Professional Documents
Culture Documents
the sample. The true value of the population parameter is specified in writing the null hypothesis.
Situation 1: An average construction worker hourly rate pay in the Philippines is Php 62.50 with a
standard deviation of Php 6.01. A random sample of 20 manufacturing workers were asked on their
hourly rate and found that they had an average of Php 50 hourly rate pay with a standard deviation of Php
5.00. Construct a 90% confidence interval for the difference between the average hourly rate for
construction workers and the average hourly rate for manufacturing workers.
Null Hypothesis: There is no significant difference between the average hourly rate for construction
workers and the average hourly rate for manufacturing workers.
Situation 2: A chemist invented an additive to increase the lifespan of rechargeable battery. The said
additive will extend on average the battery’s lifespan to 48 months.
2. At least 40% of private school students transferred to public school during the COVID 19
pandemic.
Solution: H o : μ=40
3. The mean weekly expenses of a family during the COVID 19 pandemic increased at most by 15%.
Solution: H o : μ=15
4. Thirty-five percent of senior high school students enrolled to a track/ strand because of peer
pressure.
Solution: H o : μ=35
5. During the COVID 19 pandemic, 8% of COVID 19 cases in the country were confirmed death
cases.
Solution: H o : μ=8
Below are the common phrases used in hypothesis testing that will guide you the correct symbol to be
used in formulating alternative hypothesis.
Situation 1: In 2015, it was recorded that around 34% of the population in 2015 were not married. A
researcher surveyed a random sample of 500 couples. He found that 18% of them were living together
but unmarried. Test at 5% significance level if the current percentage of unmarried couples is different
from 34%.
Alternative Hypothesis: The current percentage of unmarried couples is different from 34%.
2
Situation 2: A chemist invented an additive to increase the lifespan of rechargeable battery. The said
additive will extend on average the battery’s lifespan to 48 months.
Alternative Hypothesis: The average lifespan extension of rechargeable battery is not 48 months.
2. At least 40% of private school students transferred to public school during the COVID 19
pandemic.
Solution: H 1 : μ >40
3. The mean weekly expenses of a family during the COVID 19 pandemic increased at most by 15%.
Solution: H 1 : μ <15
4. Thirty-five percent of senior high school students enrolled to a track/ strand because of peer
pressure.
Solution: H 1 : μ ≠ 35
5. During the COVID 19 pandemic, 8% of COVID 19 cases in the country were confirmed death
cases.
Solution: H 1 : μ ≠ 8
Level of significance, or significance level, refers to a criterion of judgment upon which a decision is
made regarding the value stated in a null hypothesis. Its value is between 0 to 1 or between 0% to 100%,
denoted by the Greek letter alpha 𝜶, is a probability of rejecting a true null hypothesis. In public health
research, alpha is usually 0.01 or 1%. In social science, alpha 𝛼 is usually 0.05 or 5% and 0.10 or 10% in
other studies. This implies that there is 1%, 5%, or 10% probability of rejecting a true null hypothesis.
Further, it implies that the result has 99%, 95%, or 90% chance of being true, respectively.
Observation of hypothesis:
It was recorded that around 34% of the population in 2015 were not married – alternative hypothesis
Therefore:
α 5%
Level of significance (α ) = = = 0.025
2 2
3
2. A chemist invented an additive to increase the lifespan of rechargeable battery. The said additive
will extend on average the battery’s lifespan to 48 months. Test the hypothesis at 0.01 level of
significance that the average lifespan is higher than 48 months.
Observation of hypothesis:
The average lifespan extension of rechargeable battery is not 48 months. - Null Hypothesis
Therefore:
3. An average construction worker hourly rate pay in the Philippines is Php 62.50 with a standard
deviation of Php 6.01. A random sample of 20 manufacturing workers were asked on their hourly
rate and found out that they had an average of Php 50 hourly rate pay with a standard deviation of
Php 5.00. Construct a 90% confidence interval that the average hourly rate for construction
workers is higher than the average hourly rate for manufacturing workers.
Observation of hypothesis:
There is no significant difference between the average hourly rate for construction workers and the
average hourly rate for manufacturing workers. - Null Hypothesis
Therefore:
Critical values of the tests of hypotheses are the number or numbers that determine the rejection region.
Thus, critical region might be a single number or an interval.
For one-tailed test or directional test <, the critical region is at the left side of the acceptance region.
For one-tailed test or directional test >, the critical region is at the right side of the acceptance region.
For two-tailed test or non-directional test ≠, the critical region is at the left and right sides of the
acceptance region.
Example 1: Suppose that a normally distributed population. Construct the rejection region if 𝛼=0.05.
standard deviation (𝜎) 0.12 Notice that 𝐻1: 𝜇 > 10, this is one-tailed test / directional test.
sample size (𝑛) 10 t-Distribution Critical Value
Null hypothesis 𝐻0: 𝜇 = 10 Z α Z 0.10
= =Z 0.05 =1.645
Alternative hypothesis 𝐻1: 𝜇 > 10 2 2
Significant level 𝛼 0.05 σ 0.12
𝒄𝒓𝒊𝒕𝒊𝒄𝒂𝒍 𝒗𝒂𝒍𝒖𝒆 10.0624 μ x =μ=10 and σ x= = =0.379473319220 ...
√ n √ 10
5
Example 2: Suppose that a normally distributed population has a standard deviation𝜎=0.12. Given a
sample size 𝑛=10, 𝐻0: 𝜇=7 and 𝐻1: 𝜇≠7. Construct the rejection region if 𝛼=0.10.
Solution:
Zα Zα
Critical value = μ−( )(σ x ) and μ+( )(σ x )
2 2
σ 0.12
μ x =μ=7 and σ x= = =0.03794733192202 …
√ n √10
Notice that 𝐻1: 𝜇≠7, this is a two-tailed test. Using the t-Distribution Critical Value
Z α Z 0.10
= =Z 0.05 =1.645
2 2
Zα Zα
Critical value = μ−( )(σ x ) and μ+( )(σ x )
2 2
¿ 7−( 1.645 ) ( 0.38 ) and ¿ 7−( 1.645 ) ( 0.38 )
¿ 7−0.624 ¿ 7+0.624
¿ 6.9376 ¿ 7.0624
Type I error is committed when rejecting a true null hypothesis. The probability of committing it is
denoted by 𝜶 or the level of significance.
Type II error is committed when accepting a false null hypothesis. The probability of committing it
is denoted by 𝜷.
6
H 0 is true Type I error Correct error
Reality
H 0 is false Correct decision Type II error
Example 1: The mean number of years a teacher work before retiring is 30.
Type I error: We conclude that the mean number of years a teacher work before retiring is not 30
years, when it really is 30 years.
Type II error: We conclude that the mean number of years a teacher work before retiring is 30 years,
when in fact it really is not 30 years.
For example, a parameter can be used to describe the mean amount of loans that are awarded
to the students of NwSSU. Assuming that the population of the university is 8,000, the researcher can
start by calculating the financial aid of a few select samples of the population, or about 10 students. With
three samples of 10 students each, the researcher may obtain a mean of Php 2,000, Php 1,200, and Php
800. The researcher can use this sample mean to make an inference about the population parameter.
Parameters are difficult to obtain, but we use the corresponding statistic to estimate its value. A
statistic describes a sample of a population, while a parameter describes the entire population. Since it
will be impossible to catch and measure all the butterflies in the world, we can catch 100 butterflies and
measure their length. The mean length of the 100 butterflies is a statistic that we can use to make an
inference about the length of the entire butterfly population.
Typically, the value of a statistic can varies from one sample to another, while the parameter
remains fixed. For example, one sample of 100 butterflies may have an average length of 6.5 mm, while
another sample of 100 butterflies from another region may have an average length of 6.8 mm.
Also, a smaller sample of 50 butterflies may have an average length of 7.0 mm. The statistic
7
obtained from the sample of the population can then be used to estimate the parameter of the entire
population
Example 1:
A manufacturer of ethyl alcohol has developed a new packaging design. He claims that the new
packaging design has an average reduction of production expenses of Php 5.00 per bottle with a
standard deviation of Php 2.00. A manager of one of their satellite production branch claims that the 200
samples of this new packaging design has an average reduction of production expenses of Php 3.00.
Test the difference of the population and sample means at 0.05 level of significance.
Solution:
Given: sample size 𝑛 = 200
Parameter: population mean 𝜇0 = 5
population standard deviation 𝜎 = 2
Statistic: sample mean 𝑥̅ = 5
Example 2:
A manufacturer of face mask has developed a new face mask design. He claims that the new
design has an average profit increase of 10% with a standard deviation of 3%. Test the hypothesis that
the new face mask design average profit increase of is not 10% if a random sample of 50 face mask is
tested with an average profit increase of 4%. Use 10% level of significance.
Solution:
Given: sample size 𝑛 = 50
Parameter: population mean 𝜇0 =10
population standard deviation 𝜎 = 3
Statistic: sample mean 𝑥̅ = 4
The actual test begins by considering two hypotheses. They are called the null hypothesis and the
alternative hypothesis. Null hypothesis denoted by H 0, states that there is no difference, no changes,
nothing happened, no relationship between a parameter and a specific value, or the independent variable
has no effect on the dependent variable. It makes a statement about the population, not the sample.
Read and understand the problems below. Formulate the null and alternative hypotheses in words
and in symbol.
Example 1.
A manufacturer of face mask has developed a new face mask design. He claims that the new design
has an average profit increase of 10% with a standard deviation of 3%. Test the hypothesis that the new
face mask design average profit increase of is not 10% if a random sample of 50 face mask is tested with
an average profit increase of 4%. Use 10% level of significance.
Solution:
8
Statistic: sample mean x = 4 sample size 𝑛 = 50
H 0: In words: The average profit increase of the new face mask design is 10%.
In symbol: H 0: 𝜇 = 10%
H 1: In words: The average profit increase of the new face mask design is not 10%.
In symbol: H 1: 𝜇 ≠ 10%
Example 2.
A teacher conducted a study to know if blended learning affects the students’ performances. A class
of 30 students of Grade 11 was surveyed and found out that their mean score was 83 with a standard
deviation of 4. A study from other country revealed that 𝜇 = 80 with a standard deviation of 3. Test the
hypothesis at 0.10 level of significance.
Solution:
Given:
Parameter: population mean μ0 = 80, population standard deviation 𝜎 = 3
In symbol: H 0: 𝜇 = 80
H 1: In words: The mean score of students’ performances in blended learning is greater than 80
In symbol: H 1: 𝜇 > 80
(We used greater than because sample mean 83 is greater than population mean 80.)
Example 3.
In a study of television viewing, the mean number of television program they watched during daytime
was 7. A survey was conducted on the random sample of 25 households and found that the mean
number of television program they watched during daytime was 5 with a standard deviation of 1.5. Test
the hypothesis at 10% level of significance.
Solution:
Given:
Parameter: population mean μ0 = 7
H 0: In words: The mean number of television program they watched during daytime was 7.
In symbol, H 0: 𝜇 = 7
9
H 1: In words: The mean number of television program they watched during daytime was less
than 7.
In symbol, H 1: 𝜇 < 7
(We used less than because the sample mean 5 is less than the population mean 7.)
As mentioned in previous discussion, the hypothesis or claim about population mean or population
proportion could be tested using the five-step hypothesis testing procedure. This topic only includes the
discussion of two basic test of hypothesis about the population mean using only single sample. These
are; 1. z-test (σ : known, or n ≥ 30), 2. t-test (σ : unknown, and n ¿ 30) considering the three conditions:
In this condition, the z-score is used. The formula for z-score is below.
x−μ0
Test Statistic: z = ( )( √ n)
σ
Where:
z is the z-score, x is the sample mean, μ0 is the population mean, 𝜎 is the population standard
deviation, and n is the sample size.
Example.
Given: x=83 , μ0=80 , σ=3 , n=30
x−μ0
Test Statistic: z = ( )( √ n)
σ
= ( 83−80
3 )
( √ 30 )
= 5.48
The t-score will be used in this case. Another condition to observe when using t-score is when the
sample size n is less than 30, i.e., (𝑛 < 30) and the population is normally or approximately normally
distributed. The formula for t-score is given by the formula below.
x−μ0
Test Statistic: t = ( )( √ n)
s
Where:
t is the t-score, x is the sample mean, μ0 is the population mean, s is the sample standard
deviation, and n is the sample size.
Example.
Given: x=6 , μ0 =5 , s=2 , n=15
10
x−μ0
Test Statistic: t = ( )( √ n)
s
= ( 6−5
2 )
( √15 )
= 1.94
The Central Limit Theorem states that if a random samples of size n are drawn from a large or
infinite population with finite mean 𝜇 and variance σ 2, then the sampling distribution of the sample mean
is approximately normally distributed with mean μ x= 𝝁 and a standard deviation of σ x = σ √ n. Hence, 𝒁 =
x−μ0
( )¿
σ
In other words, the sampling distribution of the sample means approaches a normal distribution as
the sample size gets larger no matter what the shape of the population distribution. This fact holds
especially true for sample sizes over 30. All this is saying is that as you take more samples, especially
large ones, your graph of the sample means will look more like a normal distribution.
The average of your sample means will be the population mean. Compute the sum of all means
from all samples divided by the number of means added. The result is the actual population mean.
Similarly, the average of all of the standard deviations of all samples is the actual standard deviation for
your population.
Example1.
San Miguel Corporation gives a monthly benefit to their employees during the COVID19 pandemic.
They claimed that the average monthly benefit of their employees is at least 5, 000 pesos. A random
sample of 35 employees were taken as samples to verify the said claim and found that their average
monthly benefit is 6, 000 pesos with a standard deviation of 600.00 pesos. Is the company’s claim correct
at 0.05 level of significance? Assume that the population is approximately normally distributed.
= ( 6,000−5,000
101.42 )
( √35 )
11
= 58.83
Example 2.
GMA-ABS claimed that their employees had a mean monthly salary of 12,500 pesos. A reporter
wants to verify this claim by asking 30 employees. The result showed that these employees had an
average monthly salary of 10,000 pesos with a standard deviation of 2,000 pesos. Test the claim at 10%
level of significance assume that the population is approximately normally distributed.
= ( 10,000−12,000
365.15 )( √30 )
= -37.50
REFERENCES
Alferez, M.S. & Duro, M.A. (2006). MSA Statistics and Probability. MSA Publishing
House. Reprinted 2016.
Average Construction Worker Hourly Pay in Philippines. (2020). Retrieved May 27,
2020 from https://www.payscale.comresearch/Ph/Job=Construction_
Worker/Hourly_Rate
Basic Concepts and Methodology for the Health Sciences. Retrieved May 27, 2020
from https://www.pitt.edu/~super1/ResearchMethods/Arabic/Hypothesis
Testingpart1.pdf
Belecina, R. R.et.al. (2016). Statistics and Probability. First Edition. Rex Book Store,
Inc.
Minitab Express Support. (2019). Retrieved May 27, 2020 from https://support.
minitab.com/en-us/minitab-express/1/help-and-how-to/basic- statistics/
inference/supporting-topics/basics/what-is-a-critical-value/
12
Parreño, E. B. & Jimenez, R.O. (2014). Basic Statistics: A Worktext. Second Edition.
C & E Publishing, Inc.
Stephanie. (2020). Statistics How To. Retrieved May 27, 2020 from
https://www.statisticshowto.com/probability-and-statistics/hypothesis-testing/
Stephanie. (2020). Statistics How To. Retrieved May 27, 2020 from
https://www.statisticshowto.com/probability-and-statistics/normal-distribution/
central-limit-theorem-definition-examples
13