Test Statistic and

Rejection Region for

the Population Mean

MR. CESAR R. CAIRO

April 1-5, 2024
Instructor
OBJECTIVES:

❑ formulates the appropriate null and alternative hypotheses

on a population mean. M11/12SP-IVb-1

❑ identifies the appropriate form of the test-statistic when:

M11/12SP-IVb-1

(a) the population variance is assumed to be known;

(b) the population variance is assumed to be unknown; and
(c) the Central Limit Theorem is to be used.
Questions:

- How do you determine whether

a statement is a hypothesis?
- How do you differentiate the
null and alternative hypotheses?
The Null and Alternative Hypotheses on a
Population Mean
ASSUMPTIONS
A statistical test of hypotheses consists
of five parts enumerated as follows:

1. Null hypothesis 𝐻𝑜
2. Alternative hypothesis 𝐻𝑎
3. Test statistic and its 𝑝-value
4. Rejection region
5. Conclusion
 Statistical Hypothesis
a statement about population parameters

Example:
The daily mean number of customers of a coffee shop is 105.

Null Hypothesis
the hypothesis that is assumed to be true. It uses a relation symbol with a
statement of equality, such as ≥, ≤, and =, and is denoted by 𝐻0.

Example:
The average life expectancy 𝜇1 of females is the same as the
average life expectancy 𝜇2 of males. (𝐻0 : 𝜇1 = 𝜇2 )
 Alternative Hypothesis
the hypothesis that is contrary to the null hypothesis. It uses a relation symbol with
no statement of equality, such as >, <, and ≠, and is denoted by 𝐻𝐴 .

Example:
The average life expectancy 𝜇1 of females is different from the
average life expectancy 𝜇2 of males. (𝐻𝐴 : 𝜇1 ≠ 𝜇2 )
Example 1:
It is claimed that the average pulse rate of male joggers is at
least 80 beats per minute. You want to show that this is not
true. Construct the null and alternative hypotheses.
𝑯𝑶 : 𝝁 ≥ 𝟖𝟎 beats per minute
𝑯𝑨 : 𝝁 < 𝟖𝟎 beats per minute
Example 2:
A gym advertises that the average weight loss of people who
enrolled in them for 3 months is at least 15 pounds. You
doubt their advertisement. Write the null and alternative
hypotheses.
𝑯𝑶 : 𝝁 ≥ 𝟏𝟓 𝒑𝒐𝒖𝒏𝒅𝒔
𝑯𝑨 : 𝝁 < 𝟏𝟓 𝒑𝒐𝒖𝒏𝒅𝒔
Forms of Test Statistic for the Population Mean

Test Statistic
a random variable that is used in a hypothesis test

Example:
The test statistic used in a 𝑧-test is the 𝑧-statistic.

𝒛-statistic
the test statistic used in a hypothesis test for the population mean when the
population standard deviation is known and (a) the population is normal OR (b)
the sample size is sufficiently large, usually greater than or equal to 30
The 𝑧-statistic is given by

𝑥−𝜇
𝒛= 𝜎
𝑛

Example:
A head teacher claims that the mean IQ of students in their
school is above average. The mean population IQ is 150 with
a standard deviation of 13. A random sample of 30 of their
students have an average IQ of 151. Is there enough evidence
to support the head teacher’s claim?
 𝒕-statistic
the test statistic used in a hypothesis test for the population mean when the
population standard deviation is unknown and when the sample size is small,
usually less than 30

The 𝑡-statistic is given by

𝑥−𝜇
𝒕= 𝑠
Example: 𝑛
A head teacher claims that the mean IQ of students in their
school is above average. The mean population IQ is normally
distributed with a mean of 150. A random sample of 10 of
their students have an average IQ of 151. Is there enough
evidence to support the head teacher’s claim?
Practice 1:
The owner of a car rental agency claims that the mileage of
their cars is normally distributed with a mean of 8 000.
A sample of seven of their cars has an average mileage of
6490. What test statistic should be used in this case?

Practice 2:
A car manufacturer claims that the gas consumption of their
new model is 25 km/L with a standard deviation of 5 km/L.
A simple random sample of 64 cars of this model is chosen
and found out to have a mean gas consumption of 27.5
km/L. What test statistic should be used in this case?
The Rejection Region for the Population Mean

Rejection Region
the interval of values of the test statistic for which the null hypothesis is rejected

Relation Symbols in
Type of
the Hypotheses Rejection Region
Test
𝑯𝑶 𝑯𝑨
To the left of −𝑧𝛼Τ2 and
= ≠ Two-tailed
to the right of 𝑧𝛼Τ2
≥ < Left-tailed To the left of −𝑧𝛼
≤ > Right-tailed To the right of 𝑧𝛼
 Level of Significance
the probability of rejecting the null hypothesis in favor of the alternative
hypothesis when it is true, denoted by 𝛼

Example:
A significance level of 𝛼 = 0.05 means that there is a 5%
chance of rejecting a true null hypothesis.
Example 1: The owner of a car rental agency claims that the mileage of
their cars is normally distributed with an average of at most 8 000. A
sample of seven of their cars has an average mileage of 8 490 with a
standard deviation of 460 miles. In testing the hypothesis that the
average mileage of the cars is more than 8 000, if the level of significance
is set to 𝛼 = 0.05, what is the area of the rejection region and where is it
located?

Solution:
1. Identify the hypotheses.
𝐻𝑂 : 𝜇 ≤ 8 000 miles
𝐻𝐴 : 𝜇 > 8 000 miles
2. Identify the rejection region.
Example 2: A car manufacturer claims that the gas
consumption of their new model is 25 km/L with a standard
deviation of 5 km/L. A simple random sample of 64 cars of
this model is chosen and found out to have a mean gas
consumption of 27.5 km/L. Illustrate the rejection region if
𝛼 = 0.10.

Solution:
1. Identify the hypotheses.
𝐻𝑂 :𝜇 = 25 km/L
𝐻𝐴 :𝜇 ≠ 25 km/L
2. Identify the rejection region.
𝛼 0.10
= = 0.05
2 2
 KEY POINTS
Statistical Hypothesis
1 a statement about population parameters

2 Null Hypothesis
the hypothesis that is assumed to be true. It uses a relation symbol with a
statement of equality, such as ≥, ≤, and =, and is denoted by 𝐻0.

3 Alternative Hypothesis
the hypothesis that is contrary to the null hypothesis. It uses a relation symbol with
no statement of equality, such as >, <, and ≠, and is denoted by 𝐻𝐴 .
 Test Statistic
4 a random variable that is used in a hypothesis test

5 𝒛-statistic
the test statistic used in a hypothesis test for the population mean when the
population standard deviation is known and (a) the population is normal OR (b)
the sample size is sufficiently large, usually greater than or equal to 30

6 𝒕-statistic
the test statistic used in a hypothesis test for the population mean when the
population standard deviation is unknown and when the sample size is small,
usually less than 30
 Rejection Region
7 the interval of values of the test statistic for which the null hypothesis is rejected

Relation Symbols in
Type of
the Hypotheses Rejection Region
Test
𝑯𝑶 𝑯𝑨
To the left of −𝑧𝛼Τ2 and
= ≠ Two-tailed
to the right of 𝑧𝛼Τ2
≥ < Left-tailed To the left of −𝑧𝛼
≤ > Right-tailed To the right of 𝑧𝛼
 Level of Significance
8 the probability of rejecting the null hypothesis in favor of the alternative
hypothesis when it is true, denoted by 𝛼

First Steps in Hypothesis Testing for the Population

9
Mean
1. Formulate the null hypothesis.
2. Formulate the alternative hypothesis.
3. Determine the test statistic to be used.
4. Determine the type of tail test and the rejection region.
TRY THIS!
1. A random sample of 41 gallons of paint selected from the
production line of a paint manufacturing company showed a
mean drying time of 50 minutes with a standard deviation of
2.7 minutes. Test the hypothesis that the mean drying time of
the paint is more than 48 minutes at 𝛼 = 0.05.

𝑯𝑶 : 𝝁 ≤ 𝟒𝟖 minutes 𝒛-statistic can be

𝑯𝑨 : 𝝁 > 𝟒𝟖 minutes used
2. A brand of tire claims that its first-class tire averages at
least 65 000 miles before it needs to be replaced. From past
studies about the tire, the standard deviation is known to be
4 700 miles. A survey on the tire design is conducted by store
managers. Based on the 50 tires surveyed, the mean lifespan
was 61 000 miles. Test the brand’s claim at 𝛼 = 0.10.

𝑯𝑶 : 𝝁 ≥ 𝟔𝟓 𝟎𝟎𝟎 miles 𝒛-statistic can be

𝑯𝑨 : 𝝁 < 𝟔𝟓 𝟎𝟎𝟎 miles used
Thank You
for
Listening!