INSTITUTE –Chandigarh University

DEPARTMENT –University School of Business

(MA Economics)
Subject Name and Code: Research Methodology & Statistical
Applications – 20SET 713
Faculty Name: Dr. Atul Shiva (Assistant Professor)

TOPIC OF PRESENTATION
DISCOVER . LEARN . EMPOWER
Testing of Hypothesis 1
 Course Objective

COB No. Title

COB1 To acquaint students with the knowledge of Research and its types

To enable students to interpret data through various tests and various research methods to examine
COB2 various research problems.

2
 Course Outcome

Sr. No. Course Outcomes Blooms Taxonomy Level

CO1 Students will be to understand the importance and types of Understand/Remember
research.
CO2 Students will be able to comprehend with various research Apply
designs and data collection techniques.
CO3 Students will be able to appraise with various sampling Analyze
procedures and analyze data through various techniques.
CO4 Students will develop research methodological skills for Evaluate/Design/Create
undertaking research in social sciences in general and how data
analysis is done using statistical tests.

3
Lecture Overview
In this Presentation, we will learn about:
❖Different terminologies in testing of hypothesis

This lecture will cover course outcome 4 (CO4)

• This lecture will cover the Course objective 4
• CO4: Students will develop research methodological skills for
undertaking research in social sciences in general and how data
analysis is done using statistical tests.

4
Basics of Hypothesis Testing
• Population: Aggregate of facts whether animate or non-animate is
called as the population.
• Parameters: Characteristics of the population are called as the
parameters
• Sample: A small segment, part or subset of the population is called as
the sample.
• Statistic: Characteristics of the sample are termed as the statistic.

5
Hypothesis
• A hypothesis is an assumption or a statement that may or may not be true.
• The hypothesis is tested on the basis of information obtained from a
sample.
• Hypothesis tests are widely used in business and industry for making
decisions.
• Instead of asking, for example, what the mean assessed value of an
apartment in a multistoried building is, one may be interested in knowing
whether or not the assessed value equals some particular value, say Rs 80
lakh.
• Some other examples could be whether a new drug is more effective than
the existing drug based on the sample data, and whether the proportion of
smokers in a class is different from 0.30.

6
Hypothesis
• In statistics, a hypothesis is a claim or statement about a property of a
population.
• A hypothesis test (or test of significance) is a standard procedure for
testing a claim about a property of a population

7
Types of Hypothesis
• Null hypothesis: The hypotheses that are proposed with the intent of
receiving a rejection for them are called null hypotheses. This requires that
we hypothesize the opposite of what is desired to be proved. For example,
if we want to show that sales and advertisement expenditure are related,
we formulate the null hypothesis that they are not related. Null hypothesis
is denoted by H0.
• Alternative hypothesis: Rejection of null hypotheses leads to the
acceptance of alternative hypotheses. The rejection of null hypothesis
indicates that the relationship between variables (e.g., sales and
advertisement expenditure) or the difference between means (e.g., wages
of skilled workers in town 1 and town 2) or the difference between
proportions have statistical significance and the acceptance of the null
hypotheses indicates that these differences are due to chance. Alternative
hypothesis is denoted by H1.

8
Examples of Null and Alternative Hypothesis
• XYZ company claims that after using their medicine the height of a
person on average gets increased. Frame the null and alternative
hypothesis for checking this belief.
• H0: The drug is not effective
• H1: The drug is effective

9
Examples of Null and Alternative Hypothesis
• As a medical student I want to study the relationship between living
in a stressful environment and incidents of heart attack. Frame the
appropriate null and alternative hypothesis for the same.
• H0: There is no relationship between living in a stressful environment
and incidents of heart attack
• H1: There is a relationship between living in a stressful environment
and incidents of heart attack

10
Examples of Null and Alternative Hypothesis
• In a study one is looking to frame the null and alternative hypothesis
regarding whether there is any significance difference between
different gender and the statement: I have a lot of work in this
business.
• H0: There is no significant difference between the different gender on
the statement I have a lot of work in this business.
• H1: There is significant difference between the different gender on
the statement I have a lot of work in this business.

11
Type 1 Error (False Positive):
• A Type 1 error occurs when a null hypothesis that is actually true is
rejected.
• In other words, it's the error of mistakenly concluding that there is a
significant effect or relationship when there isn't one.
• It's often denoted by the symbol α (alpha) and represents the level of
significance chosen for a hypothesis test. Common significance levels
include 0.05 and 0.01.
• For example, in a medical context, a Type 1 error would be concluding
that a patient has a disease when they actually do not.

12
Type 2 Error (False Negative):
• A Type 2 error occurs when a null hypothesis that is false is not
rejected.
• In other words, it's the error of failing to identify a significant effect or
relationship when there actually is one.
• It's often denoted by the symbol β (beta).
• For example, in a medical context, a Type 2 error would be failing to
diagnose a patient with a disease when they actually have it.

13
 Type I and Type II Errors

Fail to

Copyright © 2007 Pearson Education, Inc

Publishing as Pearson Addison-Wesley.
Types of Errors in Hypothesis Testing
Case 1: Null Hypothesis is true(We are accepting it) No Error

Case 2. Null Hypothesis is true(We are rejecting it) Type One Error(Alpha-α)

Case 3. Null hypothesis is false (We are rejecting it) No Error

Case 4. Null Hypothesis is false(We are accepting it) Type Two Error(Beta-β)

Type 1 Error (False Positive)

Type 2 Error (False Negative):

15
Examples of Two types of Errors
• Suppose a new instrument has been developed to check the cancer. Check
whether the instrument is capable of detecting the disease.

• H0: There is no disease.

• H1: There is disease.

• There is no disease (When actually there is no disease) No error

• There is disease (When actually there is no disease) (Type One Error(Alpha-α) –
We rejected the null hypothesis
• There is disease (When actually there is disease) No error
• There is no disease (When there is disease) (Type Two Error(Beta-β) ) We
accepted alternate instead of null means
16
Examples of Two types of Errors
• H0: The Person is not guilty.
• H1: The Person is guilty.

• Person is not guilty (When actually he is not guilty)

• Person is guilty (When actually he is not guilty)(Alpha)
• Person is guilty (When actually he is guilty)
• Person is not guilty (When actually he guilty) (Beta)

17
Level of Significance
• Level of significance: The size of first type of error is called the level
of significance. In other words the probability of first type of error is
called level of significance.
• It is denoted by alpha (α)

18
Confidence Level
• Confidence level: 1- α is called as the confidence level.
As the total probability is one so 1 minus the probability of the first
type of error is called as the confidence level

19
Power of the Test
• Power of the Test: 1-β is called as the power of the test.

20
One Tailed Test and Two tailed Test
• One-tailed tests: A test is called one-sided (or one-tailed) only if the
null hypothesis gets rejected when a value of the test statistic falls in
one specified tail of the distribution.
• Two-tailed tests: Further, the test is called two-sided (or two-tailed)
if null hypothesis gets rejected when a value of the test statistic falls
in either one or the other of the two tails of its sampling distribution.

21
Two-tailed Test
H0: =  is divided equally between
the two tails of the critical

H1:  region

Means less than or greater than

Copyright © 2007 Pearson Education, Inc

Publishing as Pearson Addison-Wesley.
Right-tailed Test
H0: =
H1: >
Points Right

Copyright © 2007 Pearson Education, Inc

Publishing as Pearson Addison-Wesley.
Left-tailed Test
H0: =
H1: <
Points Left

Copyright © 2007 Pearson Education, Inc

Publishing as Pearson Addison-Wesley.
 Decision Criterion
Traditional method:
Reject H0 if the test statistic falls within the critical
region.

Fail to reject H0 if the test statistic does not fall within

the critical region.

Copyright © 2007 Pearson Education, Inc

Publishing as Pearson Addison-Wesley.
Qualities of a good hypothesis
• Clear and Specific: A good hypothesis should be clear and specific,
stating the relationship between variables or making a clear
prediction about the outcome of an experiment or observation.
• Testable: A hypothesis should be testable through empirical
observation or experimentation. This means that there must be a way
to gather evidence
• Falsifiable: A good hypothesis should be falsifiable, meaning that it
can be proven false if the evidence does not support it. In other
words, there should be a way to disprove the hypothesis if it is
incorrect. that either supports or refutes the hypothesis.

26
Qualities of a good hypothesis
• Relevant: A hypothesis should be relevant to the research question or
problem being investigated. It should address an important issue or
gap in knowledge and contribute to the advancement of scientific
understanding
• Based on Previous Knowledge: A good hypothesis should be based
on existing knowledge or theories in the field. It should build upon
what is already known and provide a logical explanation or prediction
based on this foundation.
• Generalizable: A good hypothesis should be generalizable beyond the
specific context of the study. It should have broader implications or
applicability beyond the immediate research setting.

27
Procedure for Hypothesis Testing
• Setting up of a hypothesis
• Setting up of a suitable significance level
• Determination of a test statistic
• Determination of critical region
• Computing the value of test-statistic
• Making decision

28
• Suppose a company wants to determine whether there is a significant
difference in employee satisfaction levels before and after
implementing a new wellness program. Employee satisfaction is
measured using a Likert scale ranging from 1 (very dissatisfied) to 5
(very satisfied).

29
Step 1: Setting up of a Hypothesis:
• Null Hypothesis (H0): There is no difference in mean satisfaction
levels before and after the wellness program (μ1 = μ2).

• Alternative Hypothesis (H1): There is a difference in mean satisfaction

levels before and after the wellness program (μ1 ≠ μ2).

30
Step 2: Setting up a Suitable Significance
Level:
• Let's choose a significance level (α) of 0.05.
• This indicates that we are willing to accept a 5% chance of rejecting
the null hypothesis when it is actually true.

31
Step 3: Determination of a Test Statistic:

32
Step 4: Determination of Critical Region:
• Since it's a two-tailed test, we're interested in the critical values at the
0.025
• level of significance (0.05 divided by 2), in both tails of the t-
distribution.
• For example, if we have a sample size of 30 (which yields 29 degrees
of freedom) and a significance level of 0.05, the critical values can be
obtained from a t-table or calculated using statistical software. Let's
say the critical values are approximately ±2.3639.
Relationship: The level of significance directly determines the size of the critical region. A higher level of
significance corresponds to a larger critical region, meaning that it is more likely to reject the null
hypothesis for a given sample size and test statistic.
Conversely, a lower level of significance results in a smaller critical region and a lower probability of
rejecting the null hypothesis. This reflects a more conservative approach to hypothesis testing, where 33
Step 5: Computing the Value of the Test
Statistic:
• Suppose the company collects data from 30 employees and finds the
following:
• Before Wellness Program:

34
35
Step 6: Making Decision:
• Since the absolute value of the calculated test statistic (2.817) is
greater than the critical value (2.3639) at the 0.025 level of
significance, we reject the null hypothesis. Therefore, we conclude
that there is a significant difference in mean satisfaction levels before
and after the wellness program.
• In summary, the company conducted a paired samples t-test to
determine whether the wellness program had an impact on employee
satisfaction levels. Based on the calculated test statistic and
comparison with critical values, the company made a decision to
reject the null hypothesis and accept the alternative hypothesis.

36
EXAMPLE
• A two-tailed test in the context of Likert scale data would involve
testing a hypothesis that a population parameter (such as the mean
or proportion) is not equal to a specific value. Let's consider an
example:
• Suppose a company wants to determine whether there is a significant
difference in employee satisfaction levels before and after
implementing a new training program. Employee satisfaction is
measured using a Likert scale ranging from 1 (very dissatisfied) to 5
(very satisfied). The company collects data from a random sample of
employees before and after the training program and wants to test
the hypothesis:

37
• Null Hypothesis (H0): There is no difference in mean satisfaction
levels before and after the training program (μ1 = μ2).

• Alternative Hypothesis (H1): There is a difference in mean

satisfaction levels before and after the training program (μ1 ≠ μ2)

38
• To perform a two-tailed test, the company would use a statistical test
such as the t-test for independent samples or the paired samples t-
test, depending on whether the samples are independent or paired
(matched).

• The choice of test depends on whether the same individuals are

measured before and after the training program.

39
• Using a two-tailed t-test, the company would calculate the test
statistic and compare it to the critical value from the t-distribution
with the appropriate degrees of freedom (based on the sample sizes
and assuming equal variances). If the test statistic falls outside the
critical region (i.e., if it is sufficiently large or small), the company
would reject the null hypothesis and conclude that there is a
significant difference in mean satisfaction levels before and after the
training program.
• In this example, a two-tailed test allows the company to detect
whether satisfaction levels have either increased or decreased
significantly as a result of the training program, without making
specific assumptions about the direction of the change.
40
 Summary
1. Hypothesis testing is a part of the inferential Statistics which help us drawing
inferences about any population parameters.
2. Hypothesis are the assumptions to be tested on the basis of the sample drawn from
the population

41