Scribd
Upload
18 views2 pages

JRF Stat STB 2017

sonam

Uploaded by

Mina kare
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
18 views2 pages

JRF Stat STB 2017

sonam

Uploaded by

Mina kare
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/ 2

1.

Consider a Markov chain {Xn : n ≥ 0} with state space S =


{0, 1, 2, 3} and stationary transition probability matrix P = ((pij ))
satisfying
X3
j pij = i for i = 0, 1, 2, 3.
j=0

Show that 0 and 3 must be absorbing states. [15]

2. Suppose that (Xi , Yi ), i ≥ 1, are independent and identically


distributed bivariate random vectors with E(X1 ) = µx , E(Y1 ) =
µy , V ar(X1 ) = σx2 , V ar(Y1) = σy2 and Corr(X1 , Y1) = ρ. If X1
and Y1 are positive random variables, show that
Pn
√

i=1 Xi µ x
Zn = n Pn −
i=1 Yi µy

converges in distribution to a normal random variable with mean


0 and variance µ14 (µ2y σx2 + µ2x σy2 − 2ρµx µy σx σy ). [15]
y

3. Consider a sequence of random variables {Xn : n ≥ 1}, where


Xn ∼ N(0, n−α ) for n = 1, 2, . . . and α > 0 is fixed. Show that
Xn converges almost surely to 0. [15]

4. Let X1 , X2 , . . . , Xn be independent Bernoulli random variables


with P (Xi = 1) = p for i = 1, 2, . . . , n, where p ∈ [1/2, 1).

(a) Is T = n−1 ni=1 Xi a minimum variance unbiased estimator


P

of p? Justify your answer.


(b) Find an estimator T0 such that E(T − p)2 > E(T0 − p)2 for
all p ∈ [1/2, 1). [7+8]

5. Let X1 , X2 , . . . , Xn be independent and identically distributed


normal variables with mean θ and variance 1. For the testing
problem H0 : θ = 0 against H1 : θ = 1, find the critical region
that minimizes P (Type I Error) + 3 P (Type II Error). [15]

2
6. Consider the following data set

x 1 2 3 4 5 6
y 18.6 15.0 10.6 7.2 3.4 −1.1

Find the equation of the line y = α + βx that passes through


the point (5, 3) and minimizes 6i=1 |yi − α − βxi |, where (xi , yi )
P

denotes the i-th (i = 1, 2, . . . , 6) observation. [15]

7. Consider the following block design D with 3 treatments denoted


by 1, 2 and 3, assigned in 3 blocks of size 5.
1 2 3 1 2
 

D= 1 2 3 2 3 
1 2 3 3 1

(a) Identify a set of maximum number of linearly independent


estimable functions of the treatment effects under the usual
additive fixed effects two way ANOVA model.
(b) Find the best linear unbiased estimator of τ1 − τ2 , where τi
denotes the i-th (i = 1, 2, 3) treatment effect. [3+12]

8. Let θ be the unknown proportion of tax evaders (denoted by


attribute A) in a finite population of size N. In order to estimate
θ, a statistician chose a sample of size n using simple random
sampling without replacement. Because of the sensitive nature of
A, a fair die was used. Two faces of the die were inscribed with A
and the other four faces were inscribed with Ac . Each person in
the sample was asked to roll the die till s/he got the face showing
her/his true state and only report Z, the number of rolls required
for it. These responses were denoted by Z1 , Z2 , . . . , Zn . Find

(a) an unbiased estimator T for θ,


(b) an unbiased estimator for Var(T ). [9+6]

You might also like