Scribd
Upload
4 views2 pages

Multivariate Analysis of Cholesterol Data

The document outlines a problem set for a Multivariate Analysis and Nonparametric Methods lab, focusing on multivariate normal distribution. It includes tasks related to heart-attack patients' cholesterol levels, conditional distributions, correlation coefficients, and parameters of a normal distribution based on physical measurements of Indian adults. The problems require deriving joint probability density functions, regression equations, and calculating various correlation coefficients.

Uploaded by

goswammiii
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 views2 pages

Multivariate Analysis of Cholesterol Data

The document outlines a problem set for a Multivariate Analysis and Nonparametric Methods lab, focusing on multivariate normal distribution. It includes tasks related to heart-attack patients' cholesterol levels, conditional distributions, correlation coefficients, and parameters of a normal distribution based on physical measurements of Indian adults. The problems require deriving joint probability density functions, regression equations, and calculating various correlation coefficients.

Uploaded by

goswammiii
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

Date: 15.05.

2023

CC-14 SEM – 6 MULTIVARIATE ANALYSIS & NONPARAMETRIC


METHODS LAB

(STS-A-CC-6-14-P)

Problem Set 3: Multivariate Normal Distribution

1. Measurements were taken on n heart-attack patients on their cholesterol levels. For


each patient, measurements were taken 0, 2, and 4 days following the attack. Treatment
was given to reduce cholesterol level. The sample mean vector of the measurement is
(259.5 230.8 221.5)′ and the covariance matrix is:

If three measurements have a trivariate normal distribution, then find the expression of
their joint probability density function. Also find the distribution of the difference
between 0–Day and the 2–Day measurements.

2. Let X  ( X 1 , X 2 , X 3 , X 4 )' follow a multivariate normal distribution with mean


~

  (2,4,1,3)' and variance covariance matrix


~

 1 1
 4 1 2
 
2
 
 3 1 1  .
 6 1 
 
 4 
Find (i) the conditional distribution of X1 given (X2, X3, X4)
(ii) the multiple correlation coefficient
(iii) the partial correlation coefficient between X1 and X2 given X3, X4.
3. Suppose that height (X1), weight (X2) and arm length (X3) of Indian adults follow
normal distribution with exponent as the following quadratic form
Q(x1, x2, x3) = 2x12+2x22+2x32+2x1x2+2x1x3+2x2x3-128x1-218x2-126x3+6022.
(i) Find the parameters of the normal distribution.
(ii) Write the concentration ellipsoid of this distribution.
(iii) Find the regression equation for forecasting weight on the basis of height and arm
length.
(iv) Find the partial correlation coefficient ρ13.2.

You might also like