0% found this document useful (0 votes)
80 views17 pages

Statprob Q4 Module 6

This document provides a learning module on hypothesis testing for population means. It begins with an introduction explaining the purpose and contents of the module. It then states the expected learning outcomes which are to identify parameters to test in problems, draw conclusions based on test statistics and rejection regions, and solve problems involving hypotheses tests on population means. A pre-test with 4 multiple choice questions is provided to assess students' prior knowledge. The main content discusses testing hypotheses concerning population means, outlining the 3 cases and appropriate test statistics.
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)
80 views17 pages

Statprob Q4 Module 6

This document provides a learning module on hypothesis testing for population means. It begins with an introduction explaining the purpose and contents of the module. It then states the expected learning outcomes which are to identify parameters to test in problems, draw conclusions based on test statistics and rejection regions, and solve problems involving hypotheses tests on population means. A pre-test with 4 multiple choice questions is provided to assess students' prior knowledge. The main content discusses testing hypotheses concerning population means, outlining the 3 cases and appropriate test statistics.
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/ 17

11

Mathematics
Fourth Quarter
Module 6: Hypothesis Testing
(Population Mean)

Page 1 of 17
Republic of the Philippines
Department of Education
REGION VII-CENTRAL VISAYAS
SCHOOLS DIVISION OF SIQUIJOR

COPYRIGHT NOTICE

Section 9 of Presidential Decree No. 49 provides:

“No copyright shall subsist in any work of the Government of the Republic of the Philippines.
However, prior approval of the government agency of office wherein the work is created shall be
necessary for exploitation of such work for profit.”

This material has been developed through the initiative of the Curriculum Implementation Division (CID) of
the Department of Education – Siquijor Division.

It can be reproduced for educational purposes and the source must be clearly acknowledged. The material
may be modified for the purpose of translation into another language, but the original work must be acknowledged.
Derivatives of the work including the creation of an edited version, supplementary work or an enhancement of it are
permitted provided that the original work is acknowledged, and the copyright is attributed. No work may be derived
from this material for commercial purposes and profit.

Borrowed materials (i.e. songs, stories, poems, pictures, photos, brand names, trademarks, etc.) included
in this module are owned by their respective copyright holders. Every effort has been exerted to locate and seek
permission to use these materials from their respective copyright owners. The publisher and authors do not
represent nor claim ownership over them.

Published by the Department of Education


OIC-Schools Division Superintendent: Dr. Neri C. Ojastro
Assistant Schools Division Superintendent: Dr. Edmark Ian L. Cabio

Development Team of Learning Module

Writer: Cherry C. Kilat


Evaluators: Marilou C. Gulahab Mera M. Tuangco
Alma B. Panzo Alberta S. Bato

Management Team: D Dr. Marlou S. Maglinao o


CID - Chief

___________Neddy G. Arong g
Education Program Supervisor (MATHEMATICS)

E Edesa T. Calvadores s
Education Program Supervisor (LRMDS)

Printed in the Philippines


Department of Education – Region VII, Central Visayas, Division of Siquijor
Office Address: Larena, Siquijor
Telephone No.: (035) 377-2034-2038
E-mail Address: [email protected]

Page 2 of 17
11

Mathematics
Fourth Quarter
Module 6: Hypothesis Testing
(Population Mean)

Page 3 of 17
INTRODUCTION

This module is written in support of the K to 12 Basic Education


Program to ensure attainment of standards expected of you as a learner.

This aims to equip you with essential knowledge on Hypothesis


Testing about Population Mean.

This includes the following activities/tasks:

▪ Expected Learning Outcome — This lays out the learning outcome


that you are expected to have accomplished at the end of the module.
▪ Pre-test — This determines your prior learning on the particular
lesson you are about to take.
▪ Discussion of the Lesson —This provides you with the important
knowledge, principles and attitude that will help you meet the
expected learning outcome.
▪ Learning Activities — These provide you with the application of the
knowledge and principles you have gained from the lesson and enable
you to further enhance your skills as you carry out prescribed tasks.
▪ Post-test/Assessment — This evaluates your overall understanding
about the module.

With the different activities provided in this module, may you find this
material engaging and challenging as it develops your critical thinking skills.

Page 4 of 17
What I Need to Know

At the end of this lesson, you will be able to:

➢ identify the parameter to be tested given a real-life problem;


➢ draw conclusion about the population mean based on the test-
statistic value and the rejection region; and
➢ solve problems involving test hypothesis on the population mean.

What I Know
To find out what you already know about the topic to be discussed in
this module, take the pre-test.

Directions: Solve the following problems. Choose your answer from the given
choices inside the box. Write only the letter of the correct
answer on your answer sheet. (4pts each)

A B C D
Step 1: Step 1: Step 1: Step 1:
𝐻0 : 𝜇 = 24 𝐻0 : 𝜇 = 18.2
𝐻a : 𝜇 ≠ 24 𝐻0 : 𝜇 = 360 𝐻0 : 𝜇 = 32 𝐻a : 𝜇 < 18.2
𝐻a : 𝜇 ≠ 360 𝐻a : 𝜇 < 32
Step 2: Step 2:
𝛼 = 0.5 Step 2: 𝛼 = 0.5
one-tailed Step 2: one-tailed
𝑧 = ±1.96 𝛼 = 0.01 𝛼 = 0.01 𝑧 = −1.65
𝑑𝑓 = 24
Step 3: 𝑑𝑓 = 24 one-tailed Step 3:
𝑧 = −0.86 𝑡0.01,24 = −2.492 𝑧 = −6.39
two-tailed
Step 4: Step 3: Step 4:
𝑡0.01,24 = ±2.797 𝑡 = −8.33
Accept 𝐻0 Reject 𝐻0
Step 3:
Step 4:
𝑡 = −2.78
Reject 𝐻0
Step 4:
Accept𝐻0

1. A manufacturing firm has been averaging 18.2 orders per week for
several years. However, during the recession, orders appear to have
slowed down. Suppose the firm’s production manager randomly

Page 5 of 17
selects 32 weeks and finds a sample mean of 15.6 orders, write a
sample standard deviation of 2.3 orders. Test to determine whether
the average number of orders is down by using 𝛼 = 0.05.

2. The manager of the women’s dress department of a store wants to


know whether the true average number of women’s dresses sold per
day is 24. In a random sample of 36 days, it has been found out that
the average number of dresses sold is 23 with a standard deviation of
7 dresses. At the 0.05 level of significance, is there a sufficient
evidence to reject the null hypothesis that 𝜇 = 24?
3. Investigating a complaint from a buyer that there is short-weight
selling, a manufacturer takes a random sample of twenty-five 32 g
cans of coffee from a large shipment and finds that the mean weight is
31 g with a standard deviation of 0.6 g. Is there evidence of short-
weighing at the 0.01 level of significance?
4. The mean content of 25 bottles of brand S mango juice is 355 ml with
a standard deviation of 9 ml. Is this in line with the manufacturer’s
claim that the bottle contains, on the average, 360 ml? Use 0.01 level of
significance.

What's In
As what was discussed in the previous lesson, a null hypothesis
is a statement that there is no difference between a parameter and a
specific value; an alternative hypothesis is a statement that there
exists a difference between a parameter and a specific value; the level
of significance is the probability of committing Type I error; a Type I
error is committed when the null hypothesis is rejected when it is
true; and a Type II error is committed when the null hypothesis is
accepted when it is false. Also, the following steps in testing
hypothesis:
1. Formulate the null and alternative hypotheses on the
population mean.
2. Set the alpha value (level of significance) and identify the
rejection region.
3. Compute the test statistic.
4. Make the decision.

Page 6 of 17
What`s New

Previously you have dealt with the process of hypothesis testing


through a thorough discussion of the four-step procedure and some
related terminologies that helped you understand better the language
of hypothesis testing.
In this module, you will continue to deepen your understanding
of these test procedures as you focus on specific tests about the
population mean.

Testing Concerning the Population Mean

In the previous lesson you have learned how to compute the


confidence interval for a population mean focusing on three different
cases. Now you will develop hypothesis tests for the same cases. The
following table summarizes these cases along with the appropriate test
statistic for each case.

Case Description Test Statistic

A test concerning the mean of a normal


1 population with a known variance or 𝑧-test
standard deviation
A large-sample test concerning the mean of
2 a population (using the central limit 𝑧-test
theorem)
A small-sample test concerning the mean of
3 𝑡-test
a population with unknown variance

In all these three cases, the null hypothesis states that the population
mean 𝜇 is equal to a particular value.

Page 7 of 17
What Is It

CASE 1

TEST CONCERNING THE MEAN OF A NORMAL POPULATION


WITH KNOWN VARIANCE

Recall that when a random sample of size n is chosen from a normal


population, then the sample mean also follows a normal distribution with
𝜎
expectation 𝜇𝑥̅ = 𝜇 and standard deviation 𝑛, where 𝜎 is the population

𝑥̅ −𝜇
standard deviation. This leads to the z-statistic 𝑧 = 𝜎 which implies that
√𝑛
the z-distribution can be used when at test is conducted about the mean of
a normally distributed population and when you have an idea about the
value of the population standard deviation (or variance). This is called the
z-test.

To perform the z-test, you simply need to apply the formula, that is,
̅−𝝁
𝒙
𝒛= 𝝈 ,
√𝒏

where 𝑥̅ = sample mean, 𝜇 = mean in the null hypothesis, 𝜎 = standard


deviation, and 𝑛 = sample size. To illustrate how the z-test works in
hypothesis testing, study the following examples.

Example 1:

A recent survey says that Filipino children spend an average of 4


hours a day playing computer games with a standard deviation of 30
minutes. A random sample of 9 children is taken from a normally
distributed population of children who spend an average of 3.5 hours
playing computer games. Using the 1% level of significance, would you
conclude that the statement given in the survey is correct?

Solution: Follow the four-step hypothesis testing procedure. Since the


Population follows a normal distribution and the population
standard deviation is given, then the z-test is applicable.

Step 1: Formulate the null and alternative hypotheses on the


population mean.
𝐻0 : 𝜇0 = 4 hr
Ha: 𝜇0 ≠ 4 hr
Step 2: Set the alpha value (level of significance) and identify the
rejection region.

Page 8 of 17
𝛼 = 0.01

In order to identify the appropriate rejection region, first, you


need to divide the alpha level by 2 since the test is non-directional
𝛼 0.01
(two-tailed). Thus, 2 = 2 = 0.005 and the rejection region corresponds
to the probability of 0.005 on the right tail and another 0.005 on the left
tail. This means that the corresponding z-score has a probability of
0.495. from the normal distribution table, 𝑧 = ±2.575. This is called the
critical valueof the hypothesis test, and the rejection regions are 𝑧 ≥
2.575 and 𝑧 ≤ −2.575.

rejection region rejection region

−2.5752.575

Step 3: Compute the test statistic.


It is given that 𝑥̅ = 3.5, 𝜎 = 0.5, and 𝑛 = 9.
𝑥̅ − 𝜇
𝑧= 𝜎
√𝑛

3.5−4
𝑧 = 0.5 = −3
√9

Step 4: Make the decision.


If you plot −3 on the standard normal curve, you will find that it
is within the rejection region.

𝑧 = −3

−2.5752.575

Therefore, you reject 𝐻0 and conclude that based on the sample


selected, the statement given by the survey on the mean number of hours
Filipino children play computer games is incorrect.

Note: The decision in hypothesis testing is dependent on the p-value of the


computed test statistic compared with the alpha value. When the p-value
of the computed statistic is less than or equal to the alpha value, the

Page 9 of 17
null hypothesis is rejected. Otherwise, it will not be rejected. An
alternative to this method is the critical value approach, as in the example
above, in which the computed statistic is compared with the critical value of
the test statistic. When the absolute value of the computed statistic is
greater than the absolute critical value, the decision is to reject 𝑯𝟎 .

CASE 2

LARGE-SAMPLE TEST CONCERNING THE MEAN OF A POPULATION


(USING THE CENTRAL LIMIT THEOREM)

As stated in the central limit theorem, if the sample size is large


enough, i.e.,𝑛 ≥ 30, then the distribution of the sample means is
𝜎
approximately normal with mean 𝜇 and standard deviation 𝑛 regardless if

the population is normally distributed or not. Also, as the sample size gets
larger, the standard deviation s gets closer to the value of 𝜎. Thus, the z-test
can be performed in order to test hypotheses concerning the value of a
population mean. Consider the next example.

Example 2:

A workout program states that there is an average weight loss of


12pounds (lbs) for those who enrol in the program for two months. Another
workout program advertises greater weight loss and was tested with a group
of 30 volunteers who averaged 13 lb weight loss after two months, with
standard deviation 2.5 lb. Does the second workout program offer a higher
average weight loss effect? Test the hypothesis at 𝛼 = 0.05.

Solution: The z-test can be used since the situation complies with the
requirements of the central limit theorem.

Step 1: State the hypotheses.


𝐻0 : 𝜇0 ≤ 12 lb
𝐻𝑎 : 𝜇0 > 12 lb
Step 2: Set the alpha value (level of significance) and identify the
rejection region.

The alpha value is 0.05 and since the test is right tailed, the
rejection region includes the range of values such that
𝑃(𝑍 > 𝑧) = 0.05. By linear interpolation, this corresponds to a
critical value of z which is 1.645. Therefore, reject the null

Page 10 of 17
hypothesis when the computed value of z-statistic is greater
than 1.645, i.e., 𝑧𝑐 > 1.645.

Step 3: Compute the z-statistic. Since 𝑛 = 30, it can be assumed that


𝜎 = 𝑠 =2.5. Thus,
𝑥̅ − 𝜇
𝑧= 𝜎
√𝑛

13 − 12
𝑧= 2.5
√30

𝑧 ≈ 2.19
Step 4: Make the decision.

Since 𝑧computed > 𝑧critical, i.e., 2.19 > 1.645, then reject the null
hypothesis.

This means that, based on the selected sample, there is a significant


difference between the two workout programs and the second workout
program has a higher average weight loss effect.

CASE 3
A SMALL-SAMPLE TEST CONCERNING THE MEAN OF A POPULATION
WITH UNKNOWN VARIANCE

You have learned from the first two cases that the z-test is the
appropriate test procedure for the population mean when the variance is
known, or even when it is unknown provided that you are given a large
sample based on the central limit theorem. However, realistically speaking,
the population variance is usually unknown and there are only a few
observations, i.e., 𝑛 < 30. In this case, you should at least know the sample
variance or standard deviation, which can be computed easily from the
observed values, and use another test procedure called t-test.

The formula for the t-statistic is basically the same as the formula for
the z-statistic, the difference being only the replacement of the population
mean with the sample mean. Thus,

𝑥̅ − 𝜇
𝑡= 𝑠
√𝑛

where 𝑥̅ = sample mean, 𝜇 = population mean, 𝑠 = sample standard


deviation, and 𝑛 = sample size.

Page 11 of 17
Recall that the z-distribution table will not apply in this case. Using
the critical value approach, you need another distribution table that gives
the critical values of the t-statistic according to what is called degree of
freedom. The degree of freedom is simply a measure of how many values can
vary in a sample statistic. For the t-test, and in most other cases, the degree
of freedom is simply 1 less than the sample size. Thus, 𝑑𝑓 = 𝑛 − 1.

The table that gives the critical values of the t-statistic at specific
levels of significance is given below. Again, finding the critical value of t
using the table is easy as it just involves finding the intersection of the
degree of freedom and the 𝛼 value, as discussed in the previous lesson. For
example, for a one-tailed test at 𝛼 = 0.05 and sample size of 10, the critical
value of t denoted as 𝑡0.05,9 is 1.833 if the test is right-tailed, or −1.833 if the
test if left-tailed. When the test is non-directional or two-tailed, the critical
values will be 𝑡0.025,9 = ±2.262.

T-distribution Table

Page 12 of 17
To illustrate how to use the t-statistic in hypothesis testing, study the
following examples.
Example 3

It is assumed that the mean IQ is 𝜇 = 100. In a study conducted by


aresearcher, a sample of 𝑛 = 16 people had an average IQ of 90 with a
standard deviation of 15. Is the group significantly different from the regular
population? Use 𝛼 = 0.10.

Solution: The t-test applies since the sample deviation is given, and 𝑛 < 30.
Step 1: State the hypotheses.
𝐻0 : 𝜇 = 100
𝐻𝑎 : 𝜇 ≠ 100
Step 2: Set the alpha value (level of significance) and identify the
rejection region.

The test is two-tailed. Thus, using the table of critical values


(table is provided below), the critical value of t with 15
degrees of freedom is1.7530. this means that the null
hypothesis will be rejected when 𝑡 ≥ 1.7530 or
when 𝑡 ≤ −1.7530.

rejection region rejection region

𝑡 = −1.7530𝑡 = 1.7530

Step 3: Compute the test statistic.


𝑥̅ − 𝜇
𝑡= 𝑠
√𝑛
90−100
𝑡= 15 = −2.6667
√16

Step 4: Make the decision.

The computed value of t falls within the rejection region on the left tail
since the computed value of t is less than −1.7530. Therefore, reject
the null hypothesis and conclude that based on the sample selected,
the group is significantly different from the regular population.

Page 13 of 17
Example 4:

A researcher wants to determine if review sessions affect the


performance of students in exam. A review session is administered to a
sample of 25 students and after the examination, a sample mean of 43 is
calculated with a standard deviation of 8. From previous examinations, it
was identified that the population mean for the same exam is 40. Can the
professor conclude that the review session is effective in improving exam
performance? Use 𝛼 = 0.01.

Solution:

Step 1:State the hypotheses.


𝐻0 : 𝜇 = 40
𝐻𝑎 : 𝜇 > 40

Step 2: Set the alpha value (level of significance) and identify the
rejection region. The test is right-tailed with 𝛼 = 0.01 and the degree of
freedom is 25 − 1 = 24.Thus, the critical value of 𝑡0.01,24 = 2.492. This
means that you reject the null hypothesis when 𝑡computed ≥ 2.492.

Step 3: Compute the test statistic.


𝑥̅ − 𝜇
𝑡= 𝑠
√𝑛

43 − 40
𝑡= 8
√25
𝑡 = 1.875

Step 4: Make the decision.

The computed value of t is outside the rejection region.


Therefore, do not reject the null hypothesis since based on the sample
selected, there is not enough evidence to support the claim that the
review session significantly improves the performance of students in
the exam.

Page 14 of 17
What`s More

Directions: Determine the decision for each of the following given the
computed and critical value of the z or t. Write your answers in your activity
notebook.
1. 𝑧computed = 1.82 𝑧critical = 1.96
2. 𝑧computed = 2.54 𝑧critical = 2.33
3. 𝑡computed = 2.02 𝑡critical = 1.771
4. 𝑡computed = 2.24 𝑡critical = 2.552

What I Have Learned

I have learned that:

▪ the test statistic or the formula for computing the test value of the t-
test of one sample mean is
𝑥̅ − 𝜇
𝑡= 𝑠
√𝑛
where
𝑥̅ = mean of the sample
𝜇 = mean of the population
𝑛 = size of the sample
𝑠 = standard deviation of the population
𝑑𝑓 = 𝑛 − 1
▪ the test statistic or the formula to compute the test value of z-test of
one sample mean is
𝑥̅ − 𝜇
𝑧= 𝜎
√𝑛
where
𝑥̅ = mean of the sample
𝜇 = mean of the population
𝑛 = size of the sample
𝜎 = standard deviation of the population
▪ the z-test is generally used when the population standard deviation is
known or given. If the population standard deviation is unknown or
not given, the z-test can still be used provided that the sample size is
large (𝑛 ≥ 30).

Page 15 of 17
What I Can Do

Directions: Find the critical value, draw the rejection regions, compute the
value of the test statistic, and make a decision whether to accept or reject
the null hypothesis in each of the following situations. Write your answer in
your activity notebook.

Test
Hypotheses Given Rejection Region Decision
Value
1. 𝐻0 : 𝜇 = 9.8 𝑥̅ = 10.0
𝐻a : 𝜇 > 9.8 𝑠 = 4.3
𝑛 = 50
𝛼 = 0.05
2. 𝐻0 : 𝜇 = 80 𝑥̅ = 75
𝐻a : 𝜇 < 80 𝑠 2 = 19
𝑛 = 50
𝛼 = 0.01

Assessment

Directions: Solve the following problems. Specify the details in each step in
the solution process. (4pts each)

1. The proportion of students who passed an engineering examination


was 80%. Students complained that they would have done better if
they were allowed to use calculators. Later, a random sample of 90
students took this exam with calculators and 75 passed. Was this a
significant improvement at 0.05 level?
2. It is claimed that the average time spent by employees on telephone
calls is less than 6 minutes. In a study of time spent on the telephone
by its employees, a large office monitors a random sample of 27
employee calls and finds the mean length of these calls to be 5.8
minutes with a standard deviation of 1.4 minutes. Is the claim true at
0.05 level of significance?

Page 16 of 17
References:

Banigon, Ricardo Jr., et. al. Statistics & Probability for Senior High School.
Philippines: Educational Resources Corporation, 2016.

Canlapan, Raymond. DIWA Senior High School Series: Statistics and


Probability.
Makati City: DIWA Learning Systems Inc., 2016.

Ocampo, Jose Jr.,and WilmerMarquez. ConceptualMath & Beyond. Statistics


and Probability. Quezon City: Brilliant Creations Publishing Inc.,
2016.

Page 17 of 17

You might also like