Moment generating functions (mgf)

Reference: 1. Meyer PL. Introductory probability and statistical applications. Oxford and IBH Publishing; 1965.
2. Johnson, Richard A., Irwin Miller, and John E. Freund. "Probability and statistics for engineers." (2000).

NOTE:
1. 𝐸 𝑋 is coefficient of t In 𝑀𝑋 𝑡 .
𝑡2
2. 𝐸 𝑋 2 is coefficient of In 𝑀𝑋 𝑡 .
2!
𝑡
3. 𝐸 𝑋 𝑛 is coefficient of In 𝑀𝑋 𝑡 .
𝑛!
4. 𝐸 𝑋 𝑛 𝑀𝑋𝑛 0

Example:
𝑒 −| |
1. Suppose that X has pdf 𝑓 𝑥 2
, ∞ 𝑥 ∞ then find E(X) and V(X) using mgf.
Solution:
∞
𝑀𝑋 𝑡 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥
−∞
∞ 𝑒 −| |
= ∫−∞ 𝑒 𝑡𝑥 2 𝑑𝑥
0 𝑒 ∞ 𝑒− 0 𝑒 1+ ∞ 𝑒 − 1−
= ∫−∞ 𝑒 𝑡𝑥 2 𝑑𝑥 + ∫0 𝑒 𝑡𝑥 2 𝑑𝑥= ∫−∞ 2
𝑑𝑥 + ∫0 2
𝑑𝑥

1
𝑀𝑋 𝑡 1−𝑡 2
, -1< t <1
𝑀𝑋1 0 0
𝑀𝑋2 0 2
E(X)= 0 and V(X)=2.
1 2𝑡 2
Or: 𝑀𝑋 𝑡 1−𝑡 2
1 𝑡2 𝑡4 𝑡6 ⋯ 1 2
𝑡4 𝑡6 ⋯
𝑡2
C E( )= 0. C 2
V( )= 2-0=2
2. L 0,1,2, 𝑓 𝑥 𝑎𝑏 𝑥 , 𝑎, 𝑏 0 & a+b=1. Find mgf
of X. If 𝐸 𝑋 𝑚1, 𝐸 𝑋 2 𝑚2 then S.T 𝑚2= 𝑚1 2𝑚1 1 .
Solution:
1 𝑎
𝑀𝑋 𝑡 ∑∞ 𝑥 𝑡𝑥
0 𝑎𝑏 𝑒 𝑎 ∑∞0 𝑏𝑒
𝑡 𝑥
= a 1−𝑏𝑒 = 1−𝑏𝑒
𝑎𝑏
𝐸 𝑋 𝑀𝑋1 0
1 𝑏 2
1 𝑏 𝑎𝑏
𝐸 𝑋2 𝑀𝑋2 0
1 𝑏 3
Given,
𝐸 𝑋 𝑚1, 𝐸 𝑋 2 𝑚2
To Prove, 𝑚2= 𝑚1 2𝑚1 1 .
𝑎𝑏 𝑎𝑏 𝑎𝑏 2𝑎𝑏+1+𝑏 2 −2𝑏
Consider, 𝑚1 2𝑚1 1 1−𝑏 2
2 1−𝑏 2
1 1−𝑏 2 1−𝑏 2
𝑎𝑏 2 𝑎𝑏
= 1−𝑏 4
2𝑏 𝑎 1 1 𝑏 == 1−𝑏 4
2𝑏 𝑏 1 𝑏 2 = 𝑚2 .
Moment generating function for Gamma Distribution

∞ 𝛼 ∞
𝑀𝑋 𝑡 ∫−∞ 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥 Γ 𝑟
∫0 𝑒 − 𝛼−𝑡 𝑥
𝑥 𝑟−1 𝑑𝑥
𝑑𝑣
Substitute, 𝑥 𝛼 𝑡 𝑣 then 𝑑𝑥 𝛼−𝑡
𝛼 ∞ 𝑣 𝑟−1 𝑑𝑣
𝑀𝑋 𝑡 Γ 𝑟
∫0 𝑒 −𝑣 𝛼−𝑡 𝛼−𝑡
𝛼 ∞ −𝑣 𝑟−1
=Γ 𝑟 𝛼−𝑡
∫0 𝑒 𝑣 𝑑𝑣
𝛼 𝛼 𝑟
= Γ 𝑟
Γ 𝑟 𝛼−𝑡 𝛼−𝑡
𝑟
𝐸 𝑋
𝛼
2 𝑟 𝑟+1
𝐸 𝑥 = 𝛼2
𝑟
V( )=
𝛼2
Moment generating function for Exponential Distribution
N : =1 .

∞ ∞
𝑀𝑋 𝑡 ∫0 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥 𝜆 ∫0 𝑒 − 𝜆−𝑡 𝑥
𝑑𝑥

𝜆
𝑀𝑋 𝑡 ,𝑡 𝜆
𝜆−𝑡
1
𝐸 𝑋
𝜆
1
𝑉 𝑋
𝜆2
O:

Moment generating function for chi square Distribution

𝒏 𝟏
S ecia ca e f Ga a di ib i :𝒓 𝜶 𝚪 𝝌𝟐 .
𝟐 𝟐
A - PDF .

∞
𝑀𝑋 𝑡 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥
−∞
∞ 1
𝛼 𝑡− 𝑥
∫−∞ 𝑒 2 𝑥 2 −1 𝑑𝑥
Γ 22
2
𝑛
−
𝑀𝑋 𝑡 1 2𝑡 2

𝐸 𝑋 V( )= 2
Moment generating function for Uniform Distribution
𝟏
𝒂 𝒙 𝒃
𝒇 𝒙 𝒃 𝒂
𝟎 ∞ 𝒆𝒍𝒔𝒆 𝒘𝒉𝒆𝒓𝒆
𝑀𝑋 𝑡 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥
−∞
1 ∞
∫ 𝑒 𝑡𝑥 𝑑𝑥
𝑏−𝑎 −∞
1
=𝑡 𝑏−𝑎
𝑒 𝑏𝑡 𝑒 𝑎𝑡
Expand and get the suitable coefficient in the expanssion to find E(X) and V(X).
 𝒂+𝒃
Mean E(X) = 𝟐
𝟐 𝒂𝟐 + 𝒃𝟐 +𝒂𝒃
E(𝑿 ) = 𝟑
𝒃−𝒂 𝟐
Variance V(X) = E(𝑿𝟐 ) 𝑬 𝑿 𝟐
= 𝟏𝟐

2
𝑥− 𝑡 2 + ∞ 2 1
By substituting, 𝑣 𝜎2
𝑎𝑛𝑑 𝑑𝑥 𝜎 2 𝑑𝑣 and ∫−∞ 𝑒 −𝑥 𝑑𝑥 Γ 2
√𝜋

Solution:
Properties of mgf
Re d c i eP e ie f gf
P be :
1. F
(- , ) 𝐸 𝑋 2𝑛 .
𝑒 𝑎 −𝑒 −𝑎 1
Solution: 𝑋~ 𝑈 𝑎, 𝑎 we know, 𝑀𝑋 𝑡 = 𝑡 𝑏−𝑎 𝑒 𝑏𝑡 𝑒 𝑎𝑡
𝑎+𝑎 𝑡
𝑒 𝑎 −𝑒 −𝑎
,
2𝑎 𝑡
𝑡2 𝑎2
𝐸 𝑋 2𝑛 𝑐𝑜𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡 𝑜𝑓
2𝑛 ! 2𝑛+1

2. I 𝜇 , 𝜎2
2𝑛
𝐸 𝑋 𝜇 1.3.5 … . 2𝑛 1 𝜎 2𝑛 .
2 2
2 𝜇𝑡+
S :G 𝑋~𝑁 𝜇, 𝜎 , 𝑀𝑋 𝑡 𝑒 2

L = 𝑋 𝜇
𝑡2
T E(𝑌 2𝑛 )= T 𝑀𝑌 𝑡 .
2𝑛 !
𝑀𝑌 𝑡 𝐸 𝑒𝑡 = 𝐸 𝑒𝑡 𝑥−𝜇

= 𝐸 𝑒 𝑡𝑥 𝐸 𝑒 −𝜇𝑡
= 𝑀𝑋 𝑡 𝐸 𝑒 −𝜇𝑡
2 2 2 2 2 3
𝜎2𝑡 2 1 𝜎2𝑡 2 1 𝜎2𝑡 2
𝑀𝑌 𝑡 𝑒 𝜇𝑡+ 2 𝑒 −𝜇𝑡 = 𝑒 2 1 ⋯
2 2! 2 3! 2
𝑡2 𝜎2 2𝑛 ! 2𝑛 !
E(𝑌 2𝑛 )= T 𝑀𝑌 𝑡 = = * 𝜎 2𝑛
2𝑛 ! 2 𝑛! 2 𝑛!
2𝑛 2𝑛−1 2𝑛−2 … 3 2 1
* 𝜎 2𝑛
2𝑛 2𝑛−2 2𝑛−4 … 6 4 2
= 1.3.5 … . 2𝑛 1 𝜎 2𝑛 .

3. L 𝑋1 ~𝜒 2 3 , 𝑋2 ~𝜒 2 5 = 𝑋1 𝑋2 𝑋1 𝑎𝑛𝑑 𝑋2 𝑖𝑛𝑑𝑒𝑝𝑒𝑛𝑑𝑒𝑛𝑡
.F 𝑀𝑍 𝑡 𝑉 𝑍 𝑎𝑛𝑑 𝑝𝑑𝑓 𝑜𝑓 𝑍.
S :
3
−
𝑋1 ~𝜒 2 3 𝑀𝑋1 𝑡 1 2𝑡 2
5
–
𝑋2 ~𝜒 2 5 𝑀𝑋2 𝑡 1 2𝑡 2

8
−
𝑀𝑍 𝑡 𝑀𝑋1 𝑡 𝑀𝑋2 𝑡 1 2𝑡 2 ~𝜒 2 8
T ,𝑉 𝑍 2𝑛 2 8 16. 𝑛 8.

𝑍 𝑍
−1 − −
𝑍2 𝑒 2 𝑍3𝑒 2
, 𝑍 0 , 𝑍 0
( )= 2 2 Γ 𝑛/2 24 Γ 4
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒 0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
4. L 𝑋1 , 𝑋2 𝑎𝑛𝑑 𝑋3 𝑎𝑟𝑒 3
(4, 1), (5,2), (7, 3) .L 𝑌 2𝑋1 2𝑋2 𝑋3 . F
𝑌−𝜇 2
𝑉 , 𝜇 𝑎𝑛𝑑 𝜎 .
𝜎
S :
𝜎2𝑡 2
𝜇𝑡+
𝑀𝑋 𝑡 𝑒 2
2
𝑌~𝑁 2 ∗ 4 2 ∗ 5 1 ∗ 7, 2 ∗1 22 ∗ 2 1∗3
𝑌~𝑁 25, 15
15𝑡 2
25𝑡+
𝑀𝑌 𝑡 𝑒 2
,

𝑌−25 2
T ,𝑉 𝑍 2 ~𝜒 2 1
√15

1 1
− − − −
𝑒 2 𝑣 2 𝑒 2 𝑣 2
1 , 𝑣 0 , 𝑣 0
(V)= 22 Γ
1 = √𝜋 2 2
1
2
0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒 0, 𝑂𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
3
5. I 𝑀𝑋 𝑡
3−𝑡
.
S :

3 3 1 𝑡 −1 𝑡 𝑡 2
𝑀𝑋 𝑡 = = 1 1 ⋯
3−𝑡 3 1−3 1−3 3 3 3
1
𝐸 𝑋 𝑐𝑜𝑒𝑓 𝑜𝑓 𝑡 𝑖𝑛 𝑀𝑋 𝑡
3
2
𝑡2 1 2
𝐸 𝑋 𝑐𝑜𝑒𝑓 𝑜𝑓 𝑖𝑛 𝑀𝑋 𝑡 2!
2! 9 9
1 1
𝑉 𝑋 . 𝐻𝑒𝑛𝑐𝑒, 𝜎
9 3
𝑘−1
6. L ( = )= 1 𝑝 ,
𝑘 1,2,3 … 𝑛. F 𝑀𝑋 𝑡 V( ).
S :
𝑀𝑋 𝑡 ∑𝑛1 𝑒 𝑡𝑥 𝑝 𝑋 𝑥

∑𝑛1 𝑒 𝑡𝑥 p 1 𝑝 𝑥−1

𝑝
∑𝑛1 𝑒 𝑡𝑥 1 𝑝 𝑥
𝑝−1
 𝑝
= ∑𝑛1 𝑒 𝑡 1 𝑝 𝑥
,E
1−𝑝
𝑝
𝑒𝑡 1 𝑝 𝑒𝑡 1 𝑝 2
⋯
1 𝑝
𝑝
𝑒𝑡 1 𝑝 1 𝑒𝑡 1 𝑝 𝑒𝑡 1 𝑝 2
⋯
1−𝑝
𝑝 𝑡
1 𝑝𝑒 𝑡
𝑀𝑋 𝑡 ∗ 𝑒 1 𝑝 ∗
1 𝑝 1 𝑒𝑡 1 𝑝 1 𝑒𝑡 1 𝑝
𝑝𝑒
𝑀𝑋1 𝑡 ,
1−𝑒 1−𝑝 2
1
= , E( )
𝑝

1 2 1 𝑝
𝐸 𝑋2
𝑝 𝑝2
1 𝑝
𝑉 𝑋
𝑝2
7. I ( )= 𝜆𝑒 −𝜆 𝑥−𝑎
,𝑋 𝑎, V( ).
A :G .
∞
𝑀𝑋 𝑡 𝑒 𝑡𝑥 𝑓 𝑥 𝑑𝑥
−∞
∞
𝑒 𝑡𝑥 𝜆𝑒 −𝜆 𝑥−𝑎
𝑑𝑥
𝑎
∞
𝜆 𝑒 𝑡𝑥 𝑒 −𝜆 𝑥−𝑎
𝑑𝑥
𝑎
𝜆𝑎 ∞
= 𝜆𝑒 ∫𝑎 𝑒 − 𝜆−𝑡 𝑥 𝑑𝑥
𝜆𝑎
𝑒 − 𝜆−𝑡 𝑥
𝜆𝑒
𝜆 𝑡
𝑒− − 𝑎 𝜆𝑒 𝑎
= 𝜆𝑒 𝜆𝑎 = ,𝜆 𝑡
𝜆−𝑡 𝜆−𝑡
1 1
E( )= 𝑎 V( )=
𝜆 𝜆2
8. I 𝑒4 𝑒 −1
P(𝑋 𝜇 𝜎) 𝜇
𝜎 S.D .
S : 𝑀𝑋 𝑡 𝑒4 𝑒 −1

𝑋~𝑝 𝛼 𝛼 4
T E( )= V( )= 4,
𝜇 4 𝑎𝑛𝑑 𝜎 2.
𝑒− 𝛼
P( = )= , = 0,1,2, .,
𝑘!
F ,𝛼 4,
𝑒 −4 4
P( = )=
𝑘!
𝑒 −4 46
T P(𝑋 𝜇 𝜎)= P(𝑋 6)= = 0.1042.
6!