Rejection Region

Test Statistics
for Population
Mean
 The learner demonstrates
understanding of key concepts of CONTENT STANDARD
tests of hypotheses on the
population mean and population
proportion.

The learner is able to perform

appropriate tests of hypotheses
PERFORMANCE STANDARD involving the population
mean and population proportion
to make inferences in real-life
problems in different disciplines.
 MOST ESSENTIAL LEARNING COMPETENCIES

01 M11/12SP-IVc-1 M11/12SP-IVd-2 03
The learner identifies the The learner draws
appropriate rejection region The learner computes conclusion about
for a given level of for the test statistic the population mean
significance when value (population based on the test
mean). statistic value and
a. the population variance the rejection region.
is assumed to be known M11/12SP-IVd-1
b. the population variance is 02
assumed to be unknown
c. the central limit theorem is
to be used.
ACTIVITY
True or False
01
Alternative
hypothesis states
that there is no FALSE
difference between
a parameter and a
specific value.
02
Right directional test is
used when the alternative
hypothesis uses
comparatives such as TRUE
greater than, higher than,
better than, superior to
and exceeds.
03
If the null
hypothesis is true
and we rejected it, TRUE
then we commit a
Type I error.
04
A t-test is used when
the population variance
or standard deviation TRUE
are not known, and the
sample size is less
than 30.
05
The critical value is a
point on the test
distribution that is
compared to the test FALSE
statistic to determine if
the alternative hypothesis
would be rejected.
 It is the area in the sampling distribution of the test statistic
which is usually located on the extreme tail(s) of the
Rejection distribution where rare observations are expected to occur.
region
The rejection region has an area equivalent to α, which is
called the level of significance.
IDENTIFYING Population Variance Is
Known
THE
REJECTION Population Variance Is
REGION Unknown
 Population
Variance Is - 1. 28

Known
GIVEN:
one-tailed test
𝛼 = 0.10 + 1. 28

TABLE NEXT
 Previous slide

Table for z-critical value

Level of Significance
Type of Test
𝜶 = 𝟏% 𝜶 = 𝟐. 𝟓% 𝜶 = 𝟓% 𝜶 = 𝟏𝟎%

one-tailed test 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓 𝒄 = ±𝟏. 𝟐𝟖

two-tailed test 𝒄 = ±𝟐. 𝟓𝟕𝟓 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓
 Population
Variance Is
Known - 1. 645 + 1.645

GIVEN: If the absolute value of the calculated statistics has a value equal to
or greater than the critical value, then the null hypothesis 𝐻𝑜 should
two-tailed test be rejected and the alternative hypothesis 𝐻𝑎 is assumed to be
𝛼 = 0.10 supported.

TABLE NEXT
 Previous slide

Table for z-critical value

Level of Significance
Type of Test
𝜶 = 𝟏% 𝜶 = 𝟐. 𝟓% 𝜶 = 𝟓% 𝜶 = 𝟏𝟎%

one-tailed test 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓 𝒄 = ±𝟏. 𝟐𝟖

two-tailed test 𝒄 = ±𝟐. 𝟓𝟕𝟓 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓
 Population
Variance Is
unKnown t = -1.325

GIVEN:
one-tailed test
𝛼 = 0.10 , df = 20
t = 1.325

TABLE NEXT
Previous slide
 Population
Variance Is
unKnown
t =- 1.725 t = + 1.725
GIVEN:
two-tailed test If the absolute value of the calculated statistics has a value equal to
𝛼 = 0.10 , df = 20 or greater than the critical value, then the null hypothesis 𝐻𝑜 should
be rejected and the alternative hypothesis 𝐻𝑎 is assumed to be
𝛼 0.10 supported.
= = 0.05
2 2

TABLE NEXT
Previous slide
 01
A left-tailed test only has

Hypothesis a rejection region tail on

the left side of the graph.

Test and
Their Tails
 02
A right-tailed test only
has a rejection region tail
Hypothesis on the right side of the
graph.

Test and
Their Tails
Hypothesis
03
A two-tailed test has
rejection region tails on
both ends of the graph.

Test and
Their Tails
 z - test

TEST If the sample size is large,

where 𝑛 ≥ 30 and the population
standard deviation (𝜎) is known
STATISTICS
FOR
t - test
POPULATION It is used when 𝑛 < 30, the
MEAN population is normal or nearly
normal, and sample standard
deviation (𝑠) is known.
 In finding z-value, use the formula
below:
where:
𝑥ҧ − 𝜇
Z -test
𝑥ҧ - sample mean
𝑧= 𝜎 μ- population mean
𝑛- sample size
𝑛 σ- population standard deviation
 In finding t-value, use the formula
below:
where:
𝑥ҧ − 𝜇
t -test
𝑥ҧ - sample mean
𝑡= 𝑠 μ- population mean
𝑛- sample size
𝑛 𝑠- sample standard deviation
 solutions:
Example 1 one-tailed (greater than (>))
σ is known and n ≥ 30 (z-test)
1.645

𝛼 = 0.05 𝑐𝑣 = 1.645
Consider the following
given information. Use
𝛼 = 0.05. Interpret the
𝑥ҧ − 𝜇 71.5 − 70 1.5
result. 𝑧= 𝜎 = = = 1.875
8 0.8
𝑛 100
Null Hypothesis: 𝐻𝑜: 𝜇 = 70
Alternative Hypothesis: 𝐻𝑎: 𝜇 > 70
critical z-value is 1.645
𝑥ҧ = 71.5
computed z-value is 1.875
𝜇 = 70 computed z-value > critical z-value
𝜎=8
Therefore, we reject the null hypothesis and support
𝑛 = 100 and accept the alternative hypothesis that the
population mean is greater than 70.
TABLE NEXT
 Previous slide

Table for z-critical value

Level of Significance
Type of Test
𝜶 = 𝟏% 𝜶 = 𝟐. 𝟓% 𝜶 = 𝟓% 𝜶 = 𝟏𝟎%

one-tailed test 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓 𝒄 = ±𝟏. 𝟐𝟖

two-tailed test 𝒄 = ±𝟐. 𝟓𝟕𝟓 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓
 solutions:
-2.718
Example 2 left-tailed (less than (<))
σ is unknown and n < 30 (t-test)
degrees of freedom (df)
Consider the following
𝑑𝑓 = 𝑛 − 1
given information. Use
𝑑𝑓 = 12 − 1
𝛼 = 0.01. Interpret the
𝑑𝑓 = 11 𝛼 = 0.01
result.
𝑐𝑣 = −2.718
Null Hypothesis: 𝐻𝑜: 𝜇 = 127 𝑥ҧ − 𝜇 124.5 − 127 −2.5
Alternative Hypothesis: 𝐻𝑎: 𝜇 < 127 𝑡= 𝑠 = = = −1.732
5 1.443
𝑛 12
𝑥ҧ = 124.5
𝜇 = 127 critical t-value is -2.718
(we failed to reject the null hypothesis)
computed t-value is -1.732
s=5
computed t-value < critical t-value
𝑛 = 12 Therefore, we conclude that the population mean is equal
to 127. In other words, though there is a numerical
difference of 2.5 in the mean values, this difference can be
TABLE attributed to chance. NEXT
Previous slide
Example 3 solutions:
Formulate the hypotheses:
The government claims Null Hypothesis: 𝐻𝑜: 𝜇 = 10 000
that P10,000 is the
monthly expenses of a Alternative Hypothesis: 𝐻𝑎: 𝜇 ≠ 10 000
Filipino family with four 𝑥ҧ = 10 900 𝜇 = 10 000 s = 1 250 𝑛 = 26
members. A sample of
two-tailed
26 families has mean
monthly expenses of σ is unknown and n < 30 (t-test)
P10,900 and a degrees of freedom (df)
standard deviation of
P1,250. Is there 𝑑𝑓 = 𝑛 − 1
𝑑𝑓 = 26 − 1 = 25 -2.060 2.060
enough evidence to 𝛼
reject the government’s = 2.5%
2
claim at 𝛼 = 5%? 𝑐𝑣 = ±2.060

TABLE NEXT
Previous slide
 solutions:
Example 3 -2.060 2.060
𝑥ҧ = 10 900 s = 1 250
The government claims 𝜇 = 10 000 𝑛 = 26
that P10,000 is the
monthly expenses of a
Filipino family with four 900 𝑐𝑣 = ±2.060
𝑥ҧ − 𝜇 10 900 − 10 000
members. A sample of 𝑡= 𝑠 = =
245.10
= 3.671
1250
26 families has mean 𝑛 26
monthly expenses of
P10,900 and a critical t-value is ±2.060
standard deviation of
computed t-value is 3.671
P1,250. Is there
computed t-value > critical t-value (reject the null hypothesis)
enough evidence to
Therefore, we can conclude that there is enough evidence
reject the government’s
to reject the claim of the government that P10,000 is the
claim at 𝛼 = 5%? monthly expenses of a Filipino family with four members.

NEXT
 solutions:
Example 4 Formulate the hypotheses
The production manager of a large
manufacturing company estimates that Null Hypothesis: 𝐻𝑜: 𝜇 = 22.8
the mean age of his workers is 22.8 Alternative Hypothesis: 𝐻𝑎: 𝜇 ≠ 22.8
years with a standard deviation of 4.6
years. The treasurer of the firm needs 𝑥ҧ = 26.2 𝜇 = 22.8 𝜎 = 4.6 𝑛 = 70
more accurate employee mean age two-tailed
figure in order to estimate the cost of an
annuity benefit program being σ is known and n > 30 (z-test)
considered for employees. The 𝛼 = 0.05
treasurer takes a random sample of 70 𝑐𝑣 = ±1.96
employees and finds that the mean age
of the sampled employees is 26.2 -1.96 1.96
years. At 0.05 level of significance, test
the hypothesis that the mean age of the
employees is not equal to 22.8 years.

TABLE NEXT
 Previous slide

Table for z-critical value

Level of Significance
Type of Test
𝜶 = 𝟏% 𝜶 = 𝟐. 𝟓% 𝜶 = 𝟓% 𝜶 = 𝟏𝟎%

one-tailed test 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓 𝒄 = ±𝟏. 𝟐𝟖

two-tailed test 𝒄 = ±𝟐. 𝟓𝟕𝟓 𝒄 = ±𝟐. 𝟑𝟐𝟔 𝒄 = ±𝟏. 𝟗𝟔𝟎 𝒄 = ±𝟏. 𝟔𝟒𝟓
 Example 4 solutions: -1.96 1.96
𝑥ҧ = 26.2 𝜇 = 22.8
The production manager of a large
manufacturing company estimates that 𝜎 = 4.6 𝑛 = 70
the mean age of his workers is 22.8
years with a standard deviation of 4.6 𝑐𝑣 = ±1.96
years. The treasurer of the firm needs
more accurate employee mean age 𝑥ҧ − 𝜇 26.2 − 22.8 3.4
figure in order to estimate the cost of an 𝑧= 𝜎 = = = 6.184
4.6 0.5498
annuity benefit program being 𝑛 70
considered for employees. The
treasurer takes a random sample of 70 critical z-value is ±1.96
employees and finds that the mean age computed z-value is 6.184
of the sampled employees is 26.2 (reject
computed z-value > critical z-value
years. At 0.05 level of significance, test the null hypothesis)
the hypothesis that the mean age of the Therefore, we can conclude that the mean age of the employees is
not equal to 22.8 years. The difference between the sample mean
employees is not equal to 22.8 years. age and population mean age is too large to attribute it to chance or
we can say that their difference is significant.
NEXT
Thank
you!