Scribd
Upload
4 views9 pages

GEC410 MGF Note5 Module1

The document discusses the Moment Generating Function (MGF) of random variables, defining its mathematical formulation for both discrete and continuous cases. It outlines properties of MGF, including its use in calculating moments and determining distributions, and provides specific examples for Bernoulli, Binomial, Poisson, Uniform, and Exponential distributions. Additionally, it explains how to derive mean and variance using MGF.

Uploaded by

Sio
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views9 pages

GEC410 MGF Note5 Module1

The document discusses the Moment Generating Function (MGF) of random variables, defining its mathematical formulation for both discrete and continuous cases. It outlines properties of MGF, including its use in calculating moments and determining distributions, and provides specific examples for Bernoulli, Binomial, Poisson, Uniform, and Exponential distributions. Additionally, it explains how to derive mean and variance using MGF.

Uploaded by

Sio
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

GEC410-Probability and

Statistics

By
Dr. T. J. Akingbade
Department of Mathematics, Covenant University Ota, Nigeria.
MOMENT GENERATING FUNCTION (MGF)

The moment generating function M X (t ) of the random variable X is defined for all real value of
t

  etx P ( X  x ), discrete
M X (t )  E (e )   etx f ( x ) dx,continuous
tx RX


 RX
MGF can be used to calculate moment of a distribution and also to determine the distribution that
a random variable follows. If the MGF of X exist, then it can uniquely determines the cumulative
distribution function. No two different distributions have the same MGF.
By Taylor’s series expansion

(tx)i
r
(tx) 2 (tx) r
e 
tx
 1  tx   ... 
i 0 i ! 2! r!
t r E ( X )r t 2 21 t r r'
M X (t )  E (e )  1  tE ( X )  .... 
tx
 1  t 1 
'
... 
r! 2! r!

Its first derivative is

2t 2' t r 1r'
M (t )  0   
' '
 ... 
(r  1)!
X 1
2!
Properties of MGF
1. If X, Y are independent random variables, then

M X Y (t )  M X (t )M Y (t )
Also,

If X 1 , X 2 ,..., X n are n independent random variables then:


(t )   i 1 M X i (t )
n
M
 i 1 X i ( t )
n

2. Let a and b both be constants, if the MGF of a random variable X is M X (t )

What is the MGF of aX+b in terms of MGF of X?


M aX b (t )  ebt M X (at )
To determine the mean and the variance using MGF approach
E ( X )  M X' (0)  1'  0  1'
E ( X 2 )  M X'' (0)
E ( X 3 )  M X''' (0)

E ( X r )  M Xr (0)
where the `primes' denote derivatives of the associated functions.

V ( X )  E ( X 2 )  ( E ( X )) 2  M X'' (0)  ( M X' (0)) 2  2'  ( 1' ) 2


t r
r 2 '
M X (t )  0  2  ... 
'' '

(r  2)!
M X'' (0)  2'  E ( X 2 )
The MGFs of the following distributions will be treated:
a) Bernoulli and Binomial distribution
b) Poisson distribution
c) Uniform distribution,
d) Exponential distribution

Bernoulli Distribution

P( X  x)  p x (1  p )1 x , x  0,1
1
M X (t )   etx p x (1  p )1 x  pet  (1  p )
x 0

Binomial Distribution

n
P ( X  x )    p x (1  p ) n  x , x  0,1,..., n
 x
n
M X (t )  E  e      ( pet ) x (1  p ) n  x
n
tx

x 0  x 

By applying the concept of binomial theorem,


n
( a  b )   nC x a x b n  x
n

x 0

M X (t )  ( pet  q)n
Obtain the mean and the variance
Poisson Distribution

X po ( )

 x e 
P( X  x)  , x=0,1,2,...
x!

(  e t x
)  (  e t 2
) 
M X (t )  e     e    1   et   ... 
x 0 x!  2! 
Recall the power series expansion of e x

x 0 x1 xr
e    ....  
x

0! 1! r 0 r !

   et   (1et )
M X (t )  e e e
Obtain the mean and the variance
Continuous Uniform Distribution
Let X be a continuous uniform distribution in the interval (a, b), the MGF of

M X (t )  E (etx )   etx f ( x)dx


b
1  e tb
 e ta

 e tx
dx   
a
ba  t (b  a) 
Exponential Distribution

Let X exp( ), such that  >0.


 x
f ( x)   e , x  0
The MGF of X is
 
M X (t )  E (etx )   etx e  t dx    e  x (  t )dx
0 0



 t

You might also like