Learning Guide Module

Subject Code Stat1 Introduction to Statistics

Module Code 29.0 The z-test for one proportion
Lesson Code 29.1 Introduction to the z-test for one proportion
Time Limit 30 mins.

TARGET
At the end of this lesson, the learner is expected to:
✓ Identify the formula for the z-test test for a proportion.
✓ Identify hypotheses that can be tested using the z-test for a proportion.
✓ Identify the conditions that should be satisfied first before using the z-test for a proportion.

HOOK
A survey about COVID-19 vaccination found that 20 out of 100 respondents do not want to
get themselves vaccinated with a COVID-19 vaccine. Is the population proportion of those
who are not willing to get vaccinated
with a COVID-19 vaccine really 20%?
A manufacturing engineer claims that
less than 3% of their output are defective.
It was later seen that 2.5% of a batch of
output are defective. Does this make the
engineer’s claim correct? A research on
a certain fertilizer claims that the
fertilizer they are developing accelerates
plant growth for over 90% of plants.
What evidence was needed to back up
their claim? Research problems like the
ones that were just mentioned involve a
test statistic that you would call a
proportion. In this lesson, you will learn
how we can use your knowledge about
sample proportions to conduct a test of
hypothesis.

IGNITE
The z-test for proportion is used to compare an observed proportion to a theoretical one. But
why is it called the z-test for a proportion? You will be answering this question indirectly by
replying to the following questions. Try your best to answer them before proceeding to the next section.
1. How does the sampling distribution of the sample proportion look like?
2. What is the mean of the sampling distribution of the sample proportion?
3. What is the standard deviation of the sampling distribution of the sample proportion?
Answers:
1. The sampling distribution of the sample proportion follows a normal distribution.
2. The mean of the sampling distribution of the sample proportion is equal to the population
proportion, p.
3. The standard deviation of the sampling distribution of the sample proportion is equal to √𝑝𝑞/𝑛.

Statistics 1 Page 1 of 4
 As you may recall, you have already learned the answers to these questions from SLG 19.2
(Title: Sampling Distribution of the Sample Proportion). Since the sampling distribution of sample
proportion is normal, the statistical analysis for one proportion is called the ‘z-test’ as a reference to the
z-scores of the standard normal distribution.

Theoretically speaking, we will use our knowledge about this sampling distribution to
determine our chances of making correct statistical inferences. Just like in the z-test for one mean, the
farther away our statistic is from the theoretical value, the less chances that we have in concluding that
the difference of the sample statistic and the theoretical value is due to sampling error.
Suppose in a test for the population proportion, the null hypothesis is given by 𝐻0 : 𝑝 = 𝑝𝑜 . Just
like in the previous test, we assume that the null hypothesis is true. That is, the mean of all the sample
proportions is assumed to be 𝑝𝑜 . Using a similar method done to determine the test statistic for the z-
test for one mean, the formula for the test statistic of the z-test for a proportion:

𝑝̂ − 𝑝𝑜
𝑧=
√𝑝𝑜 (1 − 𝑝𝑜 )/𝑛
Where:

𝑋
𝑝̂ = sample proportion =
𝑛
𝑝𝑜 = hypothesized proportion
𝑛 = sample size

Notice that the formula is a derivation of the standard score, z, in a normal distribution where
the mean is 𝑝𝑜 and the standard deviation is √𝑝𝑜 (1 − 𝑝𝑜 )/𝑛. The formula uses the z-score of the sample
proportion, 𝑝̂ , to compare its distance from the expected proportion, 𝑝𝑜 , if the population proportion is
indeed 𝑝𝑜 .

Statistics 1 Page 2 of 4
Just like the other tests, there are certain conditions that should be met first before we are able to perform
a z-test on a proportion.
1. The sample is a random sample.
2. The conditions for a binomial experiment are satisfied (see SLG 18.1).
3. 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5.
Whenever a z-test on a proportion is to be conducted, always make sure that all of these conditions
are satisfied before going on.

Example: Which of the following situations can allow us to use a z-test on a proportion?

a) Data suggests that at least 45% of senior high school athletes suffer some kind of injury
during their tenure as student athletes. The sample involves 54 respondents where 28 say
they have had injuries during their tenure.
b) Product X is 30% more effective than Product Y.
c) To test the claim that more than half of the scholars have a high level of perceived stress, a
survey was floated wherein 53 out of the 100 survey participants reported a high level of
perceived stress.
Solution: The z-test for a proportion is conducted when an observed proportion is compared against a
theoretical one.
a) A z-test could be used to test the claim that at least 40% suffer some kind of injury since
the observed proportion, 28/54 ≈ 52%, is to be compared against a theoretical one, which
is 45%. The statistical hypothesis is 𝑝 ≥ 0.40.
b) The word “more” suggests that the success rate (or proportion) of a certain Product X is to
be compared to another success rate of a certain Product Y. Therefore, a z-test for a
proportion cannot be used since two proportions are involved.
c) A z-test could be used to test the claim that more than half have a high level of perceived
stress since the observed proportion, 53/100 is compared against a theoretical one, which is
half. The statistical hypothesis is 𝑝 > 0.50.
NOTE: After confirming the correct statistical test to be conducted, make sure that the conditions
needed for the test should be satisfied first.

NAVIGATE
It is now your turn to apply the things we have discussed. Follow the indicated instructions
on each part. Some items are based on your textbook exercises (see references for the textbook titles).
Follow the instructions given by your teacher on the method of submissions of your answers. Treat
ODD numbers as practice (NOT GRADED) and EVEN numbered exercises as the assessment
(GRADED).
1. Enumerate the conditions that need to be satisfied before conducting a z-test on a proportion.
2. Which of the following situations can allow us to use a z-test on a proportion?
a. Angry clients claim that more than 10% of their parcels are not safely delivered or not
delivered at all. To test this claim, a statistician randomly selects 42 delivery orders and
found that 3 were not delivered satisfactorily.
b. A robotics company claims that their “robot basketball player” can make free throws with
90% accuracy. A test trial of 50 free throws resulted in 38 made shots.
c. A mathematics teacher wants to determine if the student’s attitudes towards a certain topic
is related to their percentage of correct answers in a given exam regarding that topic.

Statistics 1 Page 3 of 4
 KNOT
In summary, we have discussed in this module the following concepts involving the z-test on
one proportion:
𝑝̂−𝑝
1. The formula for the z-test on one proportion is 𝑧 = .
√𝑝𝑞/𝑛
2. The z-test for proportion is used to compare an observed proportion to a theoretical one.
3. Three conditions that should be satisfied first before proceeding with a z-test of proportions are as
follows: (a) The sample is a random sample; (b) The conditions for a binomial experiment are
satisfied; and (c) 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5.

References:
1. Bluman, A.G. (2014). Elementary Statistics: A step by step approach (9th Edition). Mc-Graw Hill
2. De Veaux, R.D., Velleman, P.F., & Bock, D.E. (2014). Intro stats (New International Edition).
Great Britain: Pearson Education Limited
3. De Veaux, R.D., Velleman, P.F., & Bock, D.E. (2012). Stats data and models (3rd Edition). United
States of America: Pearson Education, Inc.

Prepared by: Clifford Jed A. de Leon Reviewed by: Joseph Tabadero, Jr.
Position: SST - III Position: SST – IV
Campus: PSHS – CARC Campus: PSHS – CARC

ANSWERS TO NAVIGATE PART:

1. (a) The sample is a random sample; (b) The conditions for a binomial experiment are satistfied; and
(c) 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5.

© 2020 Philippine Science High School System. All rights reserved. This document may contain proprietary information and may only be
released to third parties with approval of management. Document is uncontrolled unless otherwise marked; uncontrolled documents
are not subject to update notification.

Statistics 1 Page 4 of 4