Scribd
Upload
6 views1 page

MH3500 Assignment03

This document outlines the requirements for Assignment 3 of the MH3500 Statistics course for AY2025/26 Semester 2. It includes instructions for submission, the necessity of showing intermediate steps, and a specific problem related to maximum likelihood estimation (MLE) of variance in a normal distribution. The assignment consists of three parts focusing on MLE, Fisher Information, and the Cramér-Rao Lower Bound (CRLB).

Uploaded by

Vũ Ngọc Linh
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
6 views1 page

MH3500 Assignment03

This document outlines the requirements for Assignment 3 of the MH3500 Statistics course for AY2025/26 Semester 2. It includes instructions for submission, the necessity of showing intermediate steps, and a specific problem related to maximum likelihood estimation (MLE) of variance in a normal distribution. The assignment consists of three parts focusing on MLE, Fisher Information, and the Cramér-Rao Lower Bound (CRLB).

Uploaded by

Vũ Ngọc Linh
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

MH3500 Statistics

Assignment 3 AY2025/26 Semester 2

Note:

• You are required to show the intermediate steps leading up to the final solution

• Solutions should be submitted via NTULearn as a single pdf file

• In case you scan your handwritten solutions, it is your responsibility to ensure that your
handwriting is legible

• Please take note of the submission deadline on NTULearn. Late submissions will not be
accepted.

Problem A3.1 (10 points)


Let 𝑋1 , … , 𝑋𝑛 be an i.i.d. sample drawn from a normal distribution 𝑁(𝜇, 𝜎 2 ). Assume that 𝜇
is a known constant and that 𝜎 2 is an unknown parameter.

a) Find the MLE of σ2 and show that it is unbiased.


b) Compute the Fisher Information 𝐼𝑋1 ,…,𝑋𝑛 (𝜎 2 ).
c) Assume that the conditions of the CRLB are satisfied. Show that the MLE of 𝜎 2 has
minimum variance amongst all unbiased estimators of σ2 .
𝑋1 −𝜇
[You may use the fact that for 𝑍 = ~𝑁(0,1) we have 𝑉𝑎𝑟(𝑍 2 ) = 2].
𝜎

You might also like