Lesson 4:

HYPOTHESIS TESTING
At the end of the lesson, the students are expected to:
a. differentiate between Null and Alternative hypotheses;
b. illustrate the role of Significance value in testing hypothesis;
c. cite examples of Type I and Type II errors; and
d. test the hypotheses using p-value method.

The main purpose of statistics is

to test a hypothesis. For example, there is
a claim that emotional intelligence and
work attitudes are associated with each
other. So you conduct a research
focusing on the two variables to confirm
if the claim is correct.

Hypothesis testing then is a

fundamental tool in research that allows
researchers to determine whether their
hypothesis is supported or not by the
data they have collected. A hypothesis is
an educated guess or prediction about a
relationship between two or more
variables. The purpose of hypothesis testing is to determine the probability that the
observed data is consistent with the hypothesis.

Psychological Statistics 1
WHAT IS A HYPOTHESIS?

A hypothesis is an educated guess about something in the world around you. It

should be testable, either by experiment or observation. For example:

 A new medicine you think might work.

 A way of teaching you think might be better.
 A possible location of new species.
 A fairer way to administer standardized tests.

It can really be anything at all as long as you can put it to the test.

HYPOTHESIS TESTING

Hypothesis testing can be one of the most confusing aspects for students, mostly
because before you can even perform a test, you have to know what your null
hypothesis is. Often, those tricky word problems that you are faced with can be difficult
to decipher. But it’s easier than you think; all you need to do is:

1. Figure out your null hypothesis,

2. Set the criteria for a decision (level of significance for a test),
3. Choose what kind of test you need to perform,
4. Either support or reject the null hypothesis.

NULL HYPOTHESIS (H0)

The null hypothesis is the statement of no effect or no difference. It is usually the

starting point and is assumed to be true until there is sufficient evidence to reject it. For
example, if we want to study whether emotional intelligence is associated with work
attitudes, the null hypothesis would be that emotional intelligence is not correlated with
work attitudes. The null hypothesis, also known as the conjecture, assumes that any kind

Psychological Statistics 2
of relationship between the chosen characteristics that you see in a set of data is due to
chance.

ALTERNATIVE HYPOTHESIS (Ha)

The alternative hypothesis is the statement that contradicts the null hypothesis. It
is the hypothesis that we want to support by rejecting the null hypothesis. Continuing
with the emotional intelligence and work attitudes, the alternative hypothesis would be
that emotional intelligence is correlated with work attitudes. The alternative hypothesis
suggests that the assumption made in the null hypothesis is not true. In other words,
there is some non-random cause influencing the data.

There are two ways to contradict the null hypothesis. One is by applying the one-
tailed test which is basically opposing the null hypothesis with one-directional claim. For
a two-tailed test, the null hypothesis is opposed using a two-directional claim. This can
be clearly seen by the examples below.

ONE-TAILED TEST OF HYPOTHESIS

a. H0: μ=k versus Ha: μ>k
b. H0: μ=k versus Ha: μ<k

We would use a single-tail hypothesis test when the direction of the results is
anticipated or we are only interested in one direction of the results.

For example, a single-tail hypothesis test may be used when evaluating whether
or not to adopt a new textbook. We would only decide to adopt the textbook if it
improved student achievement relative to the old textbook. Let’s take a look at the other
example below:

Example:

A principal claims that the average NAT score of graduating students was greater
than 95. State the alternative and the null hypotheses.

Ha : μ > 95
H0 : μ ≤ 95

Psychological Statistics 3
TWO-TAILED TEST OF HYPOTHESIS
a. H0: μ=k versus Ha: μ≠k

If you want to test whether BS-Accountancy students study 20 hours a week or

not, this time, we will use the two-tailed test of hypothesis; that is, the hypotheses would
be expressed in this way:

Ha : μ = 20
H0 : μ ≠ 20

Two-tailed test Left-tailed test Right-tailed test

Signs in the H0 H0: µ = k H0: µ = k or H0: µ ≥ k H0: µ = k or H0: µ ≤ k
Signs in the Ha Ha: µ ≠ k Ha: µ < k Ha: µ > k
Rejection region In both tails In the left tail In the right tail

TERMINOLOGIES IN HYPOTHESIS TESTING

 Test Statistics in the quantity calculated from the sample data that is used a
decisive parameter in forming the final conclusion. There are different types of
test statistics such as z-test, t-test, and ANOVA. The type of test statistics to be
used shall depend on the assumed probability model and the hypothesis under
consideration.
 Significance Level is the degree of certainty required in order to reject the null
hypothesis in favor of the alternative hypothesis. A 0.05 level of significance
(p=0.05) means that you are willing to commit an error or mistake up to 5%.
 Critical Value is the value for a hypothesis test that is threshold to which the value
of the statistics in a sample is being compared to determine whether or not the
null hypothesis is rejected.
 Critical Region is also called the rejection region. It is the set of values of the test
statistics for which the null hypothesis is rejected.

TYPE I AND TYPE II ERRORS

Once the statistic is calculated, we must take a decision: accept H0 or reject H0.
When H0 is rejected, we face one of the two following situations:
 Null hypothesis is really false, and we rejected it: VERY GOOD DECISION
 Null hypothesis is really true, and we rejected it: TYPE I ERROR

If we accept H0, we face one of the two following situations:

 Null hypothesis is really false, and we accepted it: TYPE II ERROR

Psychological Statistics 4
  Null hypothesis is really true, and we rejected it: VERY GOOD DECISION
Example:
In a criminal trial, the defendant is either innocent or guilty, and the jury can find
him innocent or guilty. There are thus four possible outcomes: innocent and found
innocent; guilty and found guilty; innocent and found guilty; or guilty and found innocent.
The first two are correct results, and the last two are errors.

The next figure shows how these errors are committed.

Defendant is really Defendant is really

innocent guilty
Jury finds
Type I error Good decision
defendant guilty
Jury finds
Good decision Type II error
defendant innocent

Factors that Causes Type I and Type II errors

1. Significance level (alpha): The significance level is the probability of making a type
1 error. When the significance level is set too high, there is a greater chance of
rejecting a true null hypothesis, leading to a type 1 error.
2. Sample size: The size of the sample used in the study can affect the likelihood of
both type 1 and type 2 errors. If the sample size is too small, the study may not
have enough power to detect a true difference, leading to a type 2 error.
Conversely, if the sample size is too large, even a small difference may be
significant, leading to a type 1 error.
3. Effect size: The effect size is the magnitude of the difference between the null
hypothesis and the alternative hypothesis. A small effect size can make it more
difficult to detect a true difference, leading to a type 2 error.
4. Variability: The variability of the data can affect the likelihood of both type 1 and
type 2 errors. When the data are highly variable, it can be more difficult to detect
a true difference, leading to a type 2 error. Conversely, when the data are not very
variable, even a small difference may be significant, leading to a type 1 error.
5. Bias: Bias in the study design, data collection, or analysis can lead to errors in
hypothesis testing. For example, if the study design is biased in favor of one
group, it can lead to a type 1 error if the null hypothesis is rejected in favor of that
group.

HYPOTHESIS TESTING USING THE P-VALUE

The p-value is the lowest level of significance

at which the observed value of a test statistic is
significant (i.e., one rejects H0).

Alternative interpretation: The p-value is the

minimum probability of a type I error with which H0
can still be rejected.

Psychological Statistics 5
 We use p-values to make conclusions in significance testing. More specifically, we
compare the p-value to a significance level ( � ) to make conclusions about our
hypotheses.

If the p-value is less than or equal to the alpha level, we reject the null hypothesis
in favor of the alternative hypothesis.

If the p-value is greater than the alpha level, then we fail to reject the null

p-value > � ⇒ accept H0 ⇒ reject Ha (No significant result)

p-value ≤ � ⇒ reject H0 ⇒ accept Ha (With significant result)

hypothesis. To summarize:

Example, suppose that, for a given hypothesis test, the p-value is 0.09. Can H0 be
rejected? It depends! At a significance level of 0.05, we cannot reject H0 because p =
0.09 > 0.05. However, for significance levels greater or equal to 0.09, we can reject H0.

In finding for the p-value, we need to consider z-score (also called the standard
score) expressed as follows:
�−�
z= �
�

where:
z = standard score
� = sample mean
� = population mean
� = standard deviation
n = sample size

Example 1:

The average weight of freshmen college students is 50 kg. A nutritionist believes

the true mean to be different. She measured the weight of 50 freshmen college students
and found the mean to be 48 kg with a standard deviation of 5.2.

a. State the null and alternative hypotheses.

b. At 95% confidence level, is there enough evidence to discard the null hypothesis?
Use p-value method.

Ha : � ≠ 50 n = 50 � = 5.2
H0 : � = 50 � = 48 � = 5% or 0.05

Compute for the standard score:

�−� 48−50
z= � = 5.2 = -2.72
� 50

Psychological Statistics 6
 Using the z table, we can tell that the z-score equal to -2.72 has an equivalent p-
value of 0.003.

Since the p-value is less than the alpha level (p-value < �), the null hypothesis is
rejected. That is, there is a statistical evidence to claim that the mean weight of college
freshmen students is not equal to 50 kg.

Example 2:
The average pregnancy age for a girl in the Philippines is 22. A researcher believes
the average age should be lower. A sample of 25 girls in NCR was taken as a sample in a
study and found to have an average of 21 with standard deviation of 6.
a. State the null and alternative hypotheses.
b. At a 5% significance level, is there enough evidence to support the idea that
the warranty should be revised?

Ha : � < 22 n = 25 �=6
H0 : � = 22 � = 21 � = 0.05

Compute for the standard score:

x-μ 21-22
z= σ = 6 = -0.83
n 25

Convert the z-value into p-value using the standard normal table. That is, the z-
value of -0.83 has a p-value of 0.20.

As observed, the p-value (0.20) is greater than the alpha level (p-value > �). Thus,
we accept the null hypothesis. This suggests that the average pregnancy age in the
Philippines is really equal to 22.

THE CRITICAL VALUE APPROACH TO HYPOTHESIS TESTING

The observed value of the statistic (sample observation) is compared to critical

value (population observation). These critical values are expressed as standard z- values.
The two figures below show the one-tailed test with rejection regions at the right
and at the left.

0.95 0.95
00
Rejection Rejection
region region
α=0.05 α=0.05

0.45
00 0.45
00

If the test is two-tailed; the rejection region is divided into two equal parts. A
rejection region of 0.025 below the critical value in the left tail and a cumulative area of
0.025 above the upper critical value of the right tail.
This can be seen through the illustration below.

Psychological Statistics 7
 2.5% 95% 2.5%

Rejection Region
Rejection Region

Nonrejection Region

Remember:
 If the computed z score is greater than the critical or tabular value (regardless of
sign), reject the null hypothesis, and accept the alternative hypothesis.
 If the computed z score is less than or equal to the critical or tabular value
(regardless of sign), reject the alternative hypothesis, and accept the null
hupothesis.

The Tabular Value of Z at Indicated Levels of Significance

0.005 0.01 0.05 0.10
One-tailed test ±2.58 ±2.33 ±1.645 ±1.28
Two-tailed test ±2.81 ±2.575 ±1.96 ±1.645

Example 3:
The average IQ score of a group of students is equal to 100. The researcher
believes that the IQ score is greater than 100. He takes a sample of 50 individuals from
the group and administers an IQ test. The sample mean is found to be 105, with a
standard deviation of 10. State the hypotheses. Is there a sufficient evidence to prove
that the average IQ score of a particular population is greater than 100?

Ha : � > 100 n = 50 � = 10
H0 : � = 100 � = 105 � = 0.05

Compute for the standard score:

x-μ 105-100
z= σ = 10 = 3.54
n 50

The given example is one-tailed, so we use ±1.645 as our critical value.

Since, the computer z value (3.54) is greater than the critical value, we reject H0 and
accept Ha. This implies that, the average IQ score of the group of students is greater
than 100.

Example 4:
It is known from the records of a ISU that the average score of takers across
different programs of College Admission Test (CAT) in SY 2022-2023 is 86.82. One
researcher believes that the mean score of freshmen BS-Accountancy students in CAT is
below the population mean. He randomly select 60 scores from BS-Psychology program
and found that the mean score is 83.27 with standard deviation of 7.87. At 99%

Psychological Statistics 8
confidence level, is there sufficient evidence to prove that the claim of the researcher is
true?

Ha : � < 86.82 n = 60 � = 7.87

H0 : � = 86.82 � = 83.27 � = 0.01

Compute for the standard score:

x-μ 83.27-86.82
z= σ = 7.87 = -3.49
n 60

Compare the computed z value and the critical value. We also use one-tailed test
since the data is one-directional.

Z value = -3.49
critical value = -2.33

Since, z value > critical value, we reject the null hypothesis and accept the
alternative hypothesis. This implies that there is an evidence to prove that the mean
score of freshmen BS-Accountancy students in CAT is below the population mean.

Psychological Statistics 9