Hypothesis Testing

HYPOTHESIS TESTING
Hypothesis
• A hypothesis is an educated guess about something and a

tentative solution to a research problem. It should be
testable, either by experiment or observation (Glen 2020).
For example, (a) a new medicine you think might work, and
(b) a way of teaching you think might be better.
• Hypothesis is a preconceived idea, assumed to be true,

and must be tested for its truth or falsity. To test the
hypothesis, inferential statistics are used.
• Hypothesis is used by the researchers to place a

temporary answer to their research questions aiming to fi nd
the diff erence between variables, a signifi cant relationship
between the variables, or interaction. Hypothesis has two
types namely: null hypothesis; and alternative hypothesis.
Types of Hypothesis
• Null hypothesis (Ho) is one that is always tested by the

researcher. It always indicates that there is no signifi cant
relationship or diff erence between the variables.
• Alternative hypothesis (Ha) indicates that there is a

true relationship or diff erence between the variables.
• Results will show that:
1. There is a meaningful relationship or diff erence

between two groups, thus reject the null hypothesis
2. The diff erence or relationship between the two groups

is not large enough to conclude that the groups are
diff erent or correlated, thus you fail to reject the null
hypothesis.
Types of Hypothesis
Hypothesis Testing
Hypothesis testing is a process in statistics by

testing an assumption regarding a population
parameter. It is the use of statistics to determine
the probability that a given hypothesis is true
(Majaski 2019). The goal of hypothesis testing is
whether to reject or accept the null hypothesis
that the researcher formulated in the study.
Inferential statistics requires that the sample be

drawn by random sampling because bias sampling
tends to give wrong inferences. Testing statistical
signifi cance is very important to determine if the
inference is valid.
Statistical Signifi cance
• Statistical Signifi cance refers to the

relationship of variables caused by something.
• Signifi cance means probably true (not due to

chance).
• Level of signifi cance means that there is a

chance that the fi nding is true.
• Statistical hypothesis testing is used to

determine whether the result of a data set is
statistically signifi cant.
Type I and Type II Errors
According to Prieto, Naval, and Carey (2017),

below are the types of errors that the
researcher could commit during hypothesis
testing.
• Type I error is committed when the researcher

rejected the null hypothesis when in fact it is
true.
• Type II error is committed when the data

produce a result that fails to reject the null
hypothesis when in fact the null hypothesis is
false and needs to be rejected.
Steps in hypothesis testing
In illustrating the steps of hypothesis

testing, we are going to use the study of
Ballera et al. (2019) entitled “Enhancing
learning competency in Practical Research
2 through learners’ module” as an example.
In this study, the researchers had two
comparing groups (control and
experimental), and each group consisted of
less than 30 participants.
1. State the hypothesis.
• Null hypothesis (H0)
There is no signifi cant diff erence between

the posttest of the control group and the
experimental group.
• Alternative hypothesis (Ha)
There is a signifi cant diff erence between the

post-test of the control group and the
experimental group.
2. Choose the statistical test to be used.
The researchers used a T-test for

independent samples to statistically
analyze their data. T-test for independent
samples is the appropriate statistical
method to apply in the study since it aimed
to determine the signifi cant diff erence
between the means of two independent
groups.
3. State the level of signifi cance for the

statistical test.
Alpha (∝) is a symbol used to denote

signifi cance level. The most frequently used
level of signifi cance is .05, .01, and .001.
The researchers used the 5% or 0.05 level of

signifi cance in their study. It means that they
are 95% confi dent that the result of the
study from the sample refl ects the total
population.
4. Do the computation using the chosen

statistical test.
There are a lot of statistical tools that the

researchers could use to save them from a
long and complicated computation for data
analysis. Some of these are SPSS
(Statistical Package for the Social
Sciences), Microsoft Excel, and some
available websites online that off er
computation for data analysis.
But if you wish to learn how to compute a t-test, then

you are referred to visit your Statistics and Probability
subject.
In our example, the researchers used SPSS in order to

compute the data they obtained from both groups of
their participants (posttest results).
5. Decide whether to reject or accept the null hypothesis.
For us to decide whether to reject the null hypothesis or not to

reject, we must understand fi rst the conditions set for our
chosen statistical method before making a decision.
Since the researcher used t-test for independent sample, the

condition set for this method is:
• Condition 1
If the computed p-value is less than the chosen level of

signifi cance, then reject the null hypothesis; or
• Condition 2
If the computed t-value is greater than the p-value, then reject

the null hypothesis.
In our example,
• Using the fi rst condition, the researchers computed p-

value of 0.001 is less than the level of signifi cance of
0.05, then the null hypothesis shall be rejected.
• Using the second condition, the researchers computed

t-value of 5.144 is greater than the p-value of 0.001,
then the null hypothesis shall be rejected.
Since the null hypothesis is rejected, then it means that

there is a signifi cant diff erence between the posttest of
both groups. It indicates that the learning module help
the students enhance their learning competency in
Practical Research 2.
Another example of hypothesis testing
Research Study:
The relationship of gender to the cookery performance

of Grade 12 Home Economics (HRS) students in Rizal
High School S.Y. 2019-2020
Step 1. State the Hypothesis
Ho: There is no signifi cant relationship between gender

and cookery performance of Grade 12 HRS students.
Step 4. Do the computation using the chosen statistical

test.
Using the chi-square computation, the researchers come

up with the following value:
• Degree of freedom: 2 (computed by subtracting 1 to

the number of response categories.)
• Critical Value: 5.991 (from chi-square table of values)
• P-value: 0.95
• Computed Chi-square value (t-value): 1.07

S t e p 5 . D e c i d e wh e t he r t o re j e ct o r a cce p t t h e nu l l h yp o t he s i s .
Conditions:
• Condition 1
I f t he c o m p u t e d p -v a l u e i s l e s s t h a n t h e cho s e n l e ve l o f s i g n i fi c a n c e ,
t he n re j e c t t h e nu l l h yp o t he s i s ; o r
• Condition 2
I f t he c o m p u t e d t -va l ue i s g re a t e r t ha n t he co m p u t e d cr i t i c a l v a l u e ,
t he n re j e c t t h e nu l l h yp o t he s i s .
D e ci s i o n:
• U s i n g C o nd i t i o n 1 , t h e p -va l ue o f 0 . 9 5 i s g re a t e r t ha n t he l e v e l o f
s i g ni fi c a nc e o f 0 . 0 5 , t he n t he n ul l h yp o t he s i s i s a cce p t e d .
• O r u s i ng C o n d i t i o n 2 , t he co m p u t e d t -va l ue o f 5 . 9 9 1 i s l e s s t h a n
t he c r i t i c a l v a l u e , t h e n t h e nu l l hy p o t he s i s i s a cce p t e d .
Activity
Directions: Accomplish the following activities in your

research ½ cross-wise.
A. Answer the following questions based on the lesson

today.
1. What is hypothesis testing?
2. Is hypothesis testing applicable to all kinds of

research? Briefl y explain your
answer.
3. Why do researchers need to test their research

hypothesis?
THANK YOU

Hypothesis Testing

Uploaded by

Copyright:

Available Formats

Hypothesis Testing

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Hypothesis Testing

Uploaded by

Copyright:

Available Formats

HYPOTHESIS TESTING

• A hypothesis is an educated guess about something and a

• Hypothesis is a preconceived idea, assumed to be true,

• Hypothesis is used by the researchers to place a

• Null hypothesis (Ho) is one that is always tested by the

• Alternative hypothesis (Ha) indicates that there is a

• Results will show that:

1. There is a meaningful relationship or diff erence

2. The diff erence or relationship between the two groups

Hypothesis testing is a process in statistics by

Inferential statistics requires that the sample be

• Statistical Signifi cance refers to the

• Signifi cance means probably true (not due to

• Level of signifi cance means that there is a

• Statistical hypothesis testing is used to

According to Prieto, Naval, and Carey (2017),

• Type I error is committed when the researcher

• Type II error is committed when the data

In illustrating the steps of hypothesis

1. State the hypothesis.

• Null hypothesis (H0)

There is no signifi cant diff erence between

• Alternative hypothesis (Ha)

There is a signifi cant diff erence between the

2. Choose the statistical test to be used.

The researchers used a T-test for

3. State the level of signifi cance for the

Alpha (∝) is a symbol used to denote

The researchers used the 5% or 0.05 level of

4. Do the computation using the chosen

There are a lot of statistical tools that the

But if you wish to learn how to compute a t-test, then

In our example, the researchers used SPSS in order to

5. Decide whether to reject or accept the null hypothesis.

For us to decide whether to reject the null hypothesis or not to

Since the researcher used t-test for independent sample, the

If the computed p-value is less than the chosen level of

If the computed t-value is greater than the p-value, then reject

• Using the fi rst condition, the researchers computed p-

• Using the second condition, the researchers computed

Since the null hypothesis is rejected, then it means that

Another example of hypothesis testing

The relationship of gender to the cookery performance

Step 1. State the Hypothesis

Ho: There is no signifi cant relationship between gender

Step 4. Do the computation using the chosen statistical

Using the chi-square computation, the researchers come

• Degree of freedom: 2 (computed by subtracting 1 to

• Critical Value: 5.991 (from chi-square table of values)

• Computed Chi-square value (t-value): 1.07

Directions: Accomplish the following activities in your

A. Answer the following questions based on the lesson

1. What is hypothesis testing?

2. Is hypothesis testing applicable to all kinds of

3. Why do researchers need to test their research

You might also like