Thanks to visit codestin.com
Credit goes to www.scribd.com

0% found this document useful (0 votes)
115 views35 pages

Allan Rey M. Paculanan: Lecturer

This document discusses hypothesis testing. It defines a hypothesis as a tentative generalization about the relationship between two or more variables. Hypotheses can be educated guesses and should be expressed declaratively. The process of hypothesis testing involves deciding whether to reject or fail to reject the null hypothesis based on statistical analysis. Some problems do not require hypotheses, such as those asking about descriptive statistics, while other problems indicating relationships or differences do require hypotheses. The document outlines the steps in hypothesis testing, including formulating the null and alternative hypotheses, choosing a statistical test, computing a test statistic, and defining a rejection region. It provides examples of null and alternative hypotheses and discusses types of errors in hypothesis testing.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
115 views35 pages

Allan Rey M. Paculanan: Lecturer

This document discusses hypothesis testing. It defines a hypothesis as a tentative generalization about the relationship between two or more variables. Hypotheses can be educated guesses and should be expressed declaratively. The process of hypothesis testing involves deciding whether to reject or fail to reject the null hypothesis based on statistical analysis. Some problems do not require hypotheses, such as those asking about descriptive statistics, while other problems indicating relationships or differences do require hypotheses. The document outlines the steps in hypothesis testing, including formulating the null and alternative hypotheses, choosing a statistical test, computing a test statistic, and defining a rejection region. It provides examples of null and alternative hypotheses and discusses types of errors in hypothesis testing.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 35

ALLAN REY M.

PACULANAN
Lecturer

12/11/20 [email protected]
HYPOTHESIS
TESTING
Hypothesis
 It is a tentative generalization
concerning the relationship between
two or more variables of critical
interest in the solution of a problem
under investigation Mouley, 1978).

12/11/20 [email protected]
HYPOTHESIS
TESTING
Educated or Intelligent Guess
 its formulation involves critical
thinking and decision on the basis of
well-thought –of objectives, research
design and review of related literature

A hypothesis should be expressed in a


declarative form (Kerlinger, 1986).
12/11/20 [email protected]
Hypothesis Testing
 A process that is undertaken by
researchers to decide whether a
stated null hypothesis is to be
rejected or accepted (failed to
reject Ho).

With this, a correct conclusion


can be drawn.
12/11/20 [email protected]
HYPOTHESIS-FREE PROBLEMS

 These are problems that do not


require a hypothesis .
e
 Problems asking about central
tendency or degree of variability
(descriptive objectives)

12/11/20 [email protected]
EXAMPLES
 What is the profile of the
 What is the perception of teachers in terms of age,
gender, tribe, religion,
Teacher Education
educational attainment
students towards the
and length of service?
proposed DepEd K + 12
program?
 What are the pressing
issues and concerns met by
 What is the performance of the Local Government
the Region XII secondary Units in implementing the
schools in the 2010 NAT? Solid Waste Management
program?

12/11/20 [email protected]
PROBLEMS THAT NEED
HYPOTHESIS

All problems indicating possible


relationship, difference
(comparison) and effect.

12/11/20 [email protected]
PROBLEMS • Is the respondents’ gender
significantly related to their
job performance?
• Is the voting preference of
Filipinos significantly • Is there a significant
affected by their religious difference between the use of
affiliation? Lecture method and
• Is the work performance Collaborative Learning
of faculty significantly approach?
related to their academic
• Is the school climate
rank and length of service?
significantly affects students
achievement in Mathematics
and Science?

12/11/20 [email protected]
TWO TYPES OF HYPOTHESIS

1. Null Hypothesis (Ho) – statements of no relationship, no effect or no difference (denial)


- expressed in negative form

2. Alternative Hypothesis (Ha) – a formal affirmative statement predicting a single research


outcome (opposite of Ho)
- A research or scientific hypothesis (Best and Khan, 1989)

12/11/20 [email protected]
EXAMPLESProblem: Is the respondents’
gender significantly related
Problem : Is the voting to their job performance?
preference of Filipinos
significantly affected by their Ho: The respondents’ gender is
religious affiliation? not significantly related to
Ho: The voting preference of Filipinos their job performance.
is not significantly affected by
their religious affiliation Ha: The respondents’ gender is
Ha: The voting preference of Filipinos significantly related to their
is significantly affected by their
job performance.
religious affiliation

12/11/20 [email protected]
EXAMPLES Problem: Is there a significant
difference between the use of
Problem: Is the work performance of Lecture method and
faculty significantly related to their
academic rank and length of service? Collaborative Learning
approach?
Ho: The work performance of faculty is
not influenced by their academic Ho: There is no significant difference
rank and length of service between the use of Lecture
method and Collaborative
Ha: The work performance of faculty is Learning approach.
influenced by their academic rank
and length of service
Ha: There is significant difference
between the use of Lecture
method and Collaborative
Learning approach.

12/11/20 [email protected]
Steps IN HYPOTHESIS TESTING
1. Formulate the null and its alternative
hypothesis.
Ho: There is no significant relationship between the educational
attainment and administrative performance of School
Principals.

Ha: There is significant relationship between the educational


attainment and administrative performance of School
Principals.

12/11/20 [email protected]
More Examples
Ho: The administrative performance of School Principals
is not dependent on their gender.

Ho: Parents’ income has no effect on the students’ level


of social interaction in school.

Ho: The religion is not related to the voting preference


of Filipinos.

12/11/20 [email protected]
2. Specify the level of significance
and sample size.

 α = 0.05 means that there are about 5


chances in 100 that we would reject the
null hypothesis (so with α = 0.01 and 0.10)

 β (= 1 – α) level of confidence

12/11/20 [email protected]
12/11/20 [email protected]
Type of Errors

 Type I
Reject Ho when it is TRUE.

 Type II
Accept Ho when it is FALSE.

12/11/20 [email protected]
Type of Errors (Analogy)

 Type I Error
Convict the suspect even when he is
INNOCENT.

 Type II Error
Acquit the suspect even if he is GUILTY.

12/11/20 [email protected]
12/11/20 [email protected]
Table 1.1 Consequences of
Decisions in Hypothesis Testing

12/11/20 [email protected]
More on α…

It is how willing the researchers are to be wrong when


they state that there is a relationship (in the case of
correlation research) or difference (in the case of a t-
test) between the two variables they measured.

12/11/20 [email protected]
Type 1 and Type 2 Error
Maria insists that she is 30 years old when in
fact she is 32 years old. What error is Mary
committing?
Soltuion
Mary is rejecting the truth, she is committing a
type I error

12/11/20 [email protected]
Stephen says that he is not bald. His hairline is
just receding. Is he committing an error? If so,
what type of error?

A man plans to go hunting the Philippine


monkey eating eagle believing that it is a proof
of his mettle. What type of error is this?

12/11/20 [email protected]
3. Choose an appropriate statistical test for
testing the null hypothesis.

 Based on the research design, level or distribution


of data
 Knowledge of statistics
 Availability of resources

12/11/20 [email protected]
Common Types of Test
 Parametric tests Z-test
- for independent and normal t-test
distribution
-- deals with interval/ratio data
ANOVA (F-
test)
 non-parametric tests
Chi-square
- distribution is not normal
Sign test (distribution-free)
McNemar test - uses ordinal/nominal data
Wilcoxon-
Signed
Kruskal-
12/11/20 [email protected]
Wallis
4. Compute the actual value of the test
statistic from the sample data.

12/11/20 [email protected]
5. Define a rejection region for the statistical
test or Establish the critical region or
tabular value for the selected test statistic
from the statistical table
2-tailed

Critical Value

Acceptance
Rejection Region Rejection
Region Region

α α
12/11/20 [email protected]
5. Define a rejection region for the statistical
test.

1-tailed

Rejection
Region
Acceptance Region

α α
12/11/20 [email protected]
12/11/20 [email protected]
• Words like greater, efficient, improves,
effective, increases and so on that suggest a
right-tailed direction in the formulation of the
alternative hypothesis.
• Words like decrease, less than ,smaller and
the like suggest a left-tailed direction.

12/11/20 [email protected]
6. Making decision, conclusion and
recommendation/s
a.Reject the null hypothesis if the
computed value is greater than or
equal to the tabular value.
b.Accept the null hypothesis if the
computed value is less than the
tabular value.

12/11/20 [email protected]
6. State your conclusion.
Ex:
Since the computed test statistic is greater
than the critical value, therefore the null
hypothesis is to be rejected.
or
Since the computed test statistic is less than the
critical value, therefore we failed to reject the
null hypothesis. (In other words, the null
hypothesis is accepted).

12/11/20 [email protected]
6. Make a decision.
Ex:
Therefore, the administrative performance of the School Principals is not
dependent on their gender.
or

Therefore, the parents’ income affects the students’ level of social


interaction in school.

12/11/20 [email protected]
Exercise 3-A: Identify which problem needs and does not require a HYPOTHESIS.
1. Is the number of drug-related arrest correlated to the frequency of information campaigns made?
2. What are the major issues and problems met in implementing the school MOOE?
3. What is the participation rate among the indigenous people in Region XII?
4. Is the implementation of the Greening Program in Sultan Kudarat affected by the political stability
in the locality?
5. What are the good practices of schools in South Cotabato on Brigada Skwela?
6. What is the perception of the policemen on MMDA proposal to issue firearms among the traffic
law enforcers?

12/11/20 [email protected]
Exercise B: State the null and alternative hypotheses for the ff. problems.
1. Is the city crime rate affected by migration?
2. Does the educational attainment of parents influence the child’s course
preference?
3. Is there a significant difference among the 3 feeding practices?
4. Is there a significant relationship between the dietary practices and child
performance in Mathematics?
5. Is the achievement in English dependent on the amount of homework?

12/11/20 [email protected]
Thank
you.
12/11/20 [email protected]

You might also like