Scribd
Upload
38 views

1.2.1 Variance of A Random Variable Definition 1.19

The document defines the variance of a random variable as the expected value of the squared deviation from the mean. It then provides four properties of variance: 1) it can be defined in terms of the expected value of X2 and the square of the expected value of X, 2) the variance of aX is a2 times the variance of X, 3) shifting a random variable by a constant does not change its variance, and 4) the variance of a constant is 0. It introduces moment generating functions as a way to obtain the moments (such as variance) of a random variable.

Uploaded by

sdklsjdflkajs
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
38 views

1.2.1 Variance of A Random Variable Definition 1.19

The document defines the variance of a random variable as the expected value of the squared deviation from the mean. It then provides four properties of variance: 1) it can be defined in terms of the expected value of X2 and the square of the expected value of X, 2) the variance of aX is a2 times the variance of X, 3) shifting a random variable by a constant does not change its variance, and 4) the variance of a constant is 0. It introduces moment generating functions as a way to obtain the moments (such as variance) of a random variable.

Uploaded by

sdklsjdflkajs
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

1.

2 Lecture 2
1.2.1 Variance of a random variable

Denition 1.19. Let X be a r.v and we set = E(X). The variance is X is denoted by Var(X)
and
Var(X) := E((X )2 )
and the standard deviation of X is the square root of the variance.

Intuitively, the variance measures on average how much does the random variable deviate from
its expectation/mean.
Lemma 1.20. Given a random variable X then for any constant a, b R,

1. Var(X) = E(X 2 ) (E(X))2 .


2. Var(aX) = a2 Var(X)
3. Var(X + b) = Var(X)
4. Var(b) = 0

Proof. 1. We compute from denition and recall that E(X) =

Var(X) = E((X )2 )
= E(X 2 X + 2 )
(by linearity) = E(X 2 ) 2E(X) + 2
= E(X 2 ) 2 .

2. From denition

Var(aX) = E((aX a)2 )


(by linearity) = a2 E((X )2 )
= a2 Var(X).

3. We know that E(X + b) = + b, then from denition of the variance

Var(X + b) = E((X + b ( + b))2 )


= E((X )2 )
= Var(X).

4. We know that E(b) = b, which implies that Var(b) = E((b b)2 ) = 0.


Example 1.21. Suppose X is a random variable with density fX (x) = ex for x 0, then from

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


 
2 x
= x e dx ( xex dx)2
0 0

We need to use integration by parts



2
E(X ) = x2 ex dx
0


= x2 ex 0 + 2xex dx
0
= 2E(X)

5
We compute now E(X), by using integration by parts

E(X) = xex dx
0


= xex 0 + ex dx
0
=1
Therefore Var(X) = 2 1 = 1

1.2.2 Moment Generating Functions

We see that the variance is X is the second moment of X subtract the rst moment of X squared.
The moments of a random variable are very important objects and we shall introduce in the following
a method to obtain the moments of a random variable.
Denition 1.22. The moment generating function (mgf) of a r.v X is denoted by
MX (u) := E(euX )
and we say that the mgf of X exists if MX (u) is nite in some interval containing zero.
Remark 1.23. The moment generating function of X exists if there exists h > 0 such that the
MX (x) is nite for x [h, h].
Example 1.24. Let X be a r.v with density function fX (x) = ex for x > 0. Then the moment
generating function of X is

E(euX ) = eux ex dx
0

= e(u1)x dx
0
e(u1)x 
= 
u1 0
from which we see that 
1
1u u<1
E(euX ) =
u1
1
from which we can say that the mfg of X exists, since we can take a take h = 2 and the mgf of X
is nite on the interval [ 12 , 12 ].
Lemma 1.25. Suppose the moment generating function of a r.v X exists then
(r) dr
E(X r ) = lim MX (u) =: lim MX (u)
u0 u0 du

Proof. As almost always, we give only the proof for the continuous case. I give only a sketch proof,

dr dr
lim MX (u) = lim eux fX (x) dx
u0 du u0 du R
 r
dr
 d ux
(by magic , we interchange du and dx ) = lim e fX (x) dx
u0 R du

= lim xr eux fX (x) dx
u0 R
= lim E(X r euX )
u0
(by some more magic ) = E( lim X r euX ) = E(X r )
u0

You might also like