0% found this document useful (0 votes)
34 views5 pages

Lecture 5

This chapter discusses estimation methods including point and interval estimation. It explains maximum likelihood estimation and provides examples estimating parameters for exponential, normal, and uniform distributions. The maximum likelihood estimation method finds the values of parameters that make the observed sample most likely. For example, the maximum likelihood estimators of the mean (μ) and variance (σ2) of a normal distribution are the sample mean (X̅) and unbiased sample variance respectively.

Uploaded by

alcinialbob1234
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
0% found this document useful (0 votes)
34 views5 pages

Lecture 5

This chapter discusses estimation methods including point and interval estimation. It explains maximum likelihood estimation and provides examples estimating parameters for exponential, normal, and uniform distributions. The maximum likelihood estimation method finds the values of parameters that make the observed sample most likely. For example, the maximum likelihood estimators of the mean (μ) and variance (σ2) of a normal distribution are the sample mean (X̅) and unbiased sample variance respectively.

Uploaded by

alcinialbob1234
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/ 5

Statistical Methods Dr.

Asmaa El-Toony

Chapter 4
Estimation

This chapter explains how to estimate some population parameters


After completing this chapter, you should be able to:
1) Identify point and interval estimation
2) Find the maximum likelihood estimation
3) Find the confidence interval for the population mean
4) Find the confidence interval for the difference between two population
means
5) Find the confidence interval for the population proportion.
Statistical Methods Dr. Asmaa El-Toony

Estimation: Is the process of estimating the value of a parameter from


information obtained from a sample.

The estimate is a single computed value, but the estimator is the rule that tell us
how to compute this value, or estimate. For example, 𝑋̅ is an estimator of the
population mean, . The single numerical value that results from evaluating this
formula is called an estimate of the parameter .

Estimate: The value(s) assigned to a population parameter based on the value


of an observed random sample.

Estimator: The sample statistic used to estimate a population parameter

There are two types of estimation:


• Point Estimate: The value of the sample statistic that is used to estimate
the population parameter.
• Interval Estimate: Is an interval or a range of values used to estimate the
population parameter.
Statistical Methods Dr. Asmaa El-Toony

Maximum likelihood Estimation:


Let X1, X2, …, Xn be a r.s from a distribution that depends on unknown parameters
𝜃1 , 𝜃2 , … , 𝜃𝑚 with pmf or pdf 𝑓(𝑥; 𝜃1 , 𝜃2 , … , 𝜃𝑚 ).
(1) 𝐿(𝜃1 , 𝜃2 , … , 𝜃𝑚 ) = 𝑓(𝑥1 ; 𝜃1 , 𝜃2 , … , 𝜃𝑚 ) ∗ 𝑓(𝑥2 𝑥; 𝜃1 , 𝜃2 , … , 𝜃𝑚 ) ∗ . .∗
𝑓(𝑥𝑚 ; 𝜃1 , 𝜃2 , … , 𝜃𝑚 )
𝑛
𝐿(𝜃) = ∏𝑖=1 𝑓(𝑥𝑖 ; 𝜃).

(2) 𝑙(𝜃) = ln 𝐿 (𝜃)


𝜕
(3) 𝑙(𝜃) = 0
𝜕𝜃

Example 1: Let X1, X2, …, Xn be a r.s from the exponential distribution with
pdf
𝑥
1
𝑓(𝑥; 𝜃) = 𝑒 −𝜃 𝑥 >0; 𝜃 >0
𝜃
Find the maximum likelihood estimator of 𝜃.

Solution

(1) 𝐿(𝜃) = ∏𝑛𝑖=1 𝑓(𝑥𝑖 ; 𝜃)


1 𝑥1 1 𝑥2 1 𝑥𝑛
= 𝑒 − 𝜃 ∗ 𝑒 − 𝜃 ∗ … … .∗ 𝑒 − 𝜃
𝜃 𝜃 𝜃
∑𝑛
𝑖=1 𝑥𝑖
−𝑛 −
= 𝜃 𝑒 𝜃
1
(2) 𝑙(𝜃) = ln 𝐿 (𝜃) = −𝑛 ln(𝜃) − ∑𝑛𝑖=1 𝑥𝑖
𝜃

𝜕 𝑛 ∑𝑛𝑖=1 𝑥𝑖
(3) 𝑙(𝜃) = − + =0
𝜕𝜃 𝜃 𝜃2
Statistical Methods Dr. Asmaa El-Toony

The solution of this equation is


𝑛
1
𝜃= ∑ 𝑥𝑖 = 𝑥̅
𝑛
𝑖=1

Then the maximum likelihood estimator for 𝜃 𝑖𝑠:


𝑛
1
𝜃̂ = ∑ 𝑋𝑖 = 𝑋̅
𝑛
𝑖=1

Example 2: Let X1, X2, …, Xn be a r.s from the Normal distribution with pdf
𝑥−𝜇
1 −
𝑓(𝑥; 𝜇, 𝜎 2 ) = 𝑒 2𝜎2 ; −∞ < 𝜇 < ∞, 𝑥, 𝜎 2 > 0
√2𝜋 𝜎
Find the maximum likelihood estimators of 𝜇, 𝜎 2 .

Solution

(1) 𝐿(𝜇, 𝜎 2 ) = ∏𝑛𝑖=1 𝑓(𝑥𝑖 ; 𝜇, 𝜎 2 )


𝑛
1 −
1
∑𝑛
𝑖=1(𝑥𝑖 −𝜇)
2
= ( ) 𝑒 2𝜎2
√2𝜋 𝜎
𝑛 1
− ∑𝑛 (𝑥 −𝜇)2
= (2𝜋)− 2 𝜎 −𝑛 𝑒 2𝜎 2 𝑖=1 𝑖

𝑛 1
(2) 𝑙(𝜃𝜇, 𝜎 2 ) = ln 𝐿 (𝜃𝜇, 𝜎 2 ) = − ln(2𝜋) − 𝑛 ln 𝜎 − ∑𝑛𝑖=1(𝑥𝑖 − 𝜇)2
2 2𝜎 2

𝑭𝒐𝒓 𝝁:
𝑛
𝜕 1
(3) 𝑙(𝜇, 𝜎 2 ) = 2 ∑(𝑥𝑖 − 𝜇) = 0
𝜕𝜇 𝜎
𝑖=1

The solution of this equation is


𝜇 = 𝑥̅
Statistical Methods Dr. Asmaa El-Toony

𝐹𝑜𝑟 𝜎 2 :
𝑛
𝜕 𝑛 1
(3) 𝑙(𝜇, 𝜎 2 ) = − + 3 ∑(𝑥𝑖 − 𝜇)2 = 0
𝜕𝜎 𝜎 𝜎
𝑖=1

The solution of this equation is


𝑛
1
𝜎 2 = ∑(𝑥𝑖 − 𝜇)2
𝑛
𝑖=1

Then the maximum likelihood estimators for 𝜇 𝑎𝑛𝑑 𝜎 2 𝑎𝑟𝑒:


𝑛

𝜇̂ = 𝑋̅, ̂2 = 1 ∑(𝑋𝑖 − 𝑋̅)2


𝜎
𝑛
𝑖=1

Exercise

(1) Suppose X1, X2, …, Xn be a r.s from a distribution with pdf


𝑓(𝑥; 𝜃) = 𝜃 𝑥 𝜃−1 0 < 𝑥 < 1, 𝜃 > 0.
Find the maximum likelihood estimator of 𝜃.

(2) Suppose X1, X2, …, Xn be a r.s from a distribution with pdf


𝑓(𝑥; 𝜃) = 𝑒 𝜃−𝑥 𝑥 > 𝜃.
Find the maximum likelihood estimator of 𝜃.

(3) Suppose X1, X2, …, Xn be a r.s from a uniform distribution with pdf
1
𝑓(𝑥; 𝜃) = 0 < 𝑥 < 𝜃.
𝜃
Find the maximum likelihood estimator of 𝜃.

You might also like