STAT 410 Fall 2010

Examples for 08/23/2010

random variables
discrete continuous

probability mass function probability density function

p.m.f. p.d.f.
p( x ) = P ( X = x ) f( x )

∀x 0 ≤ p( x ) ≤ 1 ∀x f( x ) ≥ 0
∞
∑ p(x ) = 1 ∫ f (x) d x =1
all x
−∞

cumulative distribution function

c.d.f.
F( x ) = P( X ≤ x )
x
F( x ) = ∑ p( y ) F( x ) = ∫ f (y) d y
y≤ x −∞

Example 1:

x p( x ) F( x )  0 x <1
 0 .2 1≤ x < 2
1 0.2 0.2 
2 0.4 0.6 F( x ) =  0 .6 2≤ x<3
 0 .9 3≤ x<4
3 0.3 0.9 
4 0.1 1.0  1 x≥4
Example 2:

 2 x<0 F X ( x ) = 0.
f X ( x ) =  3 x 0 < x <1
 0 o.w. x
2
0≤x<1 FX( x ) = ∫ 3y d y = x 3.
0

x≥1 F X ( x ) = 1.

fX( x ) FX( x )

Example 3:

 −6 x<1 F X ( x ) = 0.
f X ( x ) =  5 x x >1
 0 o.w. x
−6
x≥1 FX( x ) = ∫ 5y dy
1

x
= – y −5 = 1 – x – 5.
1

fX( x ) FX( x )
Example 4:
1
( Standard ) Cauchy distribution: fX( x ) = – ∞ < x < ∞.
(
π 1+ x 2 ),
x
1 1 1
FX( x ) = ∫ dy = arctan(x ) + , – ∞ < x < ∞.
−∞ π 1 + y
2
( ) π 2

-----------------------------------------------------------------------------------------------------------------

expected value
E( X ) = µX

discrete continuous
∞
If ∑ x ⋅ p ( x) < ∞, If ∫ x ⋅ f ( x) d x < ∞,
all x −∞

∞
E( X ) = ∑ x ⋅ p( x) E( X ) = ∫ x ⋅ f ( x) d x
all x −∞

Example 1:

x p( x ) x ⋅ p( x )
1 0.2 0.2
2 0.4 0.8
3 0.3 0.9
4 0.1 0.4 E ( X ) = µ X = 2.3.
2.3

Example 2:
 2
f X ( x ) =  3 x 0 < x <1
 0 o.w.

1 1
3
E( X ) = µ X = ∫ x ⋅ 3 x d x = ∫ 3 x 3 d x =
2
= 0.75.
0 0
4
Example 3:
 −6
f X ( x ) =  5 x x >1
 0 o.w.

∞ ∞ 5
E( X ) = µ X = ∫ x ⋅5 x
−6
d x = ∫ 5 x − 5 d x = = 1.25.
1 1
4

Example 4:
1
( Standard ) Cauchy distribution: fX( x ) = – ∞ < x < ∞.
(
π 1+ x 2 ),
Even though f X ( x ) is symmetric about zero, E ( X ) is undefined since
∞
1
∫ x⋅ dx = ∞.
−∞ π 1 (
+ x 2
)