CLASS Statistics

09 Continuous Random Variables

Continuous rv compared with Discrete rv

Discrete Variable Continuous Variable

Countable support Uncountable support

Probability mass function Probability density function

Probability assigned to Probability assigned to

single values intervals of values

Each possible value has Each possible value has

strictly positive probability zero probability

Comparison between CDF and PDF

Continuous Random Variables:
Probability distribution function (pdf):

P{X B} = f(x)dx

▪ Properties:
∞
1= P{X ϵ(-∞, ∞)} = ∫ f(x)dx
-∞

▪ All probability statements about X can be answered by f(x):

≤ b
P{a ≤ X ≤ b} = ∫ f(x)dx
a

a
P{X = a} = ∫ f(x)dx = 0
a

f(y)

P(a < x ≤ b)
F(t)

y
t a b
PDF

Cumulative distribution function (CDF):

x
F x (x) = P(X ≤ x) = ∫ f x (t)dt, - ∞ < x < ∞
-∞

▪ Properties:
d
F(a) = f(a)
da
▪ Acontinuous function

f(x)

P(a < x ≤ b)

x
t a b
f(t)
CDF

Valid PDF vs CDF

PDF CDF

1 1
x,0≤x≤2
3
(3x - 2), x = 0,1,2,3
f(x) = 4 p(x) = 10
0, otherwise 0, otherwise

∞ 3
1. f(x) ≥ 0 1. Σ p(x=k) = Σ p(x=k) = 1
k=0 k=0

∞ 2
1 -2
2. ∫ f(x)dx = ∫ x dx = 1
3
2. However, p(x=0) = <0
-∞ 0 4 10

Therfore, it is a valid PDF. Therfore, it is not a valid PMF.

Example to find out CDF

b

x - 3; 0 < x < 1 P(a < x < b) = F(b) - F(a) = ∫ f(x)d(x)

a

F(x) = 5 - x; 1< x < 3 2

= F(2) - F(1) = ∫ f(x)d(x)
0; x > 3
1

2
= ∫ f(x)d(x)
1
Find P(1 < x <2)
2
= ∫ f(5 - x)d(x)
1

x2
= (5x - 2
) 2
1

22 12 7
= (5 x 2 - 2
) - (5 x 1 - 2
)= 2

Uniform Distribution

P(x)
1
b-a

a c d b

a+b
Mean : μ =
2

(a + b) 2
S.D. : σ =
12
d-c
Probability : P(c ≤ X ≤ d) =
b-a

Uniform Distribution Expectation value

1
E(X) = ∫
b
x
dx f(x) = a≤x≤b
b-a
a b-a
0 otherwise
b
x 2
= 2(b - a) 1
a
= 2(b - a)
(b + a) (b - a)

1 (b - a )
=
2 2

2(b - a) a+b
E(x) =
2
 Variance of Uniform Distribution

E(X ) = ∫
2
x 2
f(x) dx
a||x

2
x
∫ dx
b
E(x ) =
2
a b - a

b
x 3
= 3(b - a) a

1 (b - a )
=
3 3

3(b - a)

1 (a 2
= + ab + b 2)
3

Var(X) = E(X ) - E (X) 2 2

( (
2
2 2
a + ab + b a+b
Var(X) = -
3 2
2 2 2 2
a + ab + b (a + 2ab + b )
= -
3 4

2 2 2 2
4a + 4ab + 4b - 3a -6ab - 3b
=
12

2 2
a - 2ab + b
=
12

2
(a + b)
=
12

Normal Distribution or Gaussian Distribution

( (
2
1 x-μ Note Constants:
1 -
f(x) = .e 2 σ π = 3.14159
e = 2.71828
σ 2π

This is a bell shaped curve with different

centers and spreads depending on μ and σ

It's a probability function, so no matter what the values of μ and σ,

must integrate to 1!

( (
2
1 x-μ
+∞ 1 -
∫ .e 2 σ
dx = 1
-∞ σ 2π

More on Normal Distribution

μ = 0, σ2 = 0.2,
1.0 μ = 0, σ2 = 1.0,
μ = 0, σ2 = 5.0,
μ = -2, σ2 = 0.5,
0.8
Øμσ (x)
2

0.6

0.4

0.2

0.0

-5 -4 -3 -2 -1 0 1 2 3 4 5

f(x) Changing μ shifts the

distribution left or right.

Changing σ increases
σ or decreases the spread.

x
μ