Scribd
Upload
16 views3 pages

Math 344

This document outlines the exam for MATH 344: Theory of Estimation. The exam contains 5 questions testing key concepts: (1) Defining estimation terms like mean square error consistency and deriving that a given estimator is biased. (2) Distinguishing between point and interval estimation and deriving a confidence interval for the difference between two sample means. (3) Finding information measures and sufficient statistics for distributions. (4) Defining uniformly minimum variance unbiased estimators and proving properties of consistent estimators. (5) Applying the Cramer-Rao inequality to show an estimator is UMVUE and finding an estimator for a distribution by the method

Uploaded by

xtnnjr
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
16 views3 pages

Math 344

This document outlines the exam for MATH 344: Theory of Estimation. The exam contains 5 questions testing key concepts: (1) Defining estimation terms like mean square error consistency and deriving that a given estimator is biased. (2) Distinguishing between point and interval estimation and deriving a confidence interval for the difference between two sample means. (3) Finding information measures and sufficient statistics for distributions. (4) Defining uniformly minimum variance unbiased estimators and proving properties of consistent estimators. (5) Applying the Cramer-Rao inequality to show an estimator is UMVUE and finding an estimator for a distribution by the method

Uploaded by

xtnnjr
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/ 3

MATH 344

CHUKA UNIVERSITY

UNIVERSITY EXAMINATIONS
EXAMINATION FOR THE AWARD OF DEGREE OF BACHELOR OF SCIENCE IN
ECONSTAT, BACHELOR OF ARTS ECON MATH AND BACHELOR OF SCIENCE
MATH 344: THEORY OF ESTIMATION
STREAMS: TIME: 2 HOURS
DAY/DATE: TUESDAY 30/03/2021 8.30 A.M – 10.30 A.M

INSTRUCTIONS:
Answer Question ONE and any other TWO questions.
All workings must be shown clearly

QUESTION 1[30 MARKS]


a) Define the following terms as used in theory of Estimation
(i) Mean square error consistency
(ii) An estimator
(iii) Unbiasedness
(iv) Sufficient statistic [8 marks]
b) Which one of the following is not an unbiased estimator of 𝜃,
given that 𝐸(𝑥𝑖 ) = 𝜃
𝑇1 = 𝑥1 + 𝑥2 + 𝑥3 + 𝑥4
𝑇2 = 2𝑥1 + 3𝑥2
𝑇3 = 4𝑥2 − 3𝑥3 [3 marks]
c) Differentiate between Point and Interval estimation [4 marks]
d) Let 𝑥𝑖 , 𝑖 = 1,2,3,4, be four independent sample observations of Poisson distribution with
1
parameter 𝜃. Show that 𝑇 = 15 (2𝑥1 + 4𝑥2 + 5𝑥3 + 3𝑥4 ) is a biased estimator of 𝜃.

Calculate the amount of bias. [5 marks]

Page 1 of 3
MATH 344

e) Let 𝑇1 be the most efficient estimator and 𝑇2 be the unbiased estimator for unknown
parameter 𝜃. If 𝜌 is the efficiency with respect to 𝑇1 , show that
1−𝜌
𝑉𝑎𝑟(𝑇1 − 𝑇2 ) = 𝜌
𝑣𝑎𝑟(𝑇1 ) [5 marks]
f) Find the sample size (n) of a random sample taken from a normal population with mean
𝜇 and variance 9 and given that 𝑋̅ is the mean of the random sample such that
𝑃[𝑥̅ − 1 < 𝜇 < 𝑥̅ + 1] = 0.9 [5 marks]

QUESTION 2 [20 MARKS]


a) Consider two random samples 𝑥1 , 𝑥2 , … , 𝑥𝑛1 of size n1 and 𝑦1 , 𝑦2 , … , 𝑦𝑛2 of size n2 both
from normal populations such that 𝑥~𝑁(𝜇1 , 𝜎12 ) and 𝑦~𝑁(𝜇2 , 𝜎22 ) respectively. Obtain
the (1 − 𝛼)100% confidence interval for (𝑥̅ − 𝑦̅). [7 marks]
𝑥 1−𝑥
b) The distribution of 𝑥is given by 𝑓(𝑥) = {𝜃 (1 − 𝜃) , 𝑥 = 0,1
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
Show that 𝑇 = ∑ 𝑥𝑖 is a sufficient statistic for 𝜃. [8Marks]

QUESTION 3 [20 MARKS]


1 1
a) Given 𝑓(𝑥, 𝜃) = 𝜋 . 1+(𝑥−𝜃)2 , −∞ < 𝑥 < ∞

Find 𝐼(𝜃) [15 Marks]


c) Find sufficient statistic for 𝛿 2 where 𝑥~𝑁(𝜇, 𝛿 2 ) [5 Marks]

QUESTION 4 [20 MARKS]


a) Define a uniformly minimum variance unbiased estimator (UMVUE) T of 𝜏(𝜃).
[5 Marks]
b) If T is a consistent estimator of 𝜃, ∅(𝑇) is also a consistent estimator of ∅(𝜃) where ∅ is
a continuous function, Proof. [15 Marks]

Page 2 of 3
MATH 344

QUESTION 5 [20 MARKS]


a) Let 𝑥1 , 𝑥2 … 𝑥3 be a random sample from a Poisson distribution with parameter 𝜃. Using
the Cramer-Rao inequality condition, show that the mean 𝑥̅ is UMVUE of the population
mean. [12 Marks]
b) Let 𝑦1 , 𝑦2 , … 𝑦𝑛 be a random sample with a distribution given as
2(𝛽 − 𝑦)
,0 < 𝑦 < 𝛽
𝑓(𝑥) = { 𝛽 2
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
i) Find an estimator of 𝛽 by method of moments [4 Marks]
ii) Determine if the estimator is unbiased [4 Marks]
---------------------------------------------------------------------------------------------------------------------

Page 3 of 3

You might also like