Scribd
Upload
55 views2 pages

Estimation: Unbiased Estimates of Population Mean and Variance

This document discusses population parameters, sample statistics, and methods for estimating population values from samples. Specifically, it notes that: 1) Population parameters are denoted with Greek letters while sample statistics use Roman letters. 2) Unbiased estimates of a population's mean and variance are those where the expected value of the statistic equals the true population parameter. 3) The variance of a sample estimate of a population's variance is equal to the population variance divided by the sample size.

Uploaded by

Strix
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
55 views2 pages

Estimation: Unbiased Estimates of Population Mean and Variance

This document discusses population parameters, sample statistics, and methods for estimating population values from samples. Specifically, it notes that: 1) Population parameters are denoted with Greek letters while sample statistics use Roman letters. 2) Unbiased estimates of a population's mean and variance are those where the expected value of the statistic equals the true population parameter. 3) The variance of a sample estimate of a population's variance is equal to the population variance divided by the sample size.

Uploaded by

Strix
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
Download as pdf or txt
Download as pdf or txt
You are on page 1/ 2

6.

Estimation
Syllabus A2 Statistic

Be cautious which is population, which is sample

Population's parameters are denoted by Greek letters: μ, σ 2

Population's parameters estimated from a sample are denoted by Roman letters: x, s2

Unbiased estimates of population mean and variance:


Sampling error will cause bias results, bias = ∣s2 − μ2 ∣
Estimates of a population’s mean and variance are called population statistics

Statistic is not bias estimate of a given population parameter only when x =μ


^ is some statistic derived from a random sample taken from a population, then
If U
^ is an unbiased estimate for U if E(U
U ^) = U

The larger the population variance, the data is more spreading so it's less likely the
sample data can be representative to the population
n−1
E(V ) = × σ 2 ; expected variance from all the possible sample of the
n
population

Variance for the population can be estimated as:

⭐ s = 21
n−1
(∑x −
2 (∑ x)2
n
)=
∑(x − x)2
n−1
; where n is the

sample size

We can use X (n) ∼ N(x, s2 /n) to prove hypotheses

Confidence interval for population mean:

6. Estimation 1
When estimated, 95% of sample means x lie
within the 95% confidence interval (CI) ⭐ (x − z.
σ
n
;x +
Note that CI's % is two-tailed, minus 2 sides
)
σ
z.
Higher percentage means more range n
covered
σ
Sample size n increases narrows the interval is standard error
n

Using large sample:

6. Estimation 2

You might also like