Moments and Other Measures in Terms of Expectations

 

Moments and Other Measures in Terms of Expectations

Data Science and A.I. Lecture Series

By Bindeshwar Singh Kushwaha – PostNetwork Academy

Moments

The rth order moment about any point A of a variable X is given by:

For discrete variables:

μr=i=1npi(xiA)r

For continuous variables:

μr=(xA)rf(x)dx

Central Moments

The rth order central moment is given by:

For discrete variables:

μr=i=1npi(xiμ)r

For continuous variables:

μr=(xμ)rf(x)dx

Expectation form:

μr=E[(Xμ)r]

Variance

Variance of a random variable X is the second-order central moment:

V(X)=E[X2](E[X])2

Using moments about the origin:

V(X)=μ2(μ1)2

Theorem: Variance Scaling Property

If X is a random variable and a,b are constants, then:

V(aX+b)=a2V(X)

Proof of Theorem

By definition of variance:

V(aX+b)=E[(aX+bE[aX+b])2]

Expanding expectation:

=E[(aX+baE[X]b)2]

Simplifying:

=E[a2(XE[X])2]

Using expectation properties:

=a2E[(XE[X])2]=a2V(X)

Example: Variance Calculation

X p(X)
-2 0.15
-1 0.30
0 0
1 0.30
2 0.25

Computing V(X):

V(X)=E[X2](E[X])2

Using values:

V(X)=2.2(0.2)2=2.20.04=2.16

Variance of a Linear Transformation

Computing V(2X+3):

Using theorem: V(aX+b)=a2V(X)

V(2X+3)=4V(X)

Substituting V(X)=2.16:

V(2X+3)=4(2.16)=8.64

Video

PDF

Loading...

Reach PostNetwork Academy

Thank You!

 

©Postnetwork-All rights reserved.