Scribd
Upload
57 views6 pages

MStat PSB 2013

This document provides instructions and questions for a test with 10 questions divided into two groups. It states that the test is 2 hours, there are 10 questions, and candidates should answer at least one question from Group A. It provides instructions on how to write responses and specifies that no calculators are allowed. The body of the document then lists the 10 questions.

Uploaded by

SOUMYADEEP GOPE
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
57 views6 pages

MStat PSB 2013

This document provides instructions and questions for a test with 10 questions divided into two groups. It states that the test is 2 hours, there are 10 questions, and candidates should answer at least one question from Group A. It provides instructions on how to write responses and specifies that no calculators are allowed. The body of the document then lists the 10 questions.

Uploaded by

SOUMYADEEP GOPE
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

2013

BOOKLET No. TEST CODE: PSB

Afternoon

Questions: 10 Time: 2 hours

Write your Name, Registration number, Test Code, Number of this booklet,
etc. in the appropriate places on the answer–booklet.

• All questions carry equal weight.

• Answer at least one question from GROUP A.

• Best five answers subject to the above condition will be considered.

Answer to each question should start on a fresh page.


All rough work must be done on this booklet
and/or the answer–booklet. You are
not allowed to use calculators.

STOP! WAIT FOR THE SIGNAL TO START.


GROUP A

1. Let E = {1, 2, . . . , n}, where n is an odd positive integer. Let V be


the vector space of all functions from E to R3 , where the vector space
operations are given by

(f + g)(k) = f (k) + g(k), for f, g ∈ V, k ∈ E,


(λf )(k) = λf (k), for f ∈ V, λ ∈ R, k ∈ E.

(a) Find the dimension of V .


(b) Let T : V → V be the map given by
1
T f (k) = (f (k) + f (n + 1 − k)) , k ∈ E.
2
Show that T is linear.
(c) Find the dimension of the null space of T .

2. Let a1 < a2 < · · · < am and b1 < b2 < · · · < bn be real numbers such
that
m
X n
X
|ai − x| = |bj − x| for all x ∈ R.
i=1 j=1

Show that m = n and aj = bj for 1 ≤ j ≤ n.

GROUP B

3. Let S = {1, 2, . . . , n}.

(a) In how many ways can we choose two subsets A and B of S so


that B 6= ∅ and B ⊆ A ⊆ S ?
(b) In how many of these cases is B a proper subset of A ?

1
4. Consider a machine with three components whose times to failure are
independently distributed as exponential random variables with mean
λ. The machine continues to work as long as at least two components
work. Find the expected time to failure of the machine.

5. A pin whose centre is fixed on a flat table is randomly and indepen-


dently spun twice. Each time, the final position is noted by drawing a
line segment.

(a) What is the probability that the smallest angle between the two
segments is more than half of the largest angle ?
(b) What is the probability that at least one of the two segments
makes an angle which is less than 45◦ with the x-axis (when mea-
sured in the anti-clockwise direction) ?

6. There are twenty individuals numbered 1, 2, . . . , 20. Each individual


chooses 10 others from this group in a random fashion, independently
of the choices of the others, and makes one phone call to each of the
10.

(a) Let X be the number of calls handled (incoming as well as out-


going) by Individual 1. Find E(X).
(b) Let Y be the number of calls between Individual 1 and Individual
2. Find E(Y ).
(c) Find E(X|Y = 1).

2
7. Let X1 , X2 , . . . , Xn be a random sample from a U nif orm(θ, 1) popu-
lation, where θ < 1.

(a) Find the MLE θ̂ of θ.


(b) Find c such that c θ̂ is unbiased for θ.

8. Let X1 , X2 , . . . , Xn be independent and identically distributed random


variables from some distribution with mean µ and variance σ 2 . Let
v
u n
u1 X
s=t (Xi − X̄)2
n
i=1

where X̄ is the sample mean. Show that s underestimates σ (that is,


it has negative bias).

9. Let X1 ∼ Geo(p1 ) and X2 ∼ Geo(p2 ) be independent random vari-


ables, where Geo(p) refers to the Geometric distribution whose p.m.f.
f is given by
f (k) = p(1 − p)k , k = 0, 1, . . . .

We are interested in testing the null hypothesis H0 : p1 = p2 against


the alternative H1 : p1 < p2 . Intuitively, it is clear that we should reject
if X1 is large, but unfortunately we cannot compute a cutoff because
the distribution of X1 under H0 depends on the unknown (common)
value of p1 and p2 .

(a) Let Y = X1 + X2 . Find the conditional distribution of X1 |Y = y


when p1 = p2 .
(b) Based on the result obtained in (a), derive a level 0.05 test for H0
against H1 that rejects H0 when X1 is large.

3
10. Let y1 , y2 , y3 , y4 be uncorrelated observations with common variance
σ 2 and expectations given by

E(y1 ) = E(y2 ) = β1 + β2 + β3
E(y3 ) = E(y4 ) = β1 − β2
P4
An observational function i=1 ai yi is said to be an error function if
its expectation is zero.

(a) Obtain a maximal set of linearly independent error functions for


the above model (that is, the set should be such that adding
any other error function to the set would make the set linearly
dependent). Justify your answer.
(b) Obtain an unbiased estimator of 3β1 − β2 + β3 such that it is
uncorrelated with each of the error functions obtained in (a).

You might also like