Chapter 4

Hypothesis Testing
 Statistics

Descriptive Inferential
** Hypothesis
** Conclusion
 Inferential Statistics
(Hypothesis Testing)

Test
Objective Hypothesis Conclusion
Statistics
 Steps in hypothesis testing
1. Formulate the null and alternative hypothesis
2. Choose a significance level, α ( usually 0.05 or 0.01 )
3. Determine the appropriate test statistic(t, z, or chi sq.)
4. Requisite in making Decision/Conclusion:
**Compare the computed value and critical value
or compare p-value and α value
**Decision : (Reject Ho) or (Do not reject Ho)
5. State the conclusion
 Hypothesis
A statement of belief used in the evaluation of
population values.
 Hypothesis
Null and Alternative
Null Hypothesis (Ho)
 A claim that there is no significant difference ___
A claim that there is no significant relationship __

Alternative Hypothesis (Ha)

 A claim that there is a significant difference___
 A claim that there is a significant relationship __
 Null hypothesis
The hypothesis that is being subjected to statistical
test
Alternative hypothesis/ Research hypothesis
A claim that disagrees with the null hypothesis.

If the null hypothesis is rejected, we are left with no

choice but to fail to reject the alternative hypothesis.
 Objective Hypothesis
(Objective) : To determine if there is a significant
difference in the mean scores of students when they
are classified according to sex.

Ho : There is no significant difference in the mean

scores of students when they are classified according
to sex.
Ha : There is a significant difference in the mean
scores of students when they are classified according
to sex.
 Objective Hypothesis
(Objective): To determine if there is a significant
difference in the mean income of respondents when
they are grouped according to their educational
attainment.
Ho : There is no significant difference in the mean
income of respondents when they are grouped
according to their educational attainment.
Ha : There is a significant difference in the mean
income of the respondents when they are grouped
according to their educational attainment.
 Objective Hypothesis
Objective: To determine if there is a significant
relationship between the age of students and the
number of sticks of cigarettes they smoked.
Ho : There is no significant relationship between the
age of students and the number of sticks of cigarettes
they smoked.
Ha : There is a significant relationship between the
age of students and the number of sticks of cigarettes
they smoked.
 Objective Hypothesis
(Objective) : To determine if there is a significant
difference between the proportion of health care
providers who are smoking and the proportion of
those who are not smoking.
Ho : There is no significant difference between the
proportion of health care providers who are smoking
and the proportion of those who are not smoking.
Ha : There is a significant difference between the
proportion of health care providers who are smoking
and the proportion of those who are not smoking.
 Level of significance
The level of probability at which the null hypothesis
can be rejected.

The significance level α is also the magnitude of error

that one is willing to accept in making the decision to
reject the null hypothesis.
 Research Objectives and Test Statistic
1. To determine if there is a significant difference in the
smoking practices of male and female students.
2. To determine if there is a significant difference in the
smoking practices of students when they are classified
according to grade level.
3. To determine if the smoking practices of students is
associated to the smoking practices of their parents.
4. To determine if there is a significant correlation
between the age of students and the number of sticks
of cigarettes they smoke per day.
 Compare/Difference
1. To determine if there is a difference in
the smoking practices of male and 2. To determine if there is a significant
female students. difference in the smoking practices of
students when they are classified
according to grade level.

Independent Dependent Independent Dependent

Variable Variable Variable Variable

Sex Smoking Year level Smoking

Practices Practices

Male, Female number of Gr 10, number of

sticks Gr 11, Gr12 sticks

Qualitative Quantitative Qualitative Quantitative

Nominal/ Interval/ Nominal/ Interval/
Ordinal Ratio Ordinal Ratio
2 groups More than 2-
groups
T-Test, Z-Test ANOVA
(F-test)
 Relation/Association
3.To determine if the smoking practices of students is 4. To determine if there is a significant
associated to the smoking practices of their parents. correlation between the age of students and the
number of sticks of cigarettes they smoke per
day.

Independent Dependent Independent Dependent

Variable Variable Variable Variable
Smoking Smoking Age Smoking
Practices of Practices of Practices
Parents Students
Smoker, Smoker, Number of Number of sticks
Non-Smoker Non-Smoker years
Qualitative Qualitative Quantitative Quantitative
Nominal/Ordinal Nominal/Ordinal Interval/Ratio Interval/Ratio

Chi-Square Test “Correlation”

Pearson’s r
 Compare/Difference Relation/Association
IV DV IV DV IV DV IV DV
Sex Smoking Year Smoking SP SP Age Smoking
Practices level Practices Parents Students Practices

M,F # of Gr 10, # of Smoker Smoker, # of # of

sticks Gr 11, sticks Non-S Non-S years sticks
Gr12
Quali Quanti Quali Quanti Quali Quali Quanti Quanti
N/O I/R N/O I/R N/O N/O I/R I/R
2 More
groups than 2-
groups

T-Test, Z-Test ANOVA Chi-Square Correlation

(F-test) Test
 Test Statistic
Finding significant Finding significant
Difference Relationship
Between two proportions Between two variables
___Z- test

Between two Groups Nominal/Ordinal and Nominal/Ordinal

___T-test or Z-test ___Chi square test

Between more than two Groups Interval/Ratio and Interval/Ratio

___ANOVA __Correlation(Pearson’s r)
 Check your progress : Determine the test statistic
1. To determine if there is a significant difference in the mean
scores of students when they are classified according to sex.
2. To determine if there is a significant difference in the mean
incomes of the respondents when they are grouped according to
their educational attainment(Elem,HS,Col).
3. To determine if the opinion of students in online class is
significantly associated to their sex.
4.To determine if there is a significant relationship between the
age and monthly income of employees.
5. To determine if there is a significant difference between the
proportion of health care providers who are smoking and the
proportion of those who are not smoking.
 Making decision by comparing the
computed value and the critical value
Computed Greater Critical Reject Ho
/Test Statistic than Value
Value **There is a significant
difference/relationship

Computed Less Critical Do not reject Ho

Value than Value
There is no significant
difference/relationship
 ILLUSTRATIONS: Critical Value Approach
Test Statistic Value vs Critical value
If the absolute Computed value > the absolute critical
value , then reject Ho
If the absolute Computed value < the absolute critical
value , then do not reject Ho

reject Ho Do not reject Ho reject Ho

critical value critical value

 Example: To determine if there is a significant difference
in the mean scores of students when they are classified
according to sex.
Ho: There is no significant difference …
Ha: There is a significant difference…
Test statistic: t-test
Critical value = +3.4
Computed value = 5.78

reject Ho Do not reject Ho reject Ho

-3.4 3.4 5.78

Decision: Reject Ho
Conclusion: (Ha)There is a significant difference…
 Making decision by comparing the
p- value and the α- value
P - Value Less than α - Value Reject Ho
**There is a significant
relationship/difference

P - Value Greater than α - Value Do not reject Ho

There is no significant
relationship/difference
 ILLUSTRATIONS: p-value approach
If p- value is less than α , then reject Ho

If p-value is greater than α, then do not reject Ho

Reject Ho Do not reject Ho

0.00 α 1.00
 Example: To determine if there is a significant relationship
between the age of students and the number of sticks of
cigarettes they smoked.
Ho: There is no significant relationship …
Ha: There is a significant relationship …
Test statistic : Correlation/ Persons’ r
α – value = 0.05
p-value = 0.112

Reject Ho Do not reject Ho

0.00 0.05 0.112 1.00

Decision: Do not reject Ho

Conclusion: (Ho) There is no significant relationship …
 Type I and Type II Errors
Ho is true Ho is false

Reject Type I No error

Do not reject
( accept)
No error Type II
End of Chapter 4

Thank you!!!