MEDIUM
Q1 – Compulsory (3×5 = 15 marks)
a) Prove that the Ordinary Least Squares (OLS) estimator is unbiased.
b) Differentiate between homoscedasticity and heteroscedasticity with suitable plots and
implications.
c) Define a Cauchy sequence. Prove that every Cauchy sequence in R\mathbb{R}R is convergent.
d) A machine produces ball bearings with a target diameter of 12 mm. A sample of 10 bearings
gives a mean of 12.1 mm and standard deviation of 0.2 mm. Test if the machine is operating
correctly at a 1% significance level.
e) State and explain any three properties of eigenvectors.
UNIT I – Probability, Distributions & Inference
Q2
a) Derive the probability density function (PDF) of the standard normal distribution.
(5 marks)
b) The heights of a group of students are normally distributed with a mean of 170 cm and
standard deviation of 10 cm. Find the probability that a student chosen at random has height:
i) greater than 180 cm,
ii) between 160 and 180 cm.
(5 marks)
c) Explain the difference between Z-test and Chi-square test with examples.
(5 marks)
Q3
a) State and explain the Central Limit Theorem. Why is it essential in sampling theory?
(5 marks)
b) Describe the procedure for performing a Chi-Square Test of Independence. Given the
following data, test if gender and preference for online learning are independent at 5%
significance level:
Prefer Don’t Prefer Total
Male 40 20 60
Female 30 10 40
Total 70 30 100
(10 marks)
UNIT II – Regression & Experimental Design
Q4
a) Derive the formula for estimating coefficients β0 and β1 using the least squares method in
simple linear regression.
(6 marks)
b) Explain the significance of residual analysis in regression. What do studentized residuals help
detect?
(4 marks)
c) A regression model gives the following output:
y=2+1.5 x1 − 0.8 x2
Interpret the coefficients. How would the model output change if x1=3, x2=2?
(5 marks)
Q5
a) What are factorial experiments? Design a 2^2 experiment and calculate the main effects and
interaction effect using hypothetical data.
(7.5 marks)
b) Explain the purpose of Box-Cox transformation. How do you choose the best λ?
(4 marks)
c) Compare Multiple Linear Regression and Logistic Regression based on assumptions, model
structure, and use cases.
(3.5 marks)
UNIT III – Metric Spaces and Sequences
Q6
a) Define a metric space. Verify whether the function d(x,y)= x−y + x−y ^2is a valid metric on R.
(5 marks)
b) Show that every convergent sequence in a metric space is a Cauchy sequence, but the
converse is not true in all spaces.
(5 marks)
c) Give one example each of:
A compact set
A connected set
A disconnected set
Explain why each example fits the definition.
(5 marks)
Q7
a) Define completeness in metric spaces. Prove that the discrete metric space is complete.
(7.5 marks)
b) Define a closed set in a metric space. Prove that every compact subset of a metric space is
closed.
(7.5 marks)
UNIT IV – Linear Algebra for Data Analytics
Q8
a) Define eigenvalues and eigenvectors. Find the eigenvalues and eigenvectors of the matrix:
A=[2 1]
[ 1 2]
(7.5 marks)
b) Define a subspace of a vector space. Show whether the following set is a subspace of R^2:
S={(x,y) element of R^2 | x=y^2}
(7.5 marks)
Q9
a) Define linear dependence. Prove that any set of more than n vectors in R^n is linearly
dependent.
(5 marks)
b) Let v1=(1,0,1), v2=(0,1,1), and v3=(1,1,2). Check whether these vectors are linearly
independent.
(5 marks)
c) Explain how eigenvalues and eigenvectors are used in Principal Component Analysis (PCA)
for dimensionality reduction.
(5 marks)