Scribd
Upload
19 views

Statistics Chp8-2

The document discusses interval estimation, including how to calculate confidence intervals for a population mean or proportion. It provides examples of how to determine margin of error, sample size, confidence levels, degrees of freedom, and how to look up t and z values in tables. Practice questions with answers are also included.

Uploaded by

Jennifer Limertha
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
19 views

Statistics Chp8-2

The document discusses interval estimation, including how to calculate confidence intervals for a population mean or proportion. It provides examples of how to determine margin of error, sample size, confidence levels, degrees of freedom, and how to look up t and z values in tables. Practice questions with answers are also included.

Uploaded by

Jennifer Limertha
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/ 35

Chp.

Statistics:
Interval Estimation

Professor: Lee Yung Hsin 李永新


[email protected]

TA: [email protected]
MS Teams : [email protected]
Interval Estimate : tells you how close the point estimate is to the value of the parameter

*a parameter is a number that describes a whole population,


while a statistic is a number that describes a sample

Interval Estimate =
Interval Estimate of a Population Mean ( μ ) : σ (SD) Known

Later it will be written as this:


Values for Zɑ/2

**From the formula you can see that we can reduce


the margin of error by:
● Population SD ↓
● Sample size n ↑
● Confidence level ↓
Estimation Process, “Confidence Level”
Understanding these values: How do we get the values for
Zɑ/2 from this table?

1. Check the confidence level used in the question


(“At 95% confidence…”)
95% = confidence level, 0.95 = confidence coefficient

2. If confidence level = 95%,


that means ɑ = 100% - 95% = 5%, which is 0.05
So ɑ/2 = 0.025

3. So we have to see which z value in the table will give


the result of ( 1 - ɑ/2 ) -> For 95% confidence, we have
to find z value for ( 1 - 0.025 = 0.9750 )

4. From the table we can see that Zɑ/2 = 1.96


How do we get the values for Zɑ/2 from
this table?

1. Check the confidence level used in


the question (“At 95% confidence…”)
95% = confidence level,
0.95 = confidence coefficient

2. If confidence level = 95%,


that means ɑ = 100% - 95% = 5%,
which is 0.05
-> So ɑ/2 = 0.025

3. So we have to see which z value


in the table will give the result of
( 1 - ɑ/2 ) -> For 95% confidence,
we have to find z value for
( 1 - 0.025 = 0.9750 )

4. From the table we can see that


Zɑ/2 = 1.96
Example - Interval Estimate of a Population Mean: σ (SD) Known

Q: A sample of 11 circuits from a normal population has a mean resistance of 2.20 ohms.
We know from past testing that the population standard deviation is 0.35 ohms.
Determine a 95% confidence interval for the true mean resistance of the population

A:

We are 95% confident that the true mean


resistance is between 1.9932 and 2.4068 ohms
How do we get the values for t (ɑ/2)
from this t distribution table ?

1. Check the confidence level used in the question


(“At 95% confidence…”)
95% = confidence level,
0.95 = confidence coefficient

2. If confidence level = 95%,


that means ɑ = 100% - 95% = 5%, which is 0.05
-> So ɑ/2 = 0.025
-> We will be looking at t₀₋₀₂₅ in the table

3. Calculate the degrees of freedom. If n = 10, then


d.f = ( 10 - 1 ) = 9

4. Check from the table, the value for d.f=9


and 0.025 to find t₀₋₀₂₅ = 2.262
Interval Estimate of a Population Mean ( μ ) : σ (SD) Unknown

*We have to use the t distribution


table instead of z table (normal
distribution table)

Later it will be written as this:

The t value depends on


“degrees of freedom” (d.f)

where
d.f = n - 1
Example - Interval Estimate of a Population Mean: σ (SD) Known

Q: A random sample of n = 25 has x = 50 and s = 8. Form a 95% confidence interval for μ

A:
Practice Q1 :

Q2:
Answers
Q1 :
Answers
Q2 :
Sample Size for an Interval Estimate of a Population Mean ( μ )

We know that the Margin of error = , where n = sample size

So to find Sample size:


Example - Sample Size for an Interval Estimate of a Population Mean

Q:

A:

**If the value of n is not a whole number, ROUND UP to the nearest whole number
Practice - Sample Size for an Interval Estimate of a Population Mean

Q:
Answer

A:
Interval Estimate of a Population Proportion ( p )

Interval Estimate:

Interval Estimate of a
Population Mean :

And it will be expressed as this:

Interval Estimate of a
Population Proportion :

And it will be expressed as this:


Example - Interval Estimate of a Population Proportion ( p )
Q:

A:
Example - Interval Estimate of a Population Proportion ( p )
Q:

A:
Practice - Interval Estimate of a Population Proportion ( p )

Q:
Answers
Q:

A:
Sample Size for an Interval Estimate of a Population Proportion

We know that the Margin of error is E= , where n = sample size

So to find Sample size:

For this, we use p* instead of because we don’t know


before we select the sample.
Sample Size for an Interval Estimate of a Population Proportion

How to find p* :

If p* is not given, just use 0.5 as the estimate.

Example of a
question where
p* is given :
Example - Sample Size for an Interval Estimate of a Population Proportion
Q:

A:

**If the value of n is not a whole number, ROUND UP to the nearest whole number
Practice Questions

1.
Answers

1.
Practice Questions

2.

**part ii & v is just for your understanding


Answers

2.
Practice Questions

3.
Answers

3.
Practice Questions

4.
Answers

4.

You might also like