IT2011

Hypothesis

• A hypothesis is a statement or claim regarding a characteristic of one or more

populations.
• It is a preconceived idea, assumed to be true but has to be tested for its truth or falsity.
Examples:
* The mean body temperature for patients admitted to elective surgery is not equal to
37.0℃.
* A consumer advocate would like to know if the mean lifetime of a bulb is less than 500
hours.
* A real estate broker believes that the mean price has increased since then because of
changes in interest rates, and other economic factors.

Hypothesis Testing

• Hypothesis testing is a procedure on sample evidence and probability used to test claims
regarding one or more populations’s characteristics.
Two (2) Types of Hypothesis
Null Hypothesis (𝐻0 ) is usually expressed in terms of equality or no difference. It suggests
that there is no significant difference in the quantitative characteristic of the population.
For example, “The mean weight of the STI students is not different from 70 kilograms.
The null hypothesis 𝐻0 would then be written as 𝐻0 : 𝜇 = 70.
It is important to recognize that we never accept the null hypothesis. We are merely
saying that the sample evidence is not strong enough to warrant rejection of the null
hypothesis.
Alternative Hypothesis (𝐻𝑎 ) is the hypothesis proposed to be accepted if the sample data
do not show evidence to prove the null hypothesis. It implies that there is a significant
difference in the quantitative characteristic of the population. For example, if the null
hypothesis 𝐻0 : 𝜇 = 70, then the alternative hypothesis would be written as:
𝐻𝑎 : 𝜇 ≠ 70 is ‘The mean weight of the STI students is different from 70 kilograms’; or
𝐻𝑎 : 𝜇 > 70 is ‘The mean weight of the STI students is greater than 70 kilograms’; or
𝐻𝑎 : 𝜇 < 70 is ‘The mean weight of the STI students is less than 70 kilograms’.

Formulating Hypothesis

Hypotheses can be written in two (2) forms. One is the statement form or textual method
of formulating the hypothesis. Another one is the mathematical form where the relationship is
expressed using equality and directional inequality, such as greater than (>), less than (<), or not
equal (≠).

05 Handout 1 *Property of STI

 [email protected] Page 1 of 5
 IT2011

In testing hypotheses, several cases will have to be considered. These are:

1. Hypotheses for single Population

2. Hypotheses for two (2) populations

3. Hypotheses for multiple populations

4. Hypotheses for the difference in frequencies

Examples:

1. Suppose a study is made to test a locally branded audio speaker’s performance in terms of its
loudness and clarity as measured in wattage unit compared to the international branded
speakers. One hundred fifty samples were selected and tested from both brands to evaluate
each brand’s average performance. Formulate the null and alternative hypotheses.

The null (𝐻0 ) and alternative (𝐻0 ) hypotheses may be stated as follows:

𝐻0 : There is no significant difference in the mean watts between the local and international
brands. (𝜇1 = 𝜇2 )

𝐻𝑎 : There is a significant difference in the mean watts between the local and international
brands. (𝜇1 ≠ 𝜇2 )

𝐻0 : There is no significant increase in the mean watts of the local from the international
brand. (𝜇1 ≤ 𝜇2 )

𝐻𝑎 : There is a significant increase in the mean watts between the local and the international
brand. (𝜇1 > 𝜇2 )

𝐻0 : There is no significant decrease in the mean watts of the local from the international
brand. (𝜇1 ≥ 𝜇2 )

𝐻𝑎 : There is a significant decrease in the mean watts between the local and the international
brand. (𝜇1 < 𝜇2 )

2. A study was conducted about the therapeutic claim of a whitening capsule. It was tested on
the average number of days it would make the skin whiter on three groups of people grouped
according to locations, say, Luzon, Visayas, and Mindanao. State the null and alternative
hypotheses.

The null (𝐻0 ) and alternative (𝐻0 ) hypotheses may be stated as follows:

𝐻0 : There is no significant difference in the mean number of days among three (3) users.
(𝐴𝑙𝑙 𝜇 ′ 𝑠 𝑎𝑟𝑒 𝑒𝑞𝑢𝑎𝑙)

𝐻𝑎 : There is a significant difference in the mean number of days among three (3) users.
(𝑁𝑜𝑡 𝑎𝑙𝑙 𝜇 ′ 𝑠 𝑎𝑟𝑒 𝑒𝑞𝑢𝑎𝑙)

05 Handout 1 *Property of STI

 [email protected] Page 2 of 5
 IT2011

Procedures for Testing Hypothesis

1. State the null and alternative hypothesis.

• In conducting a research study, if a hypothesis test is used to support a claim, the claim must be
stated to become the alternative hypothesis, so it cannot contain the condition of equality.
• There are two (2) types of alternative tests: one-tailed and two-tailed tests. If the alternative
hypothesis has a specified direction (the sign is either less than or greater than in its statement),
the test is one-tailed (left-tailed or right-tailed), otherwise two-tailed.

2. Set the level of significance or alpha level (𝜶).

• The level of significance is the probability of rejecting the null hypothesis when it is true. The
level of significance is also referred to as the level of risk. This may be a more appropriate term
because it is the risk you take of rejecting the null hypothesis when it is true. A decision must be
made to use the 0.05 level, 0.01 level, 0.10 level, or any other level between 0 and 1.
Traditionally, the 0.05 level is selected for consumer research projects, 0.01 for quality
assurance, and 0.10 for political polling. If we reject the null hypothesis when it is true, we
commit a Type I error.
The probability of committing a type I error is designated by 𝛼.
Type I error: Rejecting the null hypothesis when it is true.
𝑃(𝑇𝑦𝑝𝑒 𝐼 𝑒𝑟𝑟𝑜𝑟) = 𝛼
The probability of committing another type of error, called Type II error, is designated by 𝛽.
The type II error: Accepting the null hypothesis when it is false.

The following table summarizes the decisions a researcher could make and the possible
consequences.

𝐻0 is actually
Decision
TRUE FALSE
Type I Error
Reject 𝐻0 Correct
(False positive)
Type II Error
Retain 𝐻0 Correct
(False negative)

3. Determine the statistical test to be used.

• The statistical tests allow researchers to make inferences because they can show whether an
observed pattern is due to intervention or chance. There is a wide range of statistical tests. The
decision of which statistical test to use depends on the research design, the distribution of the
data, and the variable type. Generally, if the data is normally distributed, parametric tests
should be used. If the data is non-normal, non-parametric tests should be used. The table below
shows a list of just a few common statistical tests and their uses.

05 Handout 1 *Property of STI

 [email protected] Page 3 of 5
 IT2011

Type of Test Use

Correlational: These tests look for an association between variables.
Pearson Tests for the strength of the association between two continuous variables.
Correlation
Spearman Tests for the strength of the association between two ordinal variables (does not
Correlation rely on the assumption of normally distributed data)
Chi-Square Tests for the strength of the association between two categorical variables
Comparison of Means: These tests look for the difference between the means of variables
Paired t-Test Tests for the difference between two variables from the same population (e.g., a
pre- and posttest score)
Independent t- Tests for the difference between the same variable from different populations
Test (e.g., comparing boys to girls)
ANOVA Tests for the difference between group means after any other variance in the
outcome variable is accounted for (e.g., controlling for sex, income, or age)
Regression: These tests assess if the change in one variable predicts change in another variable
Simple Tests how the change in the predictor variable predicts the level of change in the
Regression outcome variable
Multiple Tests how changes in the combination of two or more predictor variables predict
Regression the level of change in the outcome variable

4. Calculate the test statistic or p-value.

• A p-value, or probability value, is a number describing how likely it is that your data would have
occurred under the null hypothesis of your statistical test.
• The p-value can be obtained by performing statistical analysis using statistical software such as
Excel, SPSS, R, Minitab, SAS, JASP, etc.

5. Make a statistical decision.

• Using the p-value approach

Decision rule: Reject the null hypothesis if the computed p-value is less than or equal to the set
significance level; otherwise, do not reject the null hypothesis.
Example:
If the level of significance 𝛼 = 0.05,
P-value Decision
0.01 Reject 𝐻0
0.05 Reject 𝐻0
0.10 Failed to reject 𝐻0
• Using the Traditional method
Decision rule: Reject the null hypothesis if the test statistic’s computed value falls in the region
of rejection.

05 Handout 1 *Property of STI

 [email protected] Page 4 of 5
 IT2011

Definitions:
• Rejection region or Critical
region is the set of all values of
the test statistic which lead to the
rejection of 𝐻0 .
• Acceptance region is a set of all
values of the test statistic that
leads the researcher to retain 𝐻0 .

6. Draw a conclusion.

• The final step in hypothesis testing is deciding to reject or not to reject the null
hypothesis.
• Record conclusions and recommendations in a report and associate interpretations to
justify your conclusion and recommendations.

References:
Bevans, R. (2020). Hypothesis testing. Retrieved from: https://cyfar.org/types-statistical-tests

Sullivan, M. (2017). Informed decision using data: Fifth edition: Pearson Education

Punzalan, J. (2018). Statistics and probability. Malaysia: Oxford Publishing.

05 Handout 1 *Property of STI

 [email protected] Page 5 of 5