Topic1: Understanding Confidence Interval Estimates for the Population Mean

Definitions:
1. Confidence Interval - An interval estimate, called confidence interval, is a range of values that is used
to estimate the parameter. This estimate may or may not contain the true parameter value
2. Confidence Level- The confidence level of an interval estimate of the parameter is the probability that
the interval estimates contains the parameter. It describe what percentages of interval from many
different samples that contain the unknown population parameter. This estimate may or may not
contain the value of the parameter.
*Three common confidence intervals are used : the 90%, the 95% and the 99% confidence intervals
3. Critical Values- For another level of confidence interval, the corresponding z- values can be found in the
z table. These z values are also called confidence coefficients. They are also called critical values.
Summarized Table for Critical Values
Confidence level 90% 95% 99%
Level of significance 𝜶
Two tailed
𝒁𝜶
𝟐
One tailed
𝒁𝜶

 Formula for the confidence interval of the mean for a specific 𝛼

𝝈 𝝈
̅ − 𝒛𝜶 ( ) < 𝝁 < 𝑿
𝑿 ̅ + 𝒛𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏

Lower confidence boundary or limit Upper confidence boundary or limit

*Margin of error

𝝈
 In the general formula for confidence interval, the term 𝒛𝜶 ( ) is called margin of error , denoted by
𝟐 √𝒏
E, which is defined as the maximum likely difference between the observed sample mean and true
value of the population mean 𝜇
𝝈
𝑬 = 𝒛𝜶 ( )
𝟐 √𝒏

*A Four step Process in computing the Interval Estimate

Step 1: Describe the population parameter of interest ( e.g mean)
Step 2: Specify the confidence interval criteria
A. Check the assumption
B. Determine the test statistic to be used
C. State the level of confidence
Step 3: Collect and present sample evidence
A. Collect the sample information
B. Find the point estimate
Step 4: determine the confidence interval
A. Determine the confidence coefficients
B. Find the maximum error E of the estimate
C. Find the lower and upper confidence limits
D. Describe and interpret the result
Example:

A random sample of 100 students are asked how much they spend for a meal during weekdays. The average
expenses is found to be Php. 75. past experience has revealed that the population standard deviation of Php. 5.
find the point estimate of the interval estimate of the population mean 𝝁 𝒖𝒔𝒊𝒏𝒈 𝟗𝟓 % confidence level

Step Solution

1. describe the population parameter The parameter of interest is the population mean ( 𝝁) where the sample
of interest ( e.g mean) came from
2. Specify the confidence interval criteria
A. Check the assumption The sample size is 100 students is large enough for Central Limit Theorem
(CLT), so the sampling distribution of means is normal
B. Determine the test statistic to be The Test Statistic is z, using 𝝈 = 𝟓
used
C. State the level of confidence 95 % confidence level , 𝜶 = 𝟎. 𝟎𝟓
3. Collect and present sample evidence

A. Collect the sample 𝑋̅ = 75, 𝑛 = 100 𝑎𝑛𝑑 𝜎 = 5

information
B.Find the point estimate 𝜇 = 75

4. determine the confidence interval

Determine the confidence The confidence coefficient is 𝒛𝜶 = ±𝟏. 𝟗𝟔

coefficients
𝟐

Find the maximum error E of the 𝝈

𝑬 = 𝒛𝜶 ( )
𝟐√𝒏
𝟓
𝑬 = ±𝟏. 𝟗𝟔 ( )
√𝟏𝟎𝟎
𝑬 = 𝟎. 𝟗𝟖

Find the lower and upper ̅−𝑬<𝝁<𝑿

𝑿 ̅ +𝑬
confidence limits 𝟕𝟓 − 𝟎. 𝟗𝟖 < 𝝁 < 𝟕𝟓 + 𝟎. 𝟗𝟖
𝟕𝟒. 𝟎𝟐 < 𝝁 < 𝟕𝟓. 𝟗𝟖
Describe and interpret the result With the 95 % confidence then the interval between Php. 74.02 and
Php. 75.98 contain the population mean based on the 100 students
expenses

Note :

𝒏 ≥ 𝟑𝟎: Large Sample , Central Limit Theorem applies , Test Statistic to be used: Z- test

𝒏 < 𝟑𝟎 :Small Sample , Central Limit Theorem do not applies , Test Statistic to be used : t- test

 Example 2: A researcher wants to estimate the number of hours that a 5 year old children spend
watching television . A sample of 50 five year old children was observed to have a mean viewing time
 of 3 hours. The population is normally distributed with a population S. D 0.05 having 95 % confidence
interval

Shortcut solution:

1) The parameter of interest is the population mean ( 𝜇) where the sample came from
2) A) 𝑛 = 50, 𝑙𝑎𝑟𝑔𝑒 𝑠𝑎𝑚𝑝𝑙𝑒 𝐶𝐿𝑇( 𝑐𝑒𝑛𝑡𝑟𝑎𝑙 𝑙𝑖𝑚𝑖𝑡 𝑡ℎ𝑒𝑜𝑟𝑒𝑚 )𝑎𝑝𝑝𝑙𝑖𝑒𝑠
B) Test statistic : Z test
C) Confidence Level: 95 %, then 𝛼 = 0.05

3) A) Given
𝑋̅ = 3 ℎ𝑜𝑢𝑟𝑠 , 𝑛 = 50 𝑎𝑛𝑑 𝜎 = 0.05 (𝑆. 𝐷)

B) Point Estimate:
𝜇 = 3ℎ𝑟𝑠

4) A) The confidence coefficient is 𝒛𝜶 = ±𝟏. 𝟗𝟔

𝟐

B)
𝝈
𝑬 = 𝒛𝜶 ( )
𝟐 √𝒏
𝟎. 𝟎𝟓
𝑬 = ±𝟏. 𝟗𝟔 ( )
√𝟓𝟎
𝟎. 𝟎𝟓
𝑬 = ±𝟏. 𝟗𝟔 ( )
𝟕. 𝟎𝟕
𝑬 = ±𝟏. 𝟗𝟔 (𝟎. 𝟎𝟏)
𝑬 = ±𝟎. 𝟎𝟐
C)

̅−𝑬<𝝁<𝑿
𝑿 ̅+𝑬
𝟑 − 𝟎. 𝟎𝟐 < 𝝁 < 𝟑 + 𝟎. 𝟎𝟐
𝟐. 𝟗𝟖 < 𝝁 < 𝟑. 𝟎𝟐

D) With the 95 % confidence then the interval between 2.98 hours and 3.02 hours contain the
population mean based on the 50 five year old children
  GROUP ACTIVITY : You can Z it! (Confidence Interval for the
Population Mean when the Variance is Known)

Directions: Determine the confidence interval of the following problems below

using the four step solution:

1. A sample of 60 Grade 9 students’ ages was obtained to estimate the

mean age of all Grade 9 students. The population mean was 15.3 years
and the population variance is 16. Using a 99% confidence level.
2. Given the information: the sample population is normally distributed,
𝑋= 36.5, 𝜎= 3 and n = 20. Using a 95% confidence level
3. To determine the average daily entry-level job salary in a province, 80
entry-level employees were asked about theirs. It was found out that
their average salary per day us Php 510. The population standard
deviation is is equal to Php 6. Using a 90% confidence level, determine
the level of significance, critical value, margin of error and the
confidence interval
4. A random sample of 100 car owners in Metro Manila shows that a car
driven on the average of 13, 500 km per year with a standard deviation
of 1,900 km . with a 99% confidence interval find the confidence
interval for average number in kilometers a car driven annually.
Topic 2: Confidence Interval for Mean when 𝜎 is unknown and 𝑛 < 30
• When the population standard deviation is unknown and the sample size is less than 30, the standard
deviation from the sample can be used in place of the population standard deviation . A different
distribution , called t- distribution must be used when the variable is normally or approximately
normally distributed
Properties of t- Distribution
• The t- distribution is similar to standard normal distribution in the following ways
• It is bell-shaped
• It is symmetrical about the mean
• The mean, median and mode are equal to 0 and are located at the center of the distribution
• The curve never touches the x- axis
• Properties of t- Distribution
• The t- distribution differs from the standard normal distribution in the following ways
• The variance is greater than 1
• The t- distribution is a family of the curves based on the degrees of freedom, which is a number
related to sample size
• As the sample size increases, the t distribution approaches the normal distribution
Degrees of Freedom

• The degrees of freedom are the number of values that are free to vary after a sample statistic has
been computed. The symbol d. f. will be used for degree of freedom. The degrees of freedom for
confidence interval for the mean is 𝑛 − 1

Example : Use the t- distribution table :

1. Find the 𝑡𝛼 for 99% confidence interval when sample size is 20

2

𝛼 0,01
Solution : 𝑑. 𝑓. = 𝑛 − 1 = 20 − 1 = 19, 𝑐𝑙 = 99%, 𝛼 = 0. 01 , 𝑡𝑤𝑜 𝑡𝑎𝑖𝑙𝑒𝑑 = = 0.005
2 2
answer: 𝒕𝜶=𝟐.𝟖𝟔𝟏
𝟐

2. 𝑛 = 6, 90 % 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒
𝛼 0,10
Solution : 𝑑. 𝑓. = 𝑛 − 1 = 6 − 1 = 5, 𝑐𝑙 = 90%, 𝛼 = 0. 10, 𝑡𝑤𝑜 𝑡𝑎𝑖𝑙𝑒𝑑 2
= 2
= 0.05
answer: 𝒕𝜶=𝟐.𝟎𝟏𝟓
𝟐
3. 𝑛 = 8, 99 % 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒
𝛼 0,01
Solution : 𝑑. 𝑓. = 𝑛 − 1 = 8 − 1 = 7, 𝑐𝑙 = 99%, 𝛼 = 0. 01, 𝑡𝑤𝑜 𝑡𝑎𝑖𝑙𝑒𝑑 = = 0.005
2 2

answer: 𝒕𝜶=𝟏.𝟖𝟗𝟓
𝟐

*Margin of Error

the maximum error E of the estimate

𝑠
𝐸 = 𝑡𝛼 ( )
2 √𝑛
Formula for Specific Confidence Interval for the Mean when 𝝈 is unknown
𝑠 𝑠
𝑋̅ − 𝑡𝛼 ( 𝑛) < 𝜇 < 𝑋̅ + 𝑡𝛼 ( 𝑛)
2 √ 2 √

𝑑. 𝑓 = 𝑛 − 1

Example :

A random sample of 12 graduates of a certain secretarial school typed an average of 73.9 word per
minute(wpm) with a S.D of 8.7 wpm. Assuming that the number of words typed per minute is approximately
normally distributed, find the 95% interval for the average number of words typed by all the graduates of this
school
• Solution :
From the given we have 𝑛 = 12, 𝑥 = 73.9
𝑎𝑛𝑑 𝑠 = 8.7 . Notice that a sample size is small and the population standard deviation is unknown, so t-
distribution must be used
𝛼
Since we require 95% confidence interval, 𝛼 = 0.05 𝑠𝑜 = 0.025.the d.f is n-1=12-1=11. so the C.V is
2
𝑡𝛼 = 2.201
2

𝑠 𝑠
𝑋̅ − 𝑡𝛼 ( ) < 𝜇 < 𝑋̅ + 𝑡𝛼 ( )
2 √𝑛 2 √𝑛

8.7 8.7
73.9−2.201 ( ) < 𝜇 <73.9−2.201 ( )
√12 √12

68.37 < 𝜇 < 79.43

Interpretation:

With the 95 % confidence then the interval between 68.39 wpm and 79.43 wpm contain the
population mean based on the 12 graduates
 GROUP ACTIVITY : It’s T Time! ((Confidence Interval for the
Population Mean when the Variance is Unknown)

Directions: Determine the confidence interval of the following

problems below:
1. A researcher would like to know the average score of
students who took a 100-item Mathematics exam as part of
the National Achievement Test. To do this, he took the
scores of 20 students, and found out that their scores have
an average of 78.03 points with a sample standard deviation
of 4.12 points. At a 90% confidence level, determine the
confidence interval that ill estimate the mean.

2. The mean age of 20 youth volunteers in a community

project is 17.5 years with a standard deviation of 2 years. If
the sample comes an approximately normal distribution,
what is the interval estimate of the population mean? Use
99% confidence level.

3. The average weight of 25 chocolate bars selected from a

normally distributed population is 200g with a standard
deviation of 10g. Find the interval estimate using a 95%
confidence level.