Testing of

Hypothesis
Presented by: Group 7
 What is Hypothesis

It's a statement that suggests a possible answer to your

research question. Hypotheses are important because they
help guide your research by providing a clear and testable
direction
What is Testing of Hypothesis

Testing a hypothesis in research is the process of

systematically investigating and gathering evidence to
determine whether your educated guess or prediction (the
hypothesis) is supported by the data you collect during
your research.
Points to be considered while formulating
Hypothesis
Hypothesis should be clear and precise.
Points to be considered while formulating
Hypothesis
Hypothesis should be clear and precise.

Hypothesis should be capable of being tested.

Points to be considered while formulating
Hypothesis
Hypothesis should be clear and precise.

Hypothesis should be capable of being tested.

Hypothesis should state relationship between

variables.
Points to be considered while formulating
Hypothesis
Hypothesis should be clear and precise.

Hypothesis should be capable of being tested.

Hypothesis should state relationship between

variables.

Hypothesis should be limited in scope and must be

specific.
Points to be considered while formulating
Hypothesis
Hypothesis should be stated as far as possible in
most simple terms so that the same is easily
understandable by all concerned.
Points to be considered while formulating
Hypothesis
Hypothesisshould
Hypothesis shouldbe
bestated
statedasasfar
faras
aspossible
possibleinin
mostsimple
most simpleterms
termssosothat
thatthe
thesame
sameisiseasily
easily
understandableby
understandable byall
allconcerned.
concerned.

Hypothesis
Hypothesisshould
shouldbe
beamenable
amenableto
totesting
testingwithin
withinaa
reasonable
reasonabletime.
time.
Points to be considered while formulating
Hypothesis
Hypothesisshould
Hypothesis shouldbe
bestated
statedasasfar
faras
aspossible
possibleinin
mostsimple
most simpleterms
termssosothat
thatthe
thesame
sameisiseasily
easily
understandableby
understandable byall
allconcerned.
concerned.

Hypothesis
Hypothesisshould
shouldbe
beamenable
amenableto
totesting
testingwithin
withinaa
reasonable
reasonabletime.
time.

Hypothesis must explain empirical reference.

 Independent Variable Dependent Variable

This is the variable that you, as the This is the variable that you measure or
researcher, change or manipulate in an observe to see how it responds to changes
experiment. It's what you think will have an in the independent variable. It's the
effect on the dependent variable. In simpler outcome or result you're interested in, and it
terms, it's the cause or factor you're testing. depends on what you do to the independent
variable. In simpler terms, it's the effect or
response you're studying.
Scenario: Investigating how the amount of water
affects plant growth.

Independent Variable: The amount of water given to the plants.

Dependent Variable: Plant growth (height or size).

 Types of Hypothesis

Research Hypothesis Statistical Hypothesis

 Types of Hypothesis

Research Hypothesis
A research hypothesis is a tentative solution for
the problem being investigated. In research, the
researcher determines whether or not their
supposition can be supported through scientific
investigation.

Example
Higher levels of physical exercise (independent variable) will result in lower
body mass index (BMI) scores (dependent variable) among adults
(negative relationship)
 Types of Hypothesis

Statistical Hypothesis
Statistical hypothesis is a statement about the
population which we want to verify on the basis of
sample taken from population. Statistical
hypothesis is stated in such a way that they may be
evaluated by appropriate statistical techniques

Example :
Increasing the amount of fertilizer (independent variable) will result in higher
crop yields (dependent variable) in the experimental field (positive
relationship)."
Types of Statistical Hypothesis

Null Hypothesis (H0)

A statistical hypothesis that states

that there is no difference between
a parameter and a specific value,
or that there is no difference
between two parameters

H0: parameter = value

Types of Statistical Hypothesis

Alternative Hypothesis
(H1 or Ha)

A statistical hypothesis that states

the existence of a difference
between a parameter and a
specific value, or states that there
is a difference between two
parameters. Alternative hypothesis
is created in a negative meaning of
the null hypothesis.
Types of Statistical Hypothesis
 Research Question: Does a new educational program improve
student test scores in mathematics?

Null Hypothesis (H0): Alternative Hypothesis (Ha):

The new educational The new educational

program has no significant program has a significant
effect on student test scores effect on student test scores
in mathematics. in mathematics.
BASIC CONCEPTS
CONCERNING TESTING
OF HYPOTHESIS
 Types of Error
In the context of testing of hypotheses, there are basically two
types of errors we can make

α β
Type 1 error Type II error
To reject the null hypothesis when it is true
is to make what is known as a type I error. If we do not reject the null hypothesis when in
The level at which a result is declared fact there is a difference between the groups,
significant is known as the type I error rate, we make what is known as a type II error. The
often denoted by α. type II error rate is often denoted as β.
EXAMPLE SCENARIO
You're responsible for airport security, and
you're using a metal detector to screen
Type 1 Error (False Positive):
passengers for prohibited items like weapons
This occurs when the metal detector falsely
or dangerous objects before they board a
alarms, and you detain a passenger, suspecting
flight.
they have prohibited items when they do not. It's
like accusing an innocent person of wrongdoing.

Null Hypothesis (H0): This represents the

default assumption that the passenger
Type 2 Error (False Negative):
doesn't have any prohibited items; they
This happens when the metal detector fails to
are innocent and pose no threat.
sound the alarm for a passenger who is carrying
prohibited items. It's like letting a guilty person
Alternative Hypothesis (Ha): This is the
pass through without detection.
opposite assumption, suggesting that the
passenger is carrying prohibited items
and poses a security risk.
In a tabular form the said two errors can be presented as
follows:

Decision
Particulars
Accept H0 Reject H0
Type I error
H0 (True) Correct Decision
(α error)
Type II error
H0 (False) Correct decision
(β error)
 The Level of Significance :
The level of significance denoted by alpha or 𝛂 refers to the degree of
significance in which we accept or reject the null hypothesis.
100% accuracy is not possible in accepting or rejecting a hypothesis.
The level of significance is the maximum probability of committing a Type
1 Error.
In public health research, alpha is usually 0.01 or 1%.
The probability to commit type 1 error is 1 % and the probability
of the correct decision is 99%.
In social science, alpha is usually 0.05 or 5 %.
The probability to commit type 1 error is 5 % and the
probability of the correct decision is 95%.
And 0.10 or 10% in other studies.
The probability to commit type 1 error is 10 % and
the probability of the correct decision is 90%.
 The Level of Significance :
In symbol, it is written as
𝛂 = 0.01 (1 %)
𝛂 = 0.05 (5 %)
𝛂 = 0.10 (10 %)

If the alternative hypothesis used ≠, then alpha will be divided by 2.

≠ not equal, different from, changed from, not the same as

𝛂/2 = 0.005
𝛂 /2= 0.025
𝛂 /2= 0.05
 1
Example:
In symbol, it is written as:
Determine the value of 𝛂 or 𝛂 /2 based on the alternative
𝛂 = 0.01 hypothesis in decimal form.
𝛂 = 0.05 1. Maria uses 5% level of significance in proving that there
𝛂 = 0.10 is no significant change in the average number of
enrollees in the 10 sections for the last two years. It
If the alternative hypothesis means that the chance that the null hypothesis (𝐻𝑜)
used ≠, then alpha will be would be rejected when it is true is 5%
divided by 2.

𝛂/2 = 0.005
𝛂 /2= 0.025
𝛂 /2= 0.05

𝛼 = 0.05 is the area under the normal curve within

the rejection region.
 1
Example:
In symbol, it is written as:
2. In 2015, it was recorded that around 34% of the
𝛂 = 0.01 population in 2015 were not married. A researcher surveyed
𝛂 = 0.05 a random sample of 500 couples. He found out that 18% of
𝛂 = 0.10 them were living together but unmarried. Test at 5%
significance level if the current percentage of unmarried
If the alternative hypothesis couples is different from 34%.
used ≠, then alpha will be 𝛼/2 = 0.025
divided by 2.
3. The average number of years to finish basic education is
14. A sample of 30 senior high school students were asked
𝛂/2 = 0.005 and found out that the mean number of years to finish their
𝛂 /2= 0.025 basic education is 12 with a standard deviation of 2 years.
𝛂 /2= 0.05 Test the hypothesis at 93% confidence interval that the
average number of years to finish basic education is less
than 14 years.
a = 0.07
One- tailed Test Two-tailed Test
A test of statistical hypothesis, where the A test of statistical hypothesis, where
region of rejection is on only one side of the region of rejection is on both sides
the sampling distribution of the sampling distribution
One- tailed Test Two-tailed Test
When the given statistics hypothesis When the alternative hypothesis is
assumes a less than or greater than two-sided like 𝐻𝑎: 𝜇 ≠ 𝜇0
value

Right-tailed

>
greater than, above, higher than, ≠ not equal, different from, changed
from, not the same as
longer than, bigger than, increased
𝐻𝑎: 𝜇 > 𝜇0

Left-tailed

less than, below, lower than, shorter

< than, smaller than, decreased, or
reduced from
𝐻𝑎: 𝜇 < 𝜇0
Example:
The school registrar believes that the average number of enrollees this school year is not
the same as the previous school year.
Example:
However, if the school registrar believes that the average number of enrollees this school
year is less than the previous school year, then you will have:
Example:
On the other hand, if the school registrar believes that the average number of enrollees this
school year is greater than the previous school year, then you will have:
 One- tailed Test Two-tailed Test

The mean height of grade 12 student is less The standard deviation of their height is not
than 66 inches. equal to 5 inches.

The proportion of senior male students' height Male Grade 7 and Grade 12 students differ in
is significantly higher than that of senior height on average.
female students.

The average grade of Grade 11 students in

Statistics is lower than their average grade in
Calculus.
3
Decision rule or Test of Hypothesis :
A decision rule is a procedure that the researcher uses to decide whether to accept
or reject the null hypothesis. The decision rule is a statement that tells under what
circumstances to reject the null hypothesis. The decision rule is based on specific
values of the test statistic (e.g., reject H0 if Calculated value > table value at the
same level of significance)
Decision rule or Test of Hypothesis :
Getting the P-Value
μ - population mean

Suppose you are interested in investigating whether there is a significant difference in

the wages of men and women in a particular industry. You collect data on the annual
wages of a random sample of 30 men and 30 women in this industry.

Null Hypothesis (H0): There is no significant difference in the wages of men and
women in the industry (μ_men = μ_women).
Alternative Hypothesis (Ha): There is a significant difference in the wages of men and
women in the industry (μ_men ≠ μ_women).
Decision rule or Test of Hypothesis :
Getting the P-Value

Suppose you are interested in investigating whether there is a significant difference in

the wages of men and women in a particular industry. You collect data on the annual
wages of a random sample of 30 men and 30 women in this industry.

significance level
α = 0.05.

If the p-value is less than or equal to α (0.05), you would reject the null hypothesis,
 Decision rule or Test of Hypothesis :
Getting the P-Value
Suppose you are interested in investigating whether there is a significant difference in
the wages of men and women in a particular industry. You collect data on the annual
wages of a random sample of 30 men and 30 women in this industry.

α = 0.05 <= t = 1.4035

Null Hypothesis (H0): There is no significant difference in the wages of men and women in the industry (μ_men = μ_women).
Alternative Hypothesis (Ha): There is a significant difference in the wages of men and women in the industry (μ_men ≠ μ_women).

Null Hypothesis is rejected!

 TESTS OF
HYPOTHESIS
 Tests of Hypothesis

Hypothesis testing is a statistical procedure used to

evaluate the validity of a null hypothesis by analyzing
sample data, allowing for informed decisions about
population parameters.

a) Parametric tests or standard tests of hypotheses

b) Non-parametric tests or distribution-free test of

hypotheses.
 Tests of Hypothesis

Parametric Test Non-parametric tests

Parametric tests usually assume certain
properties of the parent population from There are situations when the researcher
which we draw samples. Assumptions like cannot or does not want to make such
observations come from a normal assumptions. Non-parametric tests do
population, sample size is large, not depend on any assumption about the
assumptions about the population parameters of the parent population and
parameters like mean, variance, etc., typically work with nominal or ordinal
must hold good before parametric tests data. Non-parametric tests need more
can be used. Parametric tests require at observations than parametric tests to
least an interval scale. achieve the same error rates.
Parametric Assumptions

Normality
Dependent variable is in interval scale
Equal variance between groups
Independence

https://www.youtube.com/watch?v=6LRGhWEyUIQ&t=11s&ab_channel=LouisMontano
 IMPORTANT
PARAMETRIC TESTS
 IMPORTANT PARAMETRIC TESTS

The important parametric tests are:

1 Z- Test

2 T- Test

3 F- Test

All these tests are based on the assumption of

normality i.e., the source of data is considered to be
normally distributed.
 Z-TEST

A z test is a test that is used to check if the

means of two populations are different or not
provided the data follows a normal distribution.
For this purpose, the null hypothesis and the
alternative hypothesis must be set up and the
value of the z test statistic must be calculated.
The decision criterion is based on the z critical
value.

https://www.cuemath.com/data/z-test/
 T- TEST

A T-Test is a statistical method used to compare

the means of two groups to determine if there is
a significant difference between them. This
method can be applied to groups that may be
related or unrelated, and it assesses the
probability that the observed difference is due to
more than just random chance.
 F- TEST

F test is a statistical test that is used in hypothesis testing to check whether the variances
of two populations or two samples are equal or not. In an f test, the data follows an f
distribution. This test uses the f statistic to compare two variances by dividing them. An f
test can either be one-tailed or two-tailed depending upon the parameters of the
problem.

https://www.cuemath.com/data/f-test/
 Z-TEST EXAMPLE

Step 1 Step 2

Step 3
Step 4
 T-TEST EXAMPLE

Step 1 Step 2

Step 3
Step 4
Procedure of Hypothesis
Testing
Procedure for hypothesis testing refers
to all those steps that we undertake for
making a choice between the two
actions i.e., rejection and acceptance of
a null hypothesis.
 Procedure of Hypothesis Testing

Making a formal
statement
The step consists in

1
making a formal
statement of the null
hypothesis (H0) and also
of the alternative
hypothesis (Ha or H1).
This means that
hypotheses should be
clearly stated,
considering the nature of
the research problem.
Example:
Imagine we work for a chocolate company and want to test if a new recipe makes our
chocolate bars taste better.

Step 1: Making a formal statement:

Null Hypothesis (H0): The new recipe does not change the taste of the chocolate
bars (μ_new = μ_old).

Alternative Hypothesis (Ha): The new recipe improves the taste of the chocolate
bars (μ_new > μ_old).
 Procedure of Hypothesis Testing

Making a formal statement

The step consists in making a formal statement of
the null hypothesis (H0) and also of the alternative
hypothesis (Ha or H1). This means that hypotheses
should be clearly stated, considering the nature of

1
the research problem.

Selecting a
significance level
The hypotheses are tested 2
on a pre-determined level
of significance and as
such the same should be
specified. Generally, in
practice, either 5% level or
1% level is adopted for the
purpose.
Example:
Light Bulb Factory

Null Hypothesis (H0): The new manufacturing process has no effect on bulb
longevity; it's the same as the old process (μ_new = μ_old).
Alternative Hypothesis (Ha): The new manufacturing process results in longer-
lasting bulbs (μ_new > μ_old).

The factory sets α at 10% (0.10). This means they're okay with a 10% chance of
being wrong.
To say the new process improves bulb longevity, they need strong evidence (p-
value < 0.10).
 Procedure of Hypothesis Testing

Making a formal statement

The step consists in making a formal statement of
Deciding the
the null hypothesis (H0) and also of the alternative
hypothesis (Ha or H1). This means that hypotheses
distribution to use
should be clearly stated, considering the nature of

1
the research problem.
After deciding the level of
significance, the next
Selecting a significance level step in hypothesis testing
The hypotheses are tested on a pre-
determined level of significance and as
such the same should be specified.
2 is to determine the
appropriate sampling
Generally, in practice, either 5% level or 1% distribution. The choice
3
level is adopted for the purpose.
generally remains
between normal
distribution and the
t-distribution.
 Procedure of Hypothesis Testing

Making a formal statement

The step consists in making a formal statement of Selecting a random
the null hypothesis (H0) and also of the alternative
hypothesis (Ha or H1). This means that hypotheses sample and computing
should be clearly stated, considering the nature of
an appropriate value
1
the research problem.

Selecting a significance level

Another step is to select a

2
The hypotheses are tested on a pre-
random sample(s) and
determined level of significance and as compute an appropriate
such the same should be specified.
Generally, in practice, either 5% level or 1% value from the sample data

3 4
level is adopted for the purpose. concerning the test statistic
utilizing the relevant
Deciding the distribution to use distribution. In other words,
: After deciding the level of significance, the next step draw a sample to furnish
in hypothesis testing is to determine the appropriate
sampling distribution. The choice generally remains empirical data.
between normal distribution and the t-distribution.
Step 4: Selecting a random sample and computing an appropriate value

1. Sample Selection: You pick a random group to represent a larger population

fairly.
2. Collecting Data: You collect real-world information, like measurements or
responses, from this group.
3. Computing a Test Statistic: Using this data, you calculate a single number called
a "test statistic." It summarizes the data and helps you decide if your idea
(hypothesis) is supported or not. The test statistic is calculated based on the
data you've collected and a known statistical formula that is appropriate for
your hypothesis test. Choosing the right statistical test is essential for drawing
valid conclusions from your data analysis.
 Guides to help you select the appropriate statistical test:
For Comparing Two Groups:
1. Define Your Research Question Nominal data: Chi-squared test.
2. Identify the Type of Data: Continuous data (normal): Independent t-test.
Continuous data (not normal): Mann-Whitney U test.
a. Nominal data (e.g., colors, gender)
b. Ordinal data (e.g., education levels,)
For Comparing More than Two Groups:
c. Interval data (e.g., temperature in
Nominal data: Chi-squared or Fisher's exact test.
Celsius) Continuous data (normal): ANOVA.
d. Ratio data (e.g., height, weight) Continuous data (not normal): Kruskal-Wallis test.
3. Consider the Number of Groups/Variables
4. Know Assumptions (data normality and For Analyzing Relationships:
independence) Two continuous variables: Pearson for linear,
5. Nature of Variables (independent or Spearman for non-linear.
Categorical variables: Chi-squared or Fisher's exact
dependent)
test.
6. Choose the Right Test: One continuous and one categorical: t-test or
ANOVA.
 Procedure of Hypothesis Testing

Selecting a random sample and

Making a formal statement computing an appropriate value
The step consists in making a formal statement of
Another step is to select a random sample(s) and
the null hypothesis (H0) and also of the alternative
compute an appropriate value from the sample
hypothesis (Ha or H1). This means that hypotheses
data concerning the test statistic utilizing the
should be clearly stated, considering the nature of
relevant distribution. In other words, draw a sample

1
the research problem.
to furnish empirical data.

Selecting a significance level Calculation of the

The hypotheses are tested on a pre-
determined level of significance and as
such the same should be specified.
2 5 probability
Generally, in practice, either 5% level or 1%
One has then to calculate
3 4
level is adopted for the purpose.
the probability that the
sample result would
Deciding the distribution to use
: After deciding the level of significance, the next step diverge as widely as it
in hypothesis testing is to determine the appropriate
sampling distribution. The choice generally remains
has from expectations, if
between normal distribution and the t-distribution. the null hypothesis were
in fact true.
 Procedure of Hypothesis Testing

Comparing the
Making a formal statement
probability and Decision
The step consists in making a formal statement of
making
the null hypothesis (H0) and also of the alternative
hypothesis (Ha or H1). This means that hypotheses Yet another step consists in
should be clearly stated, considering the nature of
comparing the probability
1 6
the research problem.
thus calculated with the
specified value for α, the
Selecting a significance level significance level. If the
The hypotheses are tested on a pre-
determined level of significance and as
such the same should be specified.
2 5 calculated probability is
equal to or smaller than the α
Generally, in practice, either 5% level or 1% value in case of one-tailed
3 4
level is adopted for the purpose.
test (and α /2 in case of two-
tailed test), then reject the
Deciding the distribution to use null hypothesis (i.e., accept
: After deciding the level of significance, the next step the alternative hypothesis),
in hypothesis testing is to determine the appropriate
sampling distribution. The choice generally remains but if the calculated
between normal distribution and the t-distribution.
probability is greater, then
accept the null hypothesis.
Interpretation of the p-value:
A small p-value (typically less than your chosen significance level, α) suggests that
your observed result is unlikely to occur purely by chance if H0 is true. This indicates
strong evidence against H0.
A large p-value suggests that your observed result is reasonably likely to happen
even if there's no real effect, so you don't have strong evidence against H0.

Decision Making:
Based on your chosen significance level (α), you make a decision:
If p ≤ α, you reject H0. You conclude that there's evidence for the effect or
difference you were testing (supporting Ha).
If p > α, you fail to reject H0. You don't have enough evidence to conclude that the
effect or difference exists.

Procedure of Hypothesis testing examples:

https://www.youtube.com/watch?v=mUsv9Zsc1Lk&t=316s&ab_channel=WOWMATH
 Procedure of Hypothesis Testing

Selecting a random sample and

Making a formal statement computing an appropriate value
The step consists in making a formal statement of
Another step is to select a random sample(s) and
the null hypothesis (H0) and also of the alternative
compute an appropriate value from the sample
hypothesis (Ha or H1). This means that hypotheses
data concerning the test statistic utilizing the
should be clearly stated, considering the nature of

6
relevant distribution. In other words, draw a sample

1
the research problem.
to furnish empirical data.

Selecting a significance level Calculation of the probability

The hypotheses are tested on a pre-
determined level of significance and as
such the same should be specified.
2 5 One has then to calculate the probability
that the sample result would diverge as
widely as it has from expectations, if the
Generally, in practice, either 5% level or 1% null hypothesis were in fact true.

3 4
level is adopted for the purpose.

Comparing the probability and

Deciding the distribution to use Decision making
: After deciding the level of significance, the next step Yet another step consists in comparing the probability
in hypothesis testing is to determine the appropriate thus calculated with the specified value for α, the
sampling distribution. The choice generally remains significance level. If the calculated probability is equal to
between normal distribution and the t-distribution. or smaller than the α value in case of one-tailed test
(and α /2 in case of two-tailed test), then reject the null
hypothesis (i.e., accept the alternative hypothesis), but if
the calculated probability is greater, then accept the null
hypothesis.
Thank You
For Your Attention
 Act # 4
Testing of Hypothesis
1.the process of systematically investigating and gathering evidence to determine whether
your educated guess or prediction is supported by the data you collect during your research.
2. It is a tests usually assume certain properties of the parent population from which we
draw samples.
3. It is a tests do not depend on any assumption about the parameters of the parent
population and typically work with nominal or ordinal data.
4. a statement or assumption about a population or a phenomenon that is subject to
empirical testing using statistical methods.
(5-6) two types of errors we can make in testing of hypothesis.
(7-12) What are the procedures of hypothesis testing?
(13- 15)List three parametric test types that have been discussed in the report.