Statisticsprobability11 q4 Week2 v4
Statisticsprobability11 q4 Week2 v4
PROBABILITY 11
4th Quarter
Week 2
Telefax:
Email Address:
Competencies:
1. Formulates the appropriate null and alternative hypotheses on a
population mean M11/12SP-IVb-1
2. Identifies the appropriate form of the test statistic when
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. M11/12SP-IVb-2
Learner’s Tasks
Lesson Overview
In the previous week, you learned that hypothesis testing is a process of evaluating
claims about a population based on the characteristic of a sample from that
population. It is a procedure used by statisticians whether or not to reject the null
hypothesis.
You also learned that hypothesis testing follows the following steps:
1. Formulate the null and alternative hypotheses.
2. Select the level of significance and the test type.
3. Determine test statistic to be used.
4. Compute the test statistic and critical values.
5. Construct rejection regions.
6. Make a decision/draw a conclusion based on steps 4 and 5.
7. Interpret results.
In this lesson, you will focus on the first four steps in hypothesis testing, that is,
formulating the null and alternative hypotheses, selecting the level of significance and
the test type, determining test statistic to be used and lastly, computing the
appropriate test statistic.
During the previous week, you learned about formulating the null and
alternative hypothesis and thus, you will just have to master it this time. The second
step is usually a given value in the problem. The type of test will depend on your
alternative hypothesis as discussed in the previous week. The appropriate test statistic
will depend whether the population variance is (a) known, (b) unknown, or (c) the
Central Limit is used. This will be discussed thoroughly in this lesson.
Now, let us start by reviewing some of the concepts discussed in the previous week
which will also be an important part of this lesson.
1
Definition of Null hypothesis
The appropriate test statistic for testing a claim about a population mean when
the population variance is known and n ≥ 30 is given by:
(𝐱̅ − μ)
z= σ
√𝑛
Example 1. The leader of the association of jeepney drivers claims that the average
daily take home pay of all jeepney drivers is Php400.00. A random sample of 100
jeepney drivers was interviewed and the average daily take home pay of these drivers
is found to be Php 425.00. Use a 0.05 significance level to find out if the average daily
take home pay of all drivers is different from Php400.00. Assume that the population
variance is Php8,464.00.
Solution:
Step 1 : Formulate the null and alternative hypotheses.
𝐻0: The average daily take home pay of all drivers is Php400.00.
𝐻1: The average daily take home pay of all drivers is different from
Php400.00.
In symbols:
𝐻0: 𝜇 = 400
𝐻1: 𝜇 ≠ 400
2
Step 3: Determine test statistic to be used.
Since the population variance is known and n > 30,
(𝐱̅ − μ)
z= σ will be used.
√𝑛
The standard deviation σ is the square root of the variance σ 2 . Thus, σ = 92.
(𝐱̅ − μ)
z= σ
√𝑛
(𝟒𝟐𝟓 − 400)
z= 92
√100
25
z = 9.2
z = 2.72
Therefore, the computed test statistic is z = 2.72. This value will be used in deciding
whether or not to reject the null hypothesis. This will be discussed further in the next
lesson.
Assuming the normality of the population, the appropriate test statistic for
testing a claim about a population mean when the population variance is unknown
and n < 30 is the t – test for a single mean.
(𝐱̅ − μ)
t= s
√𝑛
Example 2. It was announced by the Department of Trade and Industry that the
average price of a kilogram of beef is Php300.00. However, a sample of 20 randomly
collected data from different market shows that the average price per kilogram of
beef is Php310.00 and a standard deviation of Php15.25. Using 0.05 level of
significance, is there a sufficient evidence to conclude that the average price per
kilogram of beef is more than Php300.00?
Solution:
Step 1: Formulate the null and alternative hypotheses.
𝐻0: The average price of a kilogram of beef is Php300.00.
𝐻1: The average price of a kilogram of beef is more than Php300.00.
3
In symbols:
𝐻0: 𝜇 = 300
𝐻1: 𝜇 > 300
Since the population variance is unknown and n < 30, t – test for a single mean
will be used.
(𝐱̅ − μ)
t= s
√𝑛
(𝟑𝟏𝟎 − 300)
t= 15.25
√20
10
t=
3.41
t = 2.93
Therefore, the computed test statistic is t = 2.93. Again, this value will be used in
deciding whether or not to reject the null hypothesis. This will be discussed further in
the next lesson.
C. Hypothesis Testing about a Population Mean Using the Central Limit Theorem (CLT)
For a large population that is not normally distributed, the Central Limit Theorem
applies as long as the size of the samples is sufficiently large. In some cases, the
population is not normally distributed and the population standard deviation is
unknown. When this happens, the sample standard deviation is a good
approximation or substitute for the unknown population standard deviation. If the
sample size is equal to or greater than 30, it is considered sufficiently large. To find z,
use the formula:
(𝐱̅ − μ)
z= s
√𝑛
4
Example 3. The Department of Education claims that the average number of hours
each teacher works in one school year is 2,400 hours. A student who thinks that the
average number of working hours of each teacher is less than this, interviewed a
random sample of 55 teachers. The interview resulted to a sample mean of 2 375 hours
and standard deviation of 100 hours. Is there a sufficient evidence to conclude that
the number of hours each teacher works in one school year is less than 2400 hours?
Use 0.05 level of significance.
Solution:
Step 1: Formulate the null and alternative hypotheses.
𝐻0: The average number of hours each teacher works in one school year
is 2,400 hours.
𝐻1: The average number of hours each teacher works in one school year
is less than 2,400 hours.
In symbols,
𝐻0: 𝜇 = 2400
𝐻1: 𝜇 < 2400
Since the sample size n = 55 is greater than 30 and based on the Central Limit
Theorem, the sampling distribution of the mean is approximately normal. The sample
standard deviation s = 100 hours can be used in place of the population standard
deviation. Thus, the appropriate test statistic is the z test for a single mean.
(𝐱̅ − μ)
z= s
√𝑛
(𝟐𝟑𝟕𝟓 − 𝟐400)
z= 100
√55
− 25
z = 13.484
z = -1.854
Therefore, the computed test statistic is z = -1.854. Again, this value will be used in
deciding whether or not to reject the null hypothesis. This will be discussed further in
the next lesson.
5
Now, let us do the following activities. Use a separate sheet of paper for your answer.
Activity 1. State the null and alternative hypotheses of the given scenario below.
a. It is claimed that the average weight of babies at birth is 3.4 kg. The average weight
of a random sample of 30 newly born babies was determined and was found out
to be 3.1 kg. Is there a reason to believe that the average weight of babies at birth
is not 3.4 kg? Assume that the population standard deviation is 1.1 kg. Use 0.05 level
of significance.
Activity 2. Using the situations above, identify and compute the appropriate test
statistic.
Formative Test
Let us see how far you have learned about our lesson. Consider the problem below
and answer the questions that follow. Write the letter corresponding to your answer in
a separate sheet of paper.
1. The principal in a certain school claims that the average grade in math of the
learners in their school for the second quarter is 82. A student researcher who wants
statistical evidence on this claim conducted her own survey. The survey resulted to
a sample average of 80. Using 0.05 significance level, can it be concluded that the
average math grade of learners for the second quarter is less than 82? State your
null and alternative hypotheses.
6
2. The Chief of Hospital claims that the mean number of patients’ admission in a day
is 10. As a researcher, you conducted a survey to 15 randomly selected hospitals
and found out that the average number of admission in a day is 15. Using 0.05 level
of significance, can you conclude that the mean admission of patients in a day is
not equal to 10? State your null and alternative hypotheses.
For items 3 - 5. Compute the appropriate test statistic for the given situation below.
3. According to a study done last year, the average daily expenses of single individual
is Php350.00. As a student researcher, you interviewed randomly selected 60 single
individuals and found out that their average daily expenses is Php380.00. Is there a
reason to believe that this has really increased? Use 0.05 level of significance and
assume that population standard deviation is Php77.00.
4. According to last years’ report, the average income of fish vendors is Php400.00. A
researcher interviewed 25 randomly selected fish vendors and determined that
their average income is Php390.00 and a standard deviation of 21.50. Using 0.01
level of significance, can it be concluded that the average income of fish vendors
in a day has decreased? Assume normality over the population.
5. A battery company claims that the average life of their product is 20,000
hours. You think that the average life is less than this so you randomly choose 64
batteries and found out that the average is 19, 969 hours and a standard deviation
of 95 hours. Use 0.05 level of significance to conclude that the average life of each
battery is less than 20,000 hours.
A. z = 2. 61 B. t = 2. 61 C. z = -2. 61 D. t = -2. 61
Answer Key
Activity 1.
In symbols,
𝐻0: 𝜇 = 3.4
𝐻1: 𝜇 ≠ 3.4
7
B. 𝐻0: The mean annual salary of call center representatives is
Php188,584.00.
𝐻1: The mean annual salary of call center representatives is
greater than Php188,584.00.
In symbols,
𝐻0: 𝜇 = Php188,584.00
𝐻1: 𝜇 > Php188,584.00
In symbols,
𝐻0: 𝜇 = 35
𝐻1: 𝜇 < 35
Activity 2
A. z = -1.49
B. z = 2.72
C. t = -1.5
Activity 3
Answers may vary.
(Possible answer) Yes, I will still follow the health protocol. Even if I do not
belong to the age bracket, it is not a guarantee that I will not be
infected with the virus.
References
Mercado, Jesus P., et.al. (2016). Next Century Mathematics, Statistics and Probability,
pp. 19 - 41, Quezon Avenue, Quezon City, Philippines. Phoenix Publishing House,
Inc.