Hypothesis Testing

In statistics, a hypothesis is a statement that

something is true.

Example:
A medical researcher claims that the mean body
temperature of healthy adults is not equal to
98.6˚F.
 COMPONENTS of a FORMAL
Hypothesis Test
• Null Hypothesis (Ho) -a statement about the
value of a population parameter (such as the
mean μ) and it must contain the condition of
equality (that is, it must be written with a symbol
= , ≤ , or ≥ ).
• Alternative Hypothesis (Haor H1) the statement
that must be true if the null hypothesis is false.
For the mean, the alternative hypothesis will be
stated in only one of three possible forms: H1: μ ≠
some value, H1: μ < some value, or H1: μ > some
value.
 Example of Null and Alternative
hypothesis
If you were testing the effectiveness of a new
drug…
Null Hypothesis:
The drug has no effect on patient recovery.
Alternative Hypothesis:
The drug has a positive effect on patient
recovery.
 COMPONENTS of a FORMAL Hypothesis Test
• Directionality
Non-directional tests (two-tailed test)
Ha: μ ≠ μo (one sample)
μ1 ≠ μ2 (two sample)
Example keywords: the same, compare, change, difference, etc.
Directional tests (one-tailed test)
Ha: μ> (or <) μo (one sample)
μ1 > (or <) μ2 (two samples)
Example keywords: reduce, improve, delay, raise, higher, below,
lower, more than, greater than, etc.
Determine if two-tailed or
one-tailed...
Thesis Title:
Significant Relationship
of Self-esteem and Class
Engagement of Students
from Cavite City
 COMPONENTS of a FORMAL
Hypothesis Test
• Decision and Errors
Type I Error – The mistake of rejecting null
hypothesis when it is true. The probability of
rejecting the null hypothesis when it is true is
called significance level; that is, the
significance level is the probability of a type I
error. The symbol α (alpha) is used to represent
the significance level. Values of alpha commonly
used are 0.05 and 0.01.
 COMPONENTS of a FORMAL
Hypothesis Test
Type II Error – The mistake of accepting the null
hypothesis when it is false. The symbol β (beta)
is used to represent the probability of type II
error.
 COMPONENTS of a FORMAL Hypothesis Test
• Test Statistics
It is used in making the decision about the
rejection of the null hypothesis.
• Significance level (denoted by α)
Baseline of rejection probability; Probability that
the test statistic will fall in the critical region when the
null hypothesis is actually true. If the test statistic falls
in the critical region, we will reject the null
hypothesis, so α is the probability of making the
mistake of rejecting the null hypothesis when it is true.
 COMPONENTS of a FORMAL Hypothesis Test
• Critical region – The set of all values of the test
statistics that would cause us to reject the null
hypothesis.
• Critical values – The value or values that separate
the critical region from the values of the statistics
that would not lead to rejection of the null
hypothesis.

Critical Acceptance
region Critical
region region
 COMPONENTS of a FORMAL Hypothesis Test
• P-value (or probability value)
The probability of getting a value of the test
statistic that is at least as extreme as the one
representing the sample data, assuming that
the null hypothesis is true.
P-value with interpretation
Conclusions in Hypothesis Testing
Five-Step Procedure for Testing a
Hypothesis

1. State the null and alternative hypothesis

2. Select a level of significance
3. Identify the test statistics
4. Formulate a decision rule
5. Make a decision
Example:
After analyzing 106 body temperatures of a
healthy adult, a medical researcher makes a
claim that the mean body temperature is less
than 98.6ºF.
a) Express the claim in symbolic form.
μ < 98.6
b) Identify the null hypothesis
Ho: μ ≥ 98.6
c) Identify the alternative hypothesis
Ha: μ < 98.6
d) Identify the test as being two-tailed, left-
tailed or right tailed:
less than so left-tailed
e) Identify the type 1 error of this test
(rejection of a true null hypothesis)
f) Identify the type 2 error of this test
(failure to reject the false null hypothesis)
g) Assume that the conclusion is to reject the null
hypothesis. State the conclusion in technical terms.
(Since null hypothesis is rejected, we conclude
that there is sufficient evidence to support the
claim that the mean is less than 98.6.)
 Test of Means and Proportions
Tests of Means:
These are used to compare the means of two or
more groups to determine if they are statistically
different. Common tests include the t-test for two
groups and ANOVA or Analysis of Variance for
multiple groups.

Example: Testing whether there is a significant

difference in test scores between two different
teaching methods.
 Testing the Population Mean
Example 1 (One-tailed test)
Consider the following hypothesis test:

A sample of 40 provided a sample mean of 26.4. The

population standard deviation is 6.
a) Compute the value of the test statistics
b) What is the p-value? At α = .01, what is your conclusion?
c) What is the critical value? Using the critical value
approach, what is your conclusion?

CALCULATOR
Population Mean: Known Population Standard Deviation
Example 2. Young millennials, adults aged 18 to 34, are viewed
as the future of the restaurant industry. During 2011, this group
consumed a mean of 192 restaurant meals per person.(NPD
Group website, Nov. 7, 2012). Conduct a hypothesis test to
determine if the poor economy caused a change in the
frequency of consuming restaurant meals by young millennials
in 2012.
a) Formulate the hypothesis
b) Based on a sample, the mean number of restaurant meals
consumed in 2012 is 182. Assume the sample size is 150,
population standard deviation is 55, compute the test
statistic and p-value.
c) At 95% confidence level, write your conclusion.

CALCULATOR
Population Mean: Unknown Population Standard Deviation

Example 3. A business travel magazine wants to classify

transatlantic gateway airports according to the mean
rating for the population of business travelers. A rating
scale with a low score of 0 and a high score of 10 will be
used, and airports with a population mean rating greater
than 7 will be designated as superior service airport. The
magazine staff surveyed a sample of 60 business
travelers at each airport to obtain the rating data. The
sample for London’s Heathrow Airport provided a
sample mean of 7.25 and a sample standard deviation of
1.052. With a level of significance of a=0.05, do the data
indicate that Heathrow should be designated as a
superior service airport?

CALCULATOR
Inferences about the Difference Between two population
mean: two population standard deviation unknown

Example 4. Consider a new computer software package developed to

help systems analysts reduce the time required to design, develop,
and implement an information system. To evaluate the benefits of
the new software package, a random sample of 24 systems analysts is
selected. Each analyst is given specifications for a hypothetical
information system. Then, 12 of the analysts are instructed to
produce the information system using current technology. The other
12 analysts are trained in the use of the new software package and
then instructed to use it to produce the information system. The
researcher is looking for evidence to conclude that the mean project
completion time for system analyst using the the new software
package is less than the mean project completion time of the current
technology. Use 95% significance level.
Completion Time Data and Summary
Statistics for the Software Testing Study
Current Technology New Software The researcher is
300 274 looking for
280 220 evidence to
344 308 conclude that the
385 336 mean project
372 198 completion time for
360 300 system analyst
288 315 using the the new
321 258 software package is
376 318 less than the mean
290 310 project completion
301 332 time of the current
283 263 technology.
CALCULATOR
 Test of Means and Proportions
Tests of Proportions: These are used to
compare the proportions or percentages in
different groups. The chi-squared test is often
used for this purpose.

Example: Analyzing whether there is a

significant difference in the proportion of
people who prefer two different brands of
soda.
Chi-Square Tests for Independence
Chi-square tests are used to determine if there is a
significant association or independence between two
categorical variables.

Chi-square test for independence is commonly used in

contingency tables.

It helps answer questions like whether there is a

relationship between gender and voting preferences
or whether smoking habits are independent of
education level.
 Summary
Hypothesis testing is a powerful statistical tool
that involves formulating null and alternative
hypotheses, managing Type I and Type II errors,
conducting tests of means and proportions, and
using chi-square tests for independence. These
methods allow researchers to draw meaningful
conclusions from data and make informed
decisions based on statistical evidence.
 Deciding on Appropriate Statistical
Methods for Research
• What is the main research question?
This needs to be able to be defined with specific
variables in mind. Which variables (types of
measurement) will help answer the research
question?
• Which is the dependent (outcome or response)
variable and what type of variable is it?
• Which are the independent (explanatory)
variables, how many are there and what data
types are they?
• Are relationships or differences between means
of interest?
 Identifying the Dependent and
Independent Variable
In the thesis entitled
"Significant Relationship of Self-esteem and
Class Engagement of Students from Cavite City,
Philippines,"

Dependent variable is "Class Engagement"

Independent variable is "Self-esteem"
 "Significant Relationship of Self-esteem and
Class Engagement of Students from Cavite City,
Philippines"
 Parametric Test
The parametric tests assume that the data are on a
quantitative (numerical) scale, with a normal distribution
of the underlying population. The samples have the same
variance (homogeneity of variances). The samples are
randomly drawn from the population, and the
observations within a group are independent of each
other. The commonly used parametric tests are the
Student's t-test, analysis of variance (ANOVA) and
repeated measures ANOVA.
However, if the distribution of the sample is skewed
towards one side or the distribution is unknown due to
the small sample size, non-parametric statistical
techniques are used. Non-parametric tests are used to
analyse ordinal and categorical data.
 Non-parametric test
When the assumptions of normality are not
met, and the sample means are not normally,
distributed parametric tests can lead to
erroneous results. Non-parametric tests
(distribution-free test) are used in such situation
as they do not require the normality
assumption. Non-parametric tests may fail to
detect a significant difference when compared
with a parametric test. That is, they usually have
less power.
Analogue of Parametric and
Non-Parametric Tests
 Which Test Should I Use?
Common Single Comparison Test
Test of Association
One scale dependent and several
independent variables

Regression or ANOVA? Use regression if you have only

scale or binary independent variables. Categorical
variables can be recorded to dummy binary variables but
if there are a lot of categories, ANOVA is preferable.