies that the continuous random variable can assume any
value in an interval (or in a collection of intervals) on the real line
• For example, if we consider the range of X as [a, b], then X can
take any value between a and b. That is a ≤ x ≤ b
• On the contrary, for a discrete random variable, the range is a finite
and countable set

3 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Random Variable: Examples

• We are interested in measuring the depth of a lake at a randomly

selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L

4 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Random Variable: Examples

• We are interested in measuring the depth of a lake at a randomly

selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph

4 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Random Variable: Examples

• We are interested in measuring the depth of a lake at a randomly

selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph
• Let X be the blood sugar level of a given person. Then the values
of X are continuous in nature

4 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Random Variable: Examples

• We are interested in measuring the depth of a lake at a randomly

selected location. Let X be the depth at a location. Then X can
take any value between 0 and maximum depth L
• Let X be the speed of a car driving in a city. X can take any value
between 0 and 100kmph
• Let X be the blood sugar level of a given person. Then the values
of X are continuous in nature
• Let the random variable X be the temperature of Hyderabad in one
day. Then X can take any value between maximum and minimum
temperatures

4 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Density Function

Definition
Let X be a continuous random variable. Then the probability distribution
function of X is a function f (x) such that for any two numbers a and b
with a ≤ b, we have

Zb
P (a ≤ X ≤ b) = f (x)dx
a

• The probability that X takes on a value in the interval [a, b] is the

area above this interval and below the curve f (x)
• The graph of f (x) is often referred to as the density curve
• Due to this, the probability distribution function is also called as the
probability density function (pdf)

5 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Continuous Density Function

Definition
Let X be a continuous random variable. Then the probability distribution
function of X is a function f (x) such that for any two numbers a and b
with a ≤ b, we have

Zb
P (a ≤ X ≤ b) = f (x)dx
a

• This formula gives us an idea about the distribution of probability

density instead of probability itself
• For any c ∈ [a, b], P (X = c) = 0. This implies that the probability
that X takes any specific value is 0 (Obvious from P (a ≤ X ≤ b),
with a = b)
• Instead of a point value, we always compute the probability of an
interval 6 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Probability Density Function

Remarks: For the function f (x) to be a legitimate probability function,

it must satisfy the following conditions

• f (x) ≥ 0, for all x

R∞
• f (x)dx = 1
−∞

• The above definite integral gives the area under the entire graph of
f (x)

7 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Probability Density Function

Note: For any two numbers a and b with a ≤ b, we have the following

Zb
f (x)dx =P (a ≤ X ≤ b)
a
=P (a < X ≤ b)
=P (a ≤ X < b)
=P (a < X < b)

8 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Cumulative Distribution Function

Definition
The cumulative distribution function cdf F (x) for a continuous random
variable X is defined for every number x by
Zx
F (x) = P (X ≤ x) = f (s)ds
−∞

• F (x) gives the area under f (x) to the left of x

• 0 ≤ F (x) ≤ 1
• Note that the function F (x) is non-decreasing

9 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Cumulative Distribution Function

Definition
The cumulative distribution function cdf F (x) for a continuous random
variable X is defined for every number x by
Zx
F (x) = P (X ≤ x) = f (s)ds
−∞

From the definition of cdf , we have the following results

• f (x) = F 0 (x)
Rb
• For a < b, P (a ≤ X ≤ b) = f (x)dx = F (b) − F (a)
a
Ra
• P (X ≤ a) = f (x)dx = F (a)
−∞
R∞
• P (X > a) = f (x)dx = 1 − F (a)
a 10 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Mean of a Continuous Random Variable

Definition
The expectation or the mean of a continuous random variable X with the
probability density function f (x) is given by
Z∞
µ = xf (x)dx
−∞

• Mean gives a measure of the centre of the distribution

• On the contrary, in the discrete case mean is given by the
summation

11 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Moments of a Continuous Random Variable

Definition
The nth moment of a continuous random variable X with the probability
density function f (x) is given by
Z∞
µn = xn f (x)dx
−∞

12 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Variance of a Continuous Random Variable

Definition
The variance of a continuous random variable X with the probability
density function f (x) and mean µ is given by
Z∞ Z∞
σ 2 = (x − µ)2 f (x)dx = x2 f (x)dx − µ2
−∞ −∞

• Variance is a measure of the spreadness of the distribution

√
• The standard deviation of X is given by σ

13 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Example Problems

Example
If a random variable has the probability density given by
(
2e−2x , x >0
f (x) =
0, x≤0

Find the probabilities that it will take on a value

• Between −1 and 3
• Greater than 0.5
• Less than or equal to 1

14 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Example Problems

Example
If a random variable has the probability density given by
(
2e−2x , x >0
f (x) =
0, x≤0

• Find the mean of the random variable

• Find the variance of the random variable

15 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Example Problems

Example
The probability of a random variable taking values between −∞ and ∞
is given as 1. For the given probability density function f (x), find the
value of k. (
0, x≤0
f (x) =
kxe−4x 2 , x > 0

16 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Example Problems

Example
In a certain city, the daily consumption of electric power is a random
variable having the probability density
(
1
xe − x3 , x >0
9
f (x) =
0, x≤0

If the city’s power plant has a daily capacity of 12 million kilowatt-hours,

what is the probability that this power supply will be inadequate on any
given day ?

17 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Example Problems

Example
The phase error in a tracking device has probability density given by
(
cos(x), 0 < x < π
f (x) = 2
0, elsewhere

Find the probability that the phase error is

π
• Between 0 and 4
π
• Greater than 4

18 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Uniform Distribution Function

Definition
A continuous random variable X has a uniform distribution, if its
probability density function is
(
1
b−a , a≤x≤b
f (x) =
0, elsewhere

• Here a and b are constants

• Note that there are an infinite number of possible constants a and
b This implies that there are an infinite number of uniform
distributions
• The most commonly used uniform distribution is the one for which
a = 0 and b = 1

19 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Uniform Distribution Function

Figure: The graph of uniform probability density function. Image

courtesy: http://math.tutorvista.com/statistics/uniform-distribution.html

Rb Rb
• P (a ≤ X ≤ b) = f (x)dx = b−a
1 dx =
a a
1
• Therefore the area under the curve f (x) and above the line
bounded by a and b is 1
• Each point in [a, b] is equally likely to be a value of X
• All intervals of equal length have equal probability of occurrence 20 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Uniform Distribution Function

• If [c, d] ⊂ [a, b], then then probability that X lies in any subinterval
[c, d] is given by

Zd Zd
1 d−c
P (c ≤ X ≤ d) = f (x)dx = dx =
b−a b−a
c c

21 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Mean and Moments of a Uniform Distribution Function

Definition
The mean of a uniform random variable X is
Z∞ Zb
x a +b
µ = xf (x)dx = dx =
b−a 2
−∞ a

Definition
The nth moment of a random variable X with uniform probability density
function f (x) is given by

Z∞ Zb
µn = xn f (x)dx = xn 1 bn+1− bn+1
dx =
b−a n +1 b−a
−∞ a

22 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Variance of a Uniform Distribution Function

Definition
The variance of a uniform random variable X is
Z∞ Zb
1 1
σ2 = (x − µ)2 f (x)dx = (x − µ)2 dx = (b − a)2
b−a 12
−∞ a

23 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Cumulative Distribution Function

Definition
The cumulative distribution function F (x) of a random variable X with
uniform probability density function f (x) is given by

Zx 0, x<a
F (x) = f (t)dt = x−a ,
b−a
a≤x≤b
−∞ 1, x >b

Figure: The graph of uniform cumulative distribution function.

24 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Uniform Distribution Function - Examples

Example
The current (in mA) measured in a piece of copper wire is known to
follow a uniform distribution over the interval [0, 25].
• Write down the formula for the probability density function f (x) of
the random variable X representing the current.
• Calculate the mean and variance of the distribution
• Find the cumulative distribution function F (x).

25 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Uniform Distribution Function - Examples

Example
The thickness x of a protective coating applied to a conductor designed
to work in corrosive conditions follows a uniform distribution over the
interval [20, 40] microns.
• Find the mean, standard deviation and cumulative distribution
function of the thickness of the protective coating.
• Find also the probability that the coating is less than 35 microns
thick.

26 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Exponential Distribution Function

Definition
A continuous random variable X has an exponential distribution with
parameter λ, if its probability density function is
(
− βx
1
βe , x ≥ 0; β > 0
f (x, λ) =
0, x < 0

• The exponential distribution is usually used to model the time until

something happens in the process
• It is also used as a survival distribution for an item which remains as
good as new during its lifetime
• Describes the arrival time of a randomly recurring independent
event sequence (Poisson processes)
• When β = 1, we then call it as standard exponential distribution
function
27 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Mean and Moments of an Exponential Distribution

Function
Definition
The mean of an exponential random variable X is
Z∞ Z∞
1 − βx
µ = xf (x)dx = x e dx = β
β
−∞ 0

Definition
The nth moment of a random variable X with exponential probability
density function f (x) is given by
Z∞ Z∞
xn f (x)dx = 1− x
µn = xn e β dx = n!β n
β
−∞ 0

28 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Variance of an Exponential Distribution Function

Definition
The variance of an exponential random variable X is
Z∞ Z∞
1
σ2 = (x − µ)2 f (x)dx = (x − µ)2 e− β dx = β 2
x

β
−∞ 0

29 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Cumulative Distribution Function

Definition
The cumulative distribution function F (x) of a random variable X with
exponential probability density function f (x) is given by
Zx (
1 − e−x/β , x ≥ 0; β > 0
F (x; β) = f (t)dt =
0, x <0
−∞

30 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Exponential Distribution Function - Problems

Example
Let X be a random variable that gives the amount of time (in minutes) a
postal section officer spends with his/her customer. The time is known
to have an exponential distribution with the average amount of time
equal to 4 minutes.
• Find the mean, variance and standard deviation of X
• Find the probability density function
• Find the probability that a clerk spends four to five minutes with a
randomly selected customer

31 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Exponential Distribution Function - Problems

Example
On the average, a certain computer part lasts 10 years. The length of
time the computer part lasts is exponentially distributed.
• What is the probability that a computer part lasts more than 7 years
?
• On the average, how long would 5 computer parts last if they are
used one after another ?
• What is the probability that a computer part lasts between 9 and 11
years ?

32 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Exponential Distribution Function - Problems

Example
Suppose that the length of a phone call, in minutes is an exponential
random variable with decay parameter 1/12. If another person arrives at a
public telephone just before you, find the probability that you will have to
wait more than 5 minutes.

33 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Exponential Distribution Function - Problems

Example
Consider the example of births at a country hospital, in which we assume
that the time between successive births, T , has an exponential
distribution with rate 1/7. What is the chance that there is a birth in the
next 10 days? 10 hours? 10 minutes?

34 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Gamma Distribution Function

For α > 0, the Gamma function is defined as

Z∞
Γ(α) = xα−1 e−x dx
0

The following are some of the properties of the Gamma function

• Γ(α) = (α − 1)Γ(α − 1)

•
For an integer n, Γ(n) = (n − 1)!
√
• Γ( 12 ) = π

35 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Gamma Distribution Function

Definition
A continuous random variable X is said to have a Gamma distribution
function if its probability density function is
(
1
β α Γ(α) x
(α−1) −x/β
e ,x ≥ 0
f (x; α, β) =
0, x < 0

• If β = 1, we get the standard gamma distribution function

• Here parameters α and β satisfy α > 0 and β > 0
• If we choose α = 1 we get the exponential distribution function

36 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Mean and Moments of a Gamma Distribution Function

Definition
The mean of a random variable X with gamma pdf is given by
Z∞
µ = xf (x)dx = αβ
−∞

37 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Variance of a Gamma Distribution Function

Definition
The variance of a random variable X with gamma pdf is given by
Z∞
σ 2 = (x − µ)2 f (x)dx = αβ 2
−∞

38 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Cumulative Distribution Function

Definition
The cumulative distribution function F (x) of a random variable X with a
standard gamma distribution is given by
Zx Zx α−1 −y
y e
F (x; α) = f (t)dt = dy, x > 0 = P (X ≤ x)
Γ(α)
−∞ 0

• F (x; α) is called incomplete gamma function

• Extensive tables of F (x; α) are available
• Note: The incomplete gamma function can also be used to compute
probabilities involving non-standard gamma distributions with given
α and β values. F (x; α, β) = F (x/β; α)

39 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Gamma Distribution Function: Examples

Example
Suppose the reaction time X of a randomly selected individual to a
certain stimulus has a standard gamma distribution with α = 2. What is
the probability that the reaction time is more than 4 seconds ?

40 /41
Continuous Random Variables and Properties Uniform Distribution Exponential Distribution Gamma Distribution

Gamma Distribution Function: Examples

Example
Suppose the survival time X in weeks of a randomly selected mouse
exposed to 240 rads of gamma radiation has a gamma distribution with
α = 8 and β = 15.
• Find the mean survival time

• Find the variance and standard deviation

• Find the probability that a mouse survives between 60 and 120
weeks

• Find the probability that a mouse survives at least 30 weeks

41 /41
Gamma Distribution Normal Distribution Beta Distribution

Probability
274/ 26 & Statistics

BITS Pilani, Hyderabad Campus

Lecture - 10
Course Number: AAOC ZC111
[email protected]

February 11, 2017

Gamma Distribution Normal Distribution Beta Distribution

Outline
275/ 26

Gamma Distribution

Normal Distribution

Beta Distribution
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function

276/ 26

For α > 0, the Gamma function is defined as

Z∞
Γ(α) = xα− 1e− x dx
0

The following are some of the properties of the Gamma function

• Γ(α) = (α − 1)Γ(α − 1)

• For an integer n, Γ(n) = (n − 1)!

√
• Γ( 1 ) = π
2
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function

277/ 26

Definition
A continuous random variable X is said to have a Gamma distribution
function if its probability density function is
(
β α Γ1(α) x(α− 1) e− x /β , x ≥ 0
f (x; α, β) = 0,
x< 0

• If β = 1, we get the standard gamma distribution function

• Here parameters α and β satisfy α > 0 and β > 0

• If we choose α = 1 we get the exponential distribution function

( 1
− x /β , x ≥ 0
βe
f (x; α, β) =
0, x< 0
Gamma Distribution Normal Distribution Beta Distribution

Mean and Moments of a Gamma Distribution Function

278/ 26

Definition
The mean of a random variable X with gamma pdf is given by

Z∞
µ= xf (x)dx = αβ
−∞
Gamma Distribution Normal Distribution Beta Distribution

Variance of a Gamma Distribution Function

279/ 26

Definition
The variance of a random variable X with gamma pdf is given by

Z∞
σ2 = (x − µ) 2f (x)dx = αβ2
−∞
Gamma Distribution Normal Distribution Beta Distribution

Cumulative Distribution Function

280/ 26

Definition
The cumulative distribution function F (x) of a random variable X with a
standard gamma distribution (β = 1) is given by
x
x Z
yα− 1e− y
F (x; α) = P (X ≤ x) = Z f (t)dt = dy, x > 0
Γ(α)
−∞ 0

• F (x; α) is called incomplete gamma function

• It is called incomplete as the limits are from 0 to x instead of 0 to ∞

• Extensive tables of F (x; α) are available

• Note: The incomplete gamma function can also be used to compute

probabilities involving non-standard gamma distributions with given
α and β values. F (x; α, β) = F (x/β; α)
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function: Examples

281/ 26

Example
Suppose the reaction time X of a randomly selected individual to a
certain stimulus has a standard gamma distribution with α = 2. What is
the probability that the reaction time is more than 4 seconds ?
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function: Examples

282/ 26

Example
Suppose the survival time X in weeks of a randomly selected mouse
exposed to 240 rads of gamma radiation has a gamma distribution with
α = 8 and β = 15.
• Find the mean survival time

• Find the variance and standard deviation

• Find the probability that a mouse survives between 60 and 120

weeks

• Find the probability that a mouse survives at least 30 weeks

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

283/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

•
−∞ < µ < ∞ and σ > 0

• The mean of a random variable X with normal pdf is given by µ

• The variance of a random variable X with normal pdf is given by σ 2

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

284/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

• A random variable X following a normal distribution is often
denoted by X ∼ N (µ, σ 2)

• Therefore, a normal distribution is completely defined by specifying

its mean and variance

• Since µ and σ 2 can both vary, there are infinitely many normal
distributions
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

285/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

• Evaluating the probabilities require the definite integrals over the
pdf, f (x; µ, σ)

• Unfortunately, closed form expressions for the definite integrals are

not available

• However, approximate values are tabulated

• Note: Since µ and σ 2 can take any values, it is impossible to give
tabulated values for all normal distributions
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Function

286/ 26

• A normal distribution with parameters µ = 0 and σ = 1 is called the

standard normal distribution

• The standard normal random variable is denoted by Z

• The corresponding pdf is given by

1 (z )2
f (z) = √ e− 2
, −∞ < z < ∞
2π

• The cumulative distribution function cdf denoted by F (z) is defined

by
z

F (z) = P (Z ≤ z) = Z f (y)dy
−∞

• It gives the area of the curve to the left of z

Gamma Distribution Normal Distribution Beta Distribution

Properties of Standard Normal Distribution Function

287/ 26

Figure: The graph of standard normal distribution

• The z curve is bell shaped and is symmetric about the mean µ

• Therefore, the area to the left of µ = the area to the right of µ
• Mean determines the center of the curve
• Standard deviation determines how flat the curve is
•
Larger σ values result in flatter curves
Gamma Distribution Normal Distribution Beta Distribution

Properties of Standard Normal Distribution Function

288/ 26

Figure: The graph of standard normal distribution

• The interval µ ± σ covers 68% of the distribution

• The interval µ ± 2σ covers 95% of the distribution
• The interval µ ± 3σ covers 99.7% of the distribution
Gamma Distribution Normal Distribution Beta Distribution

Standard and Non-Standard Normal Distributions

289/ 26

• A random variable following a non-standard normal distribution is

given by X ∼ N (µ, σ 2)

• A random variable following the standard normal distribution is

given by Z ∼ N (0, 1)

• How to convert X to Z ?

• The relationship between standard and non-standard normal

distributions is given by
X −µ
Z =
σ
Gamma Distribution Normal Distribution Beta Distribution

Standard and Non-Standard Normal Distributions

290/ 26

• We then have the following results

a− µ b− µ b− µ a− µ
P (a ≤ X ≤ b) = P ≤Z ≤ = F −F
σ σ o σ
a− µ
• P (X ≤ a) = F
o
b− µ
•
P (X ≥ b) = 1 − F σ
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Table

STANDARD NORMAL DISTRIBUTION: Table Values Represent AREA to the LEFT of the Z score.
Z .00 .01 .02 .03 .04 .05 .06 .07 .08 .09
-3.9 .00005 .00005 .00004 .00004 .00004 .00004 .00004 .00004 .00003 .00003
-3.8 .00007 .00007 .00007 .00006 .00006 .00006 .00006 .00005 .00005 .00005
-3.7 .00011 .00010 .00010 .00010 .00009 .00009 .00008 .00008 .00008 .00008
-3.6 .00016 .00015 .00015 .00014 .00014 .00013 .00013 .00012 .00012 .00011
-3.5 .00023 .00022 .00022 .00021 .00020 .00019 .00019 .00018 .00017 .00017
-3.4 .00034 .00032 .00031 .00030 .00029 .00028 .00027 .00026 .00025 .00024
-3.3 .00048 .00047 .00045 .00043 .00042 .00040 .00039 .00038 .00036 .00035
-3.2 .00069 .00066 .00064 .00062 .00060 .00058 .00056 .00054 .00052 .00050
-3.1 .00097 .00094 .00090 .00087 .00084 .00082 .00079 .00076 .00074 .00071
-3.0 .00135 .00131 .00126 .00122 .00118 .00114 .00111 .00107 .00104 .00100
-2.9 .00187 .00181 .00175 .00169 .00164 .00159 .00154 .00149 .00144 .00139
-2.8 .00256 .00248 .00240 .00233 .00226 .00219 .00212 .00205 .00199 .00193
-2.7 .00347 .00336 .00326 .00317 .00307 .00298 .00289 .00280 .00272 .00264
-2.6 .00466 .00453 .00440 .00427 .00415 .00402 .00391 .00379 .00368 .00357
-2.5 .00621 .00604 .00587 .00570 .00554 .00539 .00523 .00508 .00494 .00480
-2.4 .00820 .00798 .00776 .00755 .00734 .00714 .00695 .00676 .00657 .00639
-2.3 .01072 .01044 .01017 .00990 .00964 .00939 .00914 .00889 .00866 .00842
-2.2 .01390 .01355 .01321 .01287 .01255 .01222 .01191 .01160 .01130 .01101
-2.1 .01786 .01743 .01700 .01659 .01618 .01578 .01539 .01500 .01463 .01426
-2.0 .02275 .02222 .02169 .02118 .02068 .02018 .01970 .01923 .01876 .01831
-1.9 .02872 .02807 .02743 .02680 .02619 .02559 .02500 .02442 .02385 .02330 18/ 26
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Table

STANDARD NORMAL DISTRIBUTION: Table Values Represent AREA to the LEFT of the Z score.
Z .00 .01 .02 .03 .04 .05 .06 .07 .08 .09
0.0 .50000 .50399 .50798 .51197 .51595 .51994 .52392 .52790 .53188 .53586
0.1 .53983 .54380 .54776 .55172 .55567 .55962 .56356 .56749 .57142 .57535
0.2 .57926 .58317 .58706 .59095 .59483 .59871 .60257 .60642 .61026 .61409
0.3 .61791 .62172 .62552 .62930 .63307 .63683 .64058 .64431 .64803 .65173
0.4 .65542 .65910 .66276 .66640 .67003 .67364 .67724 .68082 .68439 .68793
0.5 .69146 .69497 .69847 .70194 .70540 .70884 .71226 .71566 .71904 .72240
0.6 .72575 .72907 .73237 .73565 .73891 .74215 .74537 .74857 .75175 .75490
0.7 .75804 .76115 .76424 .76730 .77035 .77337 .77637 .77935 .78230 .78524
0.8 .78814 .79103 .79389 .79673 .79955 .80234 .80511 .80785 .81057 .81327
0.9 .81594 .81859 .82121 .82381 .82639 .82894 .83147 .83398 .83646 .83891
1.0 .84134 .84375 .84614 .84849 .85083 .85314 .85543 .85769 .85993 .86214
1.1 .86433 .86650 .86864 .87076 .87286 .87493 .87698 .87900 .88100 .88298
1.2 .88493 .88686 .88877 .89065 .89251 .89435 .89617 .89796 .89973 .90147
1.3 .90320 .90490 .90658 .90824 .90988 .91149 .91309 .91466 .91621 .91774
1.4 .91924 .92073 .92220 .92364 .92507 .92647 .92785 .92922 .93056 .93189
1.5 .93319 .93448 .93574 .93699 .93822 .93943 .94062 .94179 .94295 .94408
1.6 .94520 .94630 .94738 .94845 .94950 .95053 .95154 .95254 .95352 .95449
1.7 .95543 .95637 .95728 .95818 .95907 .95994 .96080 .96164 .96246 .96327
1.8 .96407 .96485 .96562 .96638 .96712 .96784 .96856 .96926 .96995 .97062
1.9 .97128 .97193 .97257 .97320 .97381 .97441 .97500 .97558 .97615 .97670
2.0 .97725 .97778 .97831 .97882 .97932 .97982 .98030 .98077 .98124 .98169 19/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

293/ 26

Example
X is a normally distributed variable with mean µ = 30 and standard
deviation σ = 4.

• Find P (X < 40)

• Find P (X > 21)

• Find P (30 < X < 35)

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

294/ 26

Example
The annual salaries of employees in a large company are approximately
normally distributed with a mean of Rs. 50, 000 and a standard deviation
of Rs. 20, 000.
• What percent of people earn less than Rs. 40, 000 ?

• What percent of people earn between Rs. 45, 000 and Rs. 65, 000 ?

• What percent of people earn more than Rs. 70, 000 ?

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

Example
Suppose that the height X in inches of a person is a normal random
variable with mean µ = 70 inches. If P (X > 79) = 0.025, what is the
standard deviation of this random normal variable ?

22/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

Example
Suppose that the height X in inches of a person is a normal random
variable with mean µ = 70 inches. If P (X > 79) = 0.025, what is the
standard deviation of this random normal variable ?

Example
Suppose that the weight (X ) in pounds of a person is a normal random
variable with standard deviation σ = 20 pounds. If 5% of the population
is heavier than 214 pounds what is the mean of this distribution ?

22/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

23/ 26

Example
A bag of cookies is underweight if it weighs less than 500 grams. The
filling process dispenses cookies with weight that follows the normal
distribution with mean 510 grams and standard deviation 4 grams.
• What is the probability that a randomly selected bag is underweight?

• If you randomly select 5 bags, what is the probability that exactly 2

of them will be underweight?
Gamma Distribution Normal Distribution Beta Distribution

Beta Distribution Function

24/ 26

Definition
When a random variable takes values on the interval from 0 and 1, one
choice of a probability density function is the beta distribution function,
given by
( α− 1 β− 1
ΓΓ(α)Γ (β) x
(α+β) (1 − x) , 0 < x < 1, α > 0, β > 0
f (x) =
0, elsewhere

• When α = 1 and β = 1, we obtain the uniform distribution function

Gamma Distribution Normal Distribution Beta Distribution

Mean and Variance of Beta Distribution Function

25/ 26

Definition
The mean of a random variable with beta distribution is given by
α
µ=
α+ β

Definition
The variance of a random variable with beta distribution is given by
αβ
σ2 =
(α + β) 2(α + β + 1)
Gamma Distribution Normal Distribution Beta Distribution

Beta Distribution Function: Examples

26/ 26

Example
In a certain county, the proportion of highway sections requiring repairs
in any given year is a random variable having the beta distribution with
α = 3 and β = 2.
• On the average, what percentage of the highway sections require
repairs in any given year ?

• Find the probability that at most half of the highway sections will
require repairs in any given year.
Gamma Distribution Normal Distribution Beta Distribution

Probability
301/ 26 & Statistics

BITS Pilani, Hyderabad Campus

Lecture - 10
Course Number: AAOC ZC111
[email protected]

February 11, 2017

Gamma Distribution Normal Distribution Beta Distribution

Outline
302/ 26

Gamma Distribution

Normal Distribution

Beta Distribution
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function

303/ 26

For α > 0, the Gamma function is defined as

Z∞
Γ(α) = xα− 1e− x dx
0

The following are some of the properties of the Gamma function

• Γ(α) = (α − 1)Γ(α − 1)

• For an integer n, Γ(n) = (n − 1)!

√
• Γ( 1 ) = π
2
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function

304/ 26

Definition
A continuous random variable X is said to have a Gamma distribution
function if its probability density function is
(
β α Γ1(α) x(α− 1) e− x /β , x ≥ 0
f (x; α, β) = 0,
x< 0

• If β = 1, we get the standard gamma distribution function

• Here parameters α and β satisfy α > 0 and β > 0

• If we choose α = 1 we get the exponential distribution function

( 1
− x /β , x ≥ 0
βe
f (x; α, β) =
0, x< 0
Gamma Distribution Normal Distribution Beta Distribution

Mean and Moments of a Gamma Distribution Function

305/ 26

Definition
The mean of a random variable X with gamma pdf is given by

Z∞
µ= xf (x)dx = αβ
−∞
Gamma Distribution Normal Distribution Beta Distribution

Variance of a Gamma Distribution Function

306/ 26

Definition
The variance of a random variable X with gamma pdf is given by

Z∞
σ2 = (x − µ) 2f (x)dx = αβ2
−∞
Gamma Distribution Normal Distribution Beta Distribution

Cumulative Distribution Function

307/ 26

Definition
The cumulative distribution function F (x) of a random variable X with a
standard gamma distribution (β = 1) is given by
x
x Z
yα− 1e− y
F (x; α) = P (X ≤ x) = Z f (t)dt = dy, x > 0
Γ(α)
−∞ 0

• F (x; α) is called incomplete gamma function

• It is called incomplete as the limits are from 0 to x instead of 0 to ∞

• Extensive tables of F (x; α) are available

• Note: The incomplete gamma function can also be used to compute

probabilities involving non-standard gamma distributions with given
α and β values. F (x; α, β) = F (x/β; α)
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function: Examples

308/ 26

Example
Suppose the reaction time X of a randomly selected individual to a
certain stimulus has a standard gamma distribution with α = 2. What is
the probability that the reaction time is more than 4 seconds ?
Gamma Distribution Normal Distribution Beta Distribution

Gamma Distribution Function: Examples

309/ 26

Example
Suppose the survival time X in weeks of a randomly selected mouse
exposed to 240 rads of gamma radiation has a gamma distribution with
α = 8 and β = 15.
• Find the mean survival time

• Find the variance and standard deviation

• Find the probability that a mouse survives between 60 and 120

weeks

• Find the probability that a mouse survives at least 30 weeks

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

310/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

•
−∞ < µ < ∞ and σ > 0

• The mean of a random variable X with normal pdf is given by µ

• The variance of a random variable X with normal pdf is given by σ 2

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

311/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

• A random variable X following a normal distribution is often
denoted by X ∼ N (µ, σ 2)

• Therefore, a normal distribution is completely defined by specifying

its mean and variance

• Since µ and σ 2 can both vary, there are infinitely many normal
distributions
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution Function

312/ 26

Definition
A continuous random variable X is said to have a normal distribution
with parameters µ and σ, if the probability density function (pdf) of X is
(x − µ )2
f (x; µ, σ) = √1 e
−
2σ 2 ,∞ < x < ∞
o 2π

The following are some of the properties of the normal distribution

• Evaluating the probabilities require the definite integrals over the
pdf, f (x; µ, σ)

• Unfortunately, closed form expressions for the definite integrals are

not available

• However, approximate values are tabulated

• Note: Since µ and σ 2 can take any values, it is impossible to give
tabulated values for all normal distributions
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Function

313/ 26

• A normal distribution with parameters µ = 0 and σ = 1 is called the

standard normal distribution

• The standard normal random variable is denoted by Z

• The corresponding pdf is given by

1 (z )2
f (z) = √ e− 2
, −∞ < z < ∞
2π

• The cumulative distribution function cdf denoted by F (z) is defined

by
z

F (z) = P (Z ≤ z) = Z f (y)dy
−∞

• It gives the area of the curve to the left of z

Gamma Distribution Normal Distribution Beta Distribution

Properties of Standard Normal Distribution Function

314/ 26

Figure: The graph of standard normal distribution

• The z curve is bell shaped and is symmetric about the mean µ

• Therefore, the area to the left of µ = the area to the right of µ
• Mean determines the center of the curve
• Standard deviation determines how flat the curve is
•
Larger σ values result in flatter curves
Gamma Distribution Normal Distribution Beta Distribution

Properties of Standard Normal Distribution Function

315/ 26

Figure: The graph of standard normal distribution

• The interval µ ± σ covers 68% of the distribution

• The interval µ ± 2σ covers 95% of the distribution
• The interval µ ± 3σ covers 99.7% of the distribution
Gamma Distribution Normal Distribution Beta Distribution

Standard and Non-Standard Normal Distributions

316/ 26

• A random variable following a non-standard normal distribution is

given by X ∼ N (µ, σ 2)

• A random variable following the standard normal distribution is

given by Z ∼ N (0, 1)

• How to convert X to Z ?

• The relationship between standard and non-standard normal

distributions is given by
X −µ
Z =
σ
Gamma Distribution Normal Distribution Beta Distribution

Standard and Non-Standard Normal Distributions

317/ 26

• We then have the following results

a− µ b− µ b− µ a− µ
P (a ≤ X ≤ b) = P ≤Z ≤ = F −F
σ σ o σ
a− µ
• P (X ≤ a) = F
o
b− µ
•
P (X ≥ b) = 1 − F σ
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Table

STANDARD NORMAL DISTRIBUTION: Table Values Represent AREA to the LEFT of the Z score.
Z .00 .01 .02 .03 .04 .05 .06 .07 .08 .09
-3.9 .00005 .00005 .00004 .00004 .00004 .00004 .00004 .00004 .00003 .00003
-3.8 .00007 .00007 .00007 .00006 .00006 .00006 .00006 .00005 .00005 .00005
-3.7 .00011 .00010 .00010 .00010 .00009 .00009 .00008 .00008 .00008 .00008
-3.6 .00016 .00015 .00015 .00014 .00014 .00013 .00013 .00012 .00012 .00011
-3.5 .00023 .00022 .00022 .00021 .00020 .00019 .00019 .00018 .00017 .00017
-3.4 .00034 .00032 .00031 .00030 .00029 .00028 .00027 .00026 .00025 .00024
-3.3 .00048 .00047 .00045 .00043 .00042 .00040 .00039 .00038 .00036 .00035
-3.2 .00069 .00066 .00064 .00062 .00060 .00058 .00056 .00054 .00052 .00050
-3.1 .00097 .00094 .00090 .00087 .00084 .00082 .00079 .00076 .00074 .00071
-3.0 .00135 .00131 .00126 .00122 .00118 .00114 .00111 .00107 .00104 .00100
-2.9 .00187 .00181 .00175 .00169 .00164 .00159 .00154 .00149 .00144 .00139
-2.8 .00256 .00248 .00240 .00233 .00226 .00219 .00212 .00205 .00199 .00193
-2.7 .00347 .00336 .00326 .00317 .00307 .00298 .00289 .00280 .00272 .00264
-2.6 .00466 .00453 .00440 .00427 .00415 .00402 .00391 .00379 .00368 .00357
-2.5 .00621 .00604 .00587 .00570 .00554 .00539 .00523 .00508 .00494 .00480
-2.4 .00820 .00798 .00776 .00755 .00734 .00714 .00695 .00676 .00657 .00639
-2.3 .01072 .01044 .01017 .00990 .00964 .00939 .00914 .00889 .00866 .00842
-2.2 .01390 .01355 .01321 .01287 .01255 .01222 .01191 .01160 .01130 .01101
-2.1 .01786 .01743 .01700 .01659 .01618 .01578 .01539 .01500 .01463 .01426
-2.0 .02275 .02222 .02169 .02118 .02068 .02018 .01970 .01923 .01876 .01831
-1.9 .02872 .02807 .02743 .02680 .02619 .02559 .02500 .02442 .02385 .02330 18/ 26
Gamma Distribution Normal Distribution Beta Distribution

Standard Normal Distribution Table

STANDARD NORMAL DISTRIBUTION: Table Values Represent AREA to the LEFT of the Z score.
Z .00 .01 .02 .03 .04 .05 .06 .07 .08 .09
0.0 .50000 .50399 .50798 .51197 .51595 .51994 .52392 .52790 .53188 .53586
0.1 .53983 .54380 .54776 .55172 .55567 .55962 .56356 .56749 .57142 .57535
0.2 .57926 .58317 .58706 .59095 .59483 .59871 .60257 .60642 .61026 .61409
0.3 .61791 .62172 .62552 .62930 .63307 .63683 .64058 .64431 .64803 .65173
0.4 .65542 .65910 .66276 .66640 .67003 .67364 .67724 .68082 .68439 .68793
0.5 .69146 .69497 .69847 .70194 .70540 .70884 .71226 .71566 .71904 .72240
0.6 .72575 .72907 .73237 .73565 .73891 .74215 .74537 .74857 .75175 .75490
0.7 .75804 .76115 .76424 .76730 .77035 .77337 .77637 .77935 .78230 .78524
0.8 .78814 .79103 .79389 .79673 .79955 .80234 .80511 .80785 .81057 .81327
0.9 .81594 .81859 .82121 .82381 .82639 .82894 .83147 .83398 .83646 .83891
1.0 .84134 .84375 .84614 .84849 .85083 .85314 .85543 .85769 .85993 .86214
1.1 .86433 .86650 .86864 .87076 .87286 .87493 .87698 .87900 .88100 .88298
1.2 .88493 .88686 .88877 .89065 .89251 .89435 .89617 .89796 .89973 .90147
1.3 .90320 .90490 .90658 .90824 .90988 .91149 .91309 .91466 .91621 .91774
1.4 .91924 .92073 .92220 .92364 .92507 .92647 .92785 .92922 .93056 .93189
1.5 .93319 .93448 .93574 .93699 .93822 .93943 .94062 .94179 .94295 .94408
1.6 .94520 .94630 .94738 .94845 .94950 .95053 .95154 .95254 .95352 .95449
1.7 .95543 .95637 .95728 .95818 .95907 .95994 .96080 .96164 .96246 .96327
1.8 .96407 .96485 .96562 .96638 .96712 .96784 .96856 .96926 .96995 .97062
1.9 .97128 .97193 .97257 .97320 .97381 .97441 .97500 .97558 .97615 .97670
2.0 .97725 .97778 .97831 .97882 .97932 .97982 .98030 .98077 .98124 .98169 19/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

320/ 26

Example
X is a normally distributed variable with mean µ = 30 and standard
deviation σ = 4.

• Find P (X < 40)

• Find P (X > 21)

• Find P (30 < X < 35)

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

321/ 26

Example
The annual salaries of employees in a large company are approximately
normally distributed with a mean of Rs. 50, 000 and a standard deviation
of Rs. 20, 000.
• What percent of people earn less than Rs. 40, 000 ?

• What percent of people earn between Rs. 45, 000 and Rs. 65, 000 ?

• What percent of people earn more than Rs. 70, 000 ?

Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

Example
Suppose that the height X in inches of a person is a normal random
variable with mean µ = 70 inches. If P (X > 79) = 0.025, what is the
standard deviation of this random normal variable ?

22/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

Example
Suppose that the height X in inches of a person is a normal random
variable with mean µ = 70 inches. If P (X > 79) = 0.025, what is the
standard deviation of this random normal variable ?

Example
Suppose that the weight (X ) in pounds of a person is a normal random
variable with standard deviation σ = 20 pounds. If 5% of the population
is heavier than 214 pounds what is the mean of this distribution ?

22/ 26
Gamma Distribution Normal Distribution Beta Distribution

Normal Distribution: Problems

23/ 26

Example
A bag of cookies is underweight if it weighs less than 500 grams. The
filling process dispenses cookies with weight that follows the normal
distribution with mean 510 grams and standard deviation 4 grams.
• What is the probability that a randomly selected bag is underweight?

• If you randomly select 5 bags, what is the probability that exactly 2

of them will be underweight?
Gamma Distribution Normal Distribution Beta Distribution

Beta Distribution Function

24/ 26

Definition
When a random variable takes values on the interval from 0 and 1, one
choice of a probability density function is the beta distribution function,
given by
( α− 1 β− 1
ΓΓ(α)Γ (β) x
(α+β) (1 − x) , 0 < x < 1, α > 0, β > 0
f (x) =
0, elsewhere

• When α = 1 and β = 1, we obtain the uniform distribution function

Gamma Distribution Normal Distribution Beta Distribution

Mean and Variance of Beta Distribution Function

25/ 26

Definition
The mean of a random variable with beta distribution is given by
α
µ=
α+ β

Definition
The variance of a random variable with beta distribution is given by
αβ
σ2 =
(α + β) 2(α + β + 1)
Gamma Distribution Normal Distribution Beta Distribution

Beta Distribution Function: Examples

26/ 26

Example
In a certain county, the proportion of highway sections requiring repairs
in any given year is a random variable having the beta distribution with
α = 3 and β = 2.
• On the average, what percentage of the highway sections require
repairs in any given year ?

• Find the probability that at most half of the highway sections will
require repairs in any given year.