Scribd
Upload
17 views3 pages

Multivariate Statistics Exam 2023

The document outlines the final examination for the Department of Statistics at Jatiya Kabi Kazi Nazrul Islam University, focusing on multivariate normal distributions and related statistical analyses. It includes tasks such as generating random samples, estimating mean and covariance, computing probabilities, fitting regression models, and testing hypotheses using Hotelling's T² statistic. Additionally, it covers simulations of multivariate normal distributions and the properties of the Wishart distribution.

Uploaded by

Abdullah-Al Emon
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
17 views3 pages

Multivariate Statistics Exam 2023

The document outlines the final examination for the Department of Statistics at Jatiya Kabi Kazi Nazrul Islam University, focusing on multivariate normal distributions and related statistical analyses. It includes tasks such as generating random samples, estimating mean and covariance, computing probabilities, fitting regression models, and testing hypotheses using Hotelling's T² statistic. Additionally, it covers simulations of multivariate normal distributions and the properties of the Wishart distribution.

Uploaded by

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

Jatiya Kabi Kazi Nazrul Islam University

2 Year 2nd Semester Final Examination-2023


nd

Department of Statistics
Couse Code: STAT-302, Title: Lab-X
Group-B
Time: 6 hours Total Marks:
25 8
1. Generate 1000 random samples from a 3-dimensional multivariate normal
distribution with the following parameters:

[ ]
4 1 0
'
μ=(2 3 4) and Σ= 1 2 1
0 1 3
a) Estimate the MLE of the mean vector and covariance matrix for n=500 and
700, and comment the results.
b) Compute marginal probability for the first variable.
c) Fit a regression model of X 1 as the dependent variable and X 2 , X 3 as
predictors and compute multiple correlation.

2. Suppose you have a multivariate normal vector X ∼ N (0 , Ik) with k=6 6


independent components.
a) Generate a sample of 1,000 observations for each component of X from a
standard normal distribution.
k
2
b) For each observation, calculate the chi-square statistic χ =∑ X to create
2

i=1

a vector of chi-square values.


c) Use the chi-square values to:
i. Calculate the PDF of the chi-square distribution at a specific point x=8 .
ii. Calculate the CDF at x=8 for a chi-square distribution with 6 degrees of
freedom.
d) Plot the histogram of the chi-square values and overlay the PDF curve of a
chi-square distribution with 6 degrees of freedom.
'
3. Test and comments on the null hypothesis H 0 : μ=[ 208 400 500 500 ] for testing a 5

single mean vector using Hotelling's T ² statistic for the following multivariate
normal random samples.
X1 X2 X3 X4
580 516 613 750
473 319 514 963
664 369 782 107
739 193 293 530
143 853 927 121
127 632 512 837
703 551 936 118
108 578 856 113
185 74 244 663
111 544 618 816
815 365 500 930
770 522 542 570
759 205 443 789
928 360 402 611
849 137 396 700

4. Simulate 800 random samples from a 3-dimensional multivariate normal


distribution with the following parameters:

[ ]
5 1 0
'
μ= (1 4 5 ) and Σ= 1 2 1
0 1 3
a) Compute the sample covariance matrix from the simulated samples, which
follows the Wishart distribution.
b) How Wishart distribution follows chi-square distribution also calculate p-
value?
c) Calculated generalized variance and how can you calculate the degeneracity of
a Wishart matrix.

You might also like