Systems Engineering Program

Department of Engineering Management, Information and Systems

EMIS 7370/5370 STAT 5340 :

PROBABILITY AND STATISTICS FOR SCIENTISTS AND ENGINEERS

Special Continuous Probability Distributions

-Exponential Distribution
-Weibull Distribution

Dr. Jerrell T. Stracener, SAE Fellow

Leadership in Engineering
1
Stracener_EMIS 7370/STAT 5340_Fall 08_09.25.08
Exponential Distribution

2
 The Exponential Model - Definition

A random variable X is said to have the Exponential

Distribution with parameters , where  > 0, if the
probability density function of X is:

x
1 

e
f ( x)   , for x 0

0 , elsewhere

3
 Properties of the Exponential Model

• Probability Distribution Function

0 for x< 0
F (x)  P(X  x) 
x

 for x  0
1- e

*Note: the Exponential Distribution is said to be

without memory, i.e.

• P(X > x1 + x2 | X > x1) = P(X > x2)

4
 Properties of the Exponential Model

• Mean or Expected Value

  E (X )  
• Standard Deviation

 

5
 Exponential Model - Example

Suppose the response time X at a certain on-line computer

terminal (the elapsed time between the end of a user’s
inquiry and the beginning of the system’s response to that
inquiry) has an exponential distribution with expected
response time equal to 5 sec.

(a) What is the probability that the response time is at most 10

seconds?

(b) What is the probability that the response time is between 5 and 10
seconds?

(c) What is the value of x for which the probability of exceeding that
value is 1%?

6
 Exponential Model - Example
The E(X) = 5=θ, so λ = 0.2.
The probability that the response time is at most 10 sec is:
P ( X  10)  F (10,0.2)
 1  e (.2 )(10)
 1  0.135
 0.865
or P (X>10) = 0.135
The probability that the response time is between 5 and 10 sec is:

P(5  X  10)  F (10;0.2)  F (5;0.2)

 (1  e 2 )  (1  e 1 )
 0.233
7
 Exponential Model - Example

The value of x for which the probability of exceeding x is 1%:

P( X  x)  1  e  x  0.99
e x  0.01
 λx  ln( 0.01)
4.605
x
0.2
x  23.025 sec

F (10)  0.99
  N (10)
 1 e
8
Weibull Distribution

9
 The Weibull Probability Distribution Function

•Definition - A random variable X is said to have the

Weibull Probability Distribution with parameters  and ,
where  > 0 and  > 0, if the probability density function of x
is: 
x
  1   
x e
f ( x)   
, forx  0

0
, elsewhere

Where,  is the Shape Parameter,  is the Scale

Parameter. Note: If  = 1, the Weibull reduces to
the Exponential Distribution. 10
The Weibull Probability Distribution Function
Probability Density Function
f(t)
1.8
β=5.0
1.6
1.4 β=0.5 β=3.44
1.2
β=1.0
1.0 β=2.5
0.8
0.6
0.4

0.2
0
0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 2.0 2.2 2.4
t

t is in multiples of 
11
 The Weibull Probability Distribution Function

for x  0 x
β
 
F(x)  PX  x   1 - e θ

F(t) for various  and  = 100

1
5
0.8 3
probability, p

1
F(x) 0.6
  0.5

0.4

0.2

0
0 50 100 150 200
x 12
 Weibull Probability Paper (WPP)
• Derived from double logarithmic transformation of
the Weibull Distribution Function.
 ( t /  )
F(t )  1  e
• Of the form y  ax  b
 
y  ln ln  1  
where
  
  1 F( t )  
a   b   ln  x  ln t
•Any straight line on Weibull Probability paper is a Weibull
Probability Distribution Function with slope,  and intercept,
- ln , where the ordinate is ln{ln(1/[1-F(t)])} the abscissa is
ln t. 13
 Weibull Probability Paper (WPP)

Weibull Probability Paper links

http://perso.easynet.fr/~philimar/graphpapeng.htm

http://www.weibull.com/GPaper/index.htm

14
Use of Weibull Probability Paper
8 4 3 2 1.5 1.0 0.8 0.7 0.5

99.0

95.0

90.0

80.0

70.0

50.0
Cumulative probability in percent 40.0

F(x) 30.0

1.8 in.  

in % 20.0

1 in.
10.0

5.0
4.0
3.0

2.0

1.0

0.5
10 2 3 4 5 6 7 8 9 10 2 3 4 5 6 7 8 9 1000
15

x
 Properties of the Weibull Distribution
• 100pth Percentile 1

x p   - ln(1 - p)


and, in particular
x0.632  
• Mean or Expected Value

1 
  E(X)     1
 
Note: See the Gamma Function Table to
obtain values of (a)
16
 Properties of the Weibull Distribution

• Standard Deviation of X
1
 2  2 1  2
     1     1
     
where

 (a)  (a)
2 2

17
 The Gamma Function 
y=a  (a) a  (a) a  (a) a  (a)
1 1 1.25 0.9064 1.5 0.8862 1.75 0.9191
1.01 0.9943 1.26 0.9044 1.51 0.8866 1.76 0.9214
1.02 0.9888 1.27 0.9025 1.52 0.887 1.77 0.9238
 1.03 0.9836 1.28 0.9007 1.53 0.8876 1.78 0.9262

(a )   e x dx
x a 1 1.04 0.9784 1.29 0.899 1.54 0.8882 1.79 0.9288
1.05 0.9735 1.3 0.8975 1.55 0.8889 1.8 0.9314
1.06 0.9687 1.31 0.896 1.56 0.8896 1.81 0.9341
1.07 0.9642 1.32 0.8946 1.57 0.8905 1.82 0.9369
0 1.08 0.9597 1.33 0.8934 1.58 0.8914 1.83 0.9397
1.09 0.9555 1.34 0.8922 1.59 0.8924 1.84 0.9426

(a  1)  a(a )
1.1 0.9514 1.35 0.8912 1.6 0.8935 1.85 0.9456
1.11 0.9474 1.36 0.8902 1.61 0.8947 1.86 0.9487
1.12 0.9436 1.37 0.8893 1.62 0.8959 1.87 0.9518
1.13 0.9399 1.38 0.8885 1.63 0.8972 1.88 0.9551
1.14 0.9364 1.39 0.8879 1.64 0.8986 1.89 0.9584
1.15 0.933 1.4 0.8873 1.65 0.9001 1.9 0.9618
1.16 0.9298 1.41 0.8868 1.66 0.9017 1.91 0.9652
1.17 0.9267 1.42 0.8864 1.67 0.9033 1.92 0.9688
1.18 0.9237 1.43 0.886 1.68 0.905 1.93 0.9724
Values of the 1.19 0.9209 1.44 0.8858 1.69 0.9068 1.94 0.9761

Gamma Function 1.2

1.21
0.9182
0.9156
1.45
1.46
0.8857
0.8856
1.7
1.71
0.9086
0.9106
1.95
1.96
0.9799
0.9837
1.22 0.9131 1.47 0.8856 1.72 0.9126 1.97 0.9877
1.23 0.9108 1.48 0.8858 1.73 0.9147 1.98 0.9917
1.24 0.9085 1.49 0.886 1.74 0.9168 1.99 0.9958
2 1

18
 Properties of the Weibull Distribution
• Mode - The value of x for which the probability
density function is maximum

i.e., f x mode   max f ( x)

x mode   1  1  
1

f(x) Max f(x)=f(xmode)

0 x
xmode 19
 Weibull Distribution - Example

Let X = the ultimate tensile strength (ksi) at -200

degrees F of a type of steel that exhibits ‘cold
brittleness’ at low temperatures. Suppose X has a
Weibull distribution with parameters  = 20,
and  = 100. Find:

(a) P( X  105)

(b) P(98  X  102)

(c) the value of x such that P( X  x) = 0.10

20
 Weibull Distribution - Example Solution
(a) P( X  105) = F(105; 20, 100)
 (105/100) 20
 1 e  1  0.070  0.930

(b) P(98  X  102)

= F(102; 20, 100) - F(98; 20, 100)

 ( 0.98) 20  (1.02) 20
e e

 0.513  0.226  0.287

21
 Weibull Distribution - Example Solution

(c) P( X  x) = 0.10
 ( x /100) 20
 1 e  0.10
P( X  x)
 ( x / 100) 20
e  0.90
Then
( x / 100) 20   ln 0.90
( x / 100) 20   ln 0.90
x / 100   ln 0.90
1/ 20

x  100 ln 0.90
1/ 20

x  89.36
22
 Weibull Distribution - Example

The random variable X can modeled by a Weibull

distribution with  = ½ and  = 1000. The spec time limit is
set at x = 4000. What is the proportion of items not
meeting spec?

23
 Weibull Distribution - Example

The fraction of items not meeting spec is

PX  4000  1  P( X  4000)

 1  F(4000)
1/2
 4000 
 
e  1000 

2
e
 0.1353
That is, all but about 13.53% of the items will not meet
spec.
24