Scribd
Upload
29 views6 pages

Mathematical Statistics (MA212M) : Lecture Slides

This document summarizes key concepts about the univariate and bivariate normal distributions: 1) A univariate normal distribution is completely specified by its mean and variance. 2) A bivariate normal distribution means that all linear combinations of the variables are univariate normal. It is specified by a mean vector and variance-covariance matrix. 3) If the variables are bivariate normal, their marginal distributions are univariate normal and their joint density can be written in terms of the mean, variances, and correlation coefficient.

Uploaded by

akshay
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
29 views6 pages

Mathematical Statistics (MA212M) : Lecture Slides

This document summarizes key concepts about the univariate and bivariate normal distributions: 1) A univariate normal distribution is completely specified by its mean and variance. 2) A bivariate normal distribution means that all linear combinations of the variables are univariate normal. It is specified by a mean vector and variance-covariance matrix. 3) If the variables are bivariate normal, their marginal distributions are univariate normal and their joint density can be written in terms of the mean, variances, and correlation coefficient.

Uploaded by

akshay
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
You are on page 1/ 6

Mathematical Statistics (MA212M)

Lecture Slides
Lecture 21
Univariate Normal Distribution

Def: A continuous random variable X is said to have a univarite


normal distribution if the PDF of X is given by
1 1 x−µ 2
f (x) = √ e − 2 ( σ ) for all x ∈ R,
σ 2π
where µ ∈ R and σ > 0.
Notation: X ∼ N(µ, σ 2 ).
Theorem: If X ∼ N(µ, σ 2 ), all moments of X exist. In particular,
E (X ) and Var (X ) exist, and they are given by E (X ) = µ and
Var (X ) = σ 2 .
Remark: This means that a normal distribution is completely specified
by its mean and variance.
Bivariate Normal

Def: A two dimensional random vector X = (X1 , X2 ) is said to have


a bivariate normal distribution if aX1 + bX2 is a univariate normal for
all (a, b) ∈ R2 \ (0, 0).
Remark: If X has bivariate normal distribution, then each of X1 and
X2 is univariate normal. Hence E (X1 ), E (X2 ), Var (X1 ), Var (X2 ), and
Cov (X1 , X2 ) exist.
   
µ1 σ11 σ12
Notation: µ = E (X ) = and Σ = Var (X ) = .
µ2 σ21 σ22
Theorem: Let X be a bivariate normal random vector. If µ = E (X )
and Σ = Var (X ), then for any fixed u = (a, b) ∈ R2 \ (0, 0),
u 0 X ∼ N(u 0 µ, u 0 Σu).
Bivariate Normal

Theorem: Let X be a bivariate normal random vector, then


0 1 0
MX (t) = e t µ+ 2 t Σt for all t ∈ R2 .
Remark: Thus the bivariate normal distribution is completely specified
by the mean vector µ and the variance-covariance matrix Σ.
Notation: X ∼ N2 (µ, Σ).
Corollary: If X ∼ N2 (µ, Σ), then X1 ∼ N(µ1 , σ11 ) and
X2 ∼ N(µ2 , σ22 ).
Remark: The converse of the above theorem is not true.
Remark: If X ∼ N2 (µ, Σ) and Cov (X1 , X2 ) = 0, then X1 and X2 are
independent.
Probability Density Function

Theorem: Let X ∼ N2 (µ, Σ) be such that Σ is invertible, then, for


all x ∈ R2 , X has a joint PDF given by
 
1 1 0 −1
f (x) = exp − (x − µ) Σ (x − µ)
2π|Σ|1/2 2
1
= p e A(x1 , x2 , µ1 , µ2 , σ1 , σ2 , ρ) ,
2πσ1 σ2 1 − ρ 2

√ √
where σ1 = σ11 , σ2 = σ22 , ρ is correlation coefficient between X1
and X2 , and
( 2     2 )
1 x1 − µ1 x1 − µ1 x2 − µ2 x2 − µ2
A=− − 2ρ + .
2(1 − ρ2 ) σ1 σ1 σ2 σ2
Conditional Probability Density Function

Theorem: Let X ∼ N2 (µ, Σ) be such that Σ is invertible, then


1 for all x2 ∈ R, the conditional PDF of X1 given X2 = x2 is given
by
" 2 #
1 x1 − µ1|2

1
fX1 |X2 (x1 |x2 ) = √ exp − for x1 ∈ R,
σ1|2 2π 2 σ1|2

where µ1|2 = µ1 + ρ σσ21 (x2 − µ2 ) and σ1|2


2
= σ12 (1 − ρ2 ).
 
2
2 X1 |X2 = x2 ∼ N µ1|2 , σ1|2 .
3 E (X1 |X2 = x2 ) = µ1|2 = µ1 + ρ σσ21 (x2 − µ2 ) for all x2 ∈ R.
2
4 Var (X1 |X2 = x2 ) = σ1|2 = σ12 (1 − ρ2 ) for all x2 ∈ R. Hence the
conditional varinace does not depend on x2 .

You might also like