Scribd
Upload
4 views

2022 2023midterm

The document is a midterm exam for a statistics course consisting of 3 questions worth a total of 60 marks. Question 1 has two parts worth 10 marks total about the distribution of a sum of random variables and approximating the distribution of a sample mean. Question 2 worth 10 marks is about finding the maximum likelihood estimator of a parameter of a uniform distribution. Question 3 worth 40 marks has seven parts about moment generating functions, expectations, distributions, maximum likelihood estimation, unbiased minimum variance, and comparing estimators based on mean squared error.

Uploaded by

Cyber Alpha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

2022 2023midterm

The document is a midterm exam for a statistics course consisting of 3 questions worth a total of 60 marks. Question 1 has two parts worth 10 marks total about the distribution of a sum of random variables and approximating the distribution of a sample mean. Question 2 worth 10 marks is about finding the maximum likelihood estimator of a parameter of a uniform distribution. Question 3 worth 40 marks has seven parts about moment generating functions, expectations, distributions, maximum likelihood estimation, unbiased minimum variance, and comparing estimators based on mean squared error.

Uploaded by

Cyber Alpha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

NOT TO BE TAKEN AWAY

THE UNIVERSITY OF HONG KONG


DEPARTMENT OF STATISTICS AND ACTUARIAL SCIENCE

STAT2602/STAT3902

Midterm Exam Total: 60 marks

Date: Oct 25, 2022 Time: 1:30 p.m. - 3:00 p.m.

Answer ALL Three questions. Marks are shown in square brackets.


S&AS: STAT2602/STAT3902

1. Let X = {X1 , X2 , · · · , X30 } be an independent random sample from the discrete


distribution f (x), where
1
f (x) = , for x = 1, 2.
2
(1) Find the distribution of X1 + 3X2 by using the m.g.f. [5 marks]
30
1 X
(2) Specify the approximated distribution of Xi . [5 marks]
30 i=1

[Total: 10 marks]

2. Let X = {X1 , X2 , · · · , Xn } be an independent random sample from a uniformly


distribution over the interval [β, 0]. Find the MLE of β.
[Total: 10 marks]

3. Suppose that X = ξ1 − ξ2 , where ξ1 ∼ N (θ, 1), ξ2 ∼ N (λθ, λ2 ), and ξ1 and ξ2 are


independent. Here, λ ≥ 1 is a given constant, and θ is a unknown parameter.

(i) Calculate the moment generating function of X. [5 marks]


(ii) Calculate E(X 2 ). [3 marks]
(iii) Specify the distribution of X. [2 marks]
(iv) Let X1 , X2 , · · · , Xn be an independent random sample from the distribution
of X. Find the MLE of θ (denoted by θb1 ). [10 marks]
(v) Will θb1 be the UMVUE of θ and why? [10 marks]
n   i
1 X 1
(vi) Let θb2 = Xi be another estimator of θ. Calculate the mean
1 − λ i=1 2
squared error of θb2 . [5 marks]
(vii) Will θb2 be better than θb1 in terms of mean squared error and why? [5 marks]
[Total: 40 marks]

P. 2 of 3
S&AS: STAT2602/STAT3902

A LIST OF STATISTICAL FORMULAE

dr
 
1. MX (t) = E(e ). tX
MX (t) = µ0r .
dtr t=0

2. For X ∼ N(µ, σ 2 ),

(x − µ)2
   
1 1 22
fX (x) = √ exp − , MX (t) = exp µt + σ t .
2πσ 2 2σ 2 2

n n
1X 2 1X 2
3. X = Xi . S = Xi − X .
n i=1 n i=1
h i h i2
4. Bias(θ̂) = E(θ̂) − θ. E (θ̂ − θ)2 = Var(θ̂) + Bias(θ̂) .
" 2 #  2 
∂ ln f (X; θ) ∂ ln f (X; θ) 1
5. I(θ) = E =E − . Var(θ̂) ≥ .
∂θ ∂θ2 nI(θ)

6. Factorization: f (x1 , · · · , xn ; θ) = g T (x1 , · · · , xn ); θ h(x1 , · · · , xn ).
s
!
X
7. Expontial family: f (x; θ) = h(x)c(θ) exp pi (θ)ti (x) .
i=1

********** END OF PAPER **********

P. 3 of 3

You might also like