Sunteți pe pagina 1din 100

Methodology Used In

Social Science
and
Management
Prof. P. Veni,
Dept. of Commerce & Management Studies,
Andhra University, Visakhapatnam

Research
Research is collection of information
to test new ideas or disprove old
ones.
In scientific terminology research is
an endeavour to discover facts by
scientific methods and is a course of
critical investigation.
An original investigation to the
existing stock of knowledge, making
for its advancement.

Research (Contd.)
Definition:
A research comprises of defining and
redefining problems, formulating
hypothesis (or) suggesting solutions,
collecting, organising and evaluating data,
making decisions and reaching conclusions
to decide whether they fit the formulating
hypothesis.

Clifford Woody

Types of Research: Based on


Nature of Study
Nature/Physical Science Research: Its the
search for knowledge in order to understand the
physical world.
Social Sciences Research: Its the search for
knowledge about individual human beings and
their societies.

Social Science Research


Questioning for Growing Importance of Social
Research
Why does a society devote some of its resources to
this business of developing new knowledge about
the social words?
Or
What has motivated the social researchers to
devote their lives to developing the new
knowledge?

Social Science Research (Contd.)


Reasons for Such Growing Importance of
Social Science Research
Desire to improve peoples lives.
Societys desire for economic development
Humanitys increasing control over our planet
and its environment.

Expectations From Social Sciences


Research
To enhance understanding of the society
and its functioning;
Provide input for policies, procedures of
socio-economic management and
development
Generate ideas and information that could
be used for teaching of various levels of
education
Growth of disciplined based and technique
oriented research.

Social Sciences: Disciplines


1.Various Disciplines

2.Multidisciplinar
y

Behaviour
Science
Geography
History
Law
Linguistics
Psychology
Public
Administrati
on

Social Sciences

3.STEM

Sciences
(Natural/Life)
Commerce
Technology
Management Engineering
Anthropolog Mathematics

y
Economics
Sociology
Political
Studies
Social Work
Education
Demography

4.Humanities

History
Literature
Languages
Library
Studies

5.Cross-Over Disciplinary Groups


Social Sciences & Humanities
Law, Cultural Studies,
Library Sciences, education
Social Sciences & STEM
Geography Psychology,
Health Sciences,
STEM & Humanities (STEAM)
Architecture, Arts

Social Research
Social research examines a societys
attitudes, assumptions, beliefs,
trends, stratifications and rules
Social research is a systematic
method of exploring, analysing &
conceptualising human life in order
to extend, correct or verify
knowledge of human behaviour and
social life.

Science::Scientific Research:: Social


Science Research
Science: A science is often thought of as
being a coherent body of thought about a
topic over which theres a broad
consensus among its practitioners.
Scientific Research: A research is said to
be scientific, when it follows the two
primary functions
1. The development of theory
2. Testing of substantive hypothesis deducted
from the theory

Science::Scientific Research:: Social


Science Research (Contd.)
Scientific Research Involves
Use Theory

Modify Theory

Create Theory

Social Science Research:


Social science research attempts to create
or validate theories through data
collection, data analysis and its goal is
exploration, description and explanation.

Management: An Interdisciplinary Subject

Academic Disciplines that Affected


Management
Anthropology - work on cultures and social
environments
Economics - concern about the allocation
and distribution of scarce resources
Philosophy - examines the nature of things
Political science - effect of political
environment on individuals and groups
Psychology - seeks to measure, explain, and
change human behavior
Sociology - studies people in relation to their

Management Research:: Substantive


Areas:: Content Domains

Policy/Strategy
Organization Theory
Organization Behaviour
Human Resource Management
Marketing
Production & Operations Management
Finance

Philosophical Assumptions of Social


Sciences & Management Research
In any discipline, there will always be a number of underlying
philosophical predispositions in the projects of scientists.
Some of these predispositions involve the nature of social
knowledge itself, the nature of social reality, and the locus of
human control in action. As social scientists, we must
understand the three philosophical assumptions that
influence social research.
1. EPISTEMOLOGY

2. ONTOLOGY

3. METHODOLOGY

1. Epistemology
It concerns clarification of researchers beliefs
about how knowledge is created?
Views on Epistemology
Normative Approach (or) Positivism
Research creates knowledge by building on the
foundations of accepted and rationally defensible
theory

Interpretative Approach (or) Constructivism


Research must set aside existing knowledge and create
new knowledge from internal coherence.

2. Ontology
It concerns about the nature of the world and
human beings in social contexts (Bryman., 2001)
Ontology assures that social phenomena can be
studied objectively apart from the people who
make it.
In cut-short
Different researchers may have different conclusions
from one study.

3. Methodology
Methodological assumptions focus on analysis of the
methods used for gathering research data.
(Louis Kohen, Lawrence Manion & Keith Morrision, 2001)

Research methodology is a way to systematically


solve the research problem.
Researchers need to understand the
assumptions underlying various techniques,
procedures, and their applicability criteria.

3. Methodology (Contd.)
Research Methodology: Approaches
In social sciences research, the researchers commonly had two
basic approaches to conduct their respective research works.
They are:
1. Quantitative Approach
2. Qualitative Approach
Quantitative Approach:
The quantitative approach involves the generation of data in
quantitative form and which can be subjected to rigours
quantitative analysis ina formal and rigid fashion.
Observe & Interpret the Data

3. Methodology (Contd.)
Qualitative Approach:
The qualitative approach to research is concerned with subjective
assessment of attitudes, opinions & behaviour.
Research in qualitative approach is a function of researchers insights &
impressions
Investigate into the data

Social Science Research: Problems


Complexity in Communication of Research
The routes and mechanisms through which research is
communicated to places where it can make a difference are many and
varied. The ways in which the research is then used is also complex.

Thus, the major difficulty lies in tracking the following subtle


changes resulting the complexity in communication of
research
Research may directly influence the changes in policies, practices &
behaviour
(or)
Research, in a more subtle way changes peoples knowledge,
understanding and attitudes toward social issues.

Social Science Research: Problems (Contd.)


Additional Problems
Who are research users?
(Where to look for research impacts)

How long will it take to effect?


(When to look for research impacts)
Was this a key factor to the changes observed?
(How to assess the specific contributions made by
the research)

Social Science Research: Problems (Contd.)


Addressing the problems
Tracking forward from completed research works
to see where and how it is communicated and to
what effect
(OR)
Examining policy choices, organisational
management and professional practice to explore
how research is sought out and used in these
areas and to what effects

Social Science Research: Decision Making


Both of the following kinds of researches are
used in decision making
Academic Research: The autonomous research
contributions by social scientists
In Addition to
Inferior Research: Researches sponsored by
govt. Agencies with specific objectives for
performance of policies and programmes

Social Science Research:: Decision Making::


A Dichotomy
There exists a false dichotomy in between
these academic and inferior researches
Academic Research is not used for policy
making
Inferior research didnt come to work on
subjects and choose questions of direct
relevance.

Objectives of Research
Exploratory Research
To gain familiarity with a phenomena
To achieve new insights into it

Descriptive Research
To portray the characteristics of a particular situation
or group

Diagnostic Research
To determine the frequency with which it is associated
with something else, when something occurs.

Hypothesis Testing Research


To test a hypothesis of a casual relationship between
variables under the study.

Social Science Research:


Reasoning
Deductive Reasoning
Inductive Reasoning

Social Science Research:


Reasoning
Deductive Reasoning
In deductive research, the decisions are
derived and show general to the particular
i.e., some (or) particular inference is made
from general observation of earlier studies
The conclusion follows logically from
premises. Theory
Hypothesis
Observation
Confirmation

Social Science Research:


Reasoning
Inductive Reasoning
Inductive research is just opp. of deductive
reasoning.
This research arrives at universal generalisations
from particular facts
Theory
The conclusions are likely
based on premises it
Hypothesis
involves a great
Pattern
degree of
uncertainty
Observation
Its concerned
with the establishment of material truth of universal
propositions

Ideas: What we think

THEORY

DEDUCTIVE
REASONING

INDUCTIVE
REASONING

DATA
Reality: What we observe

Social Science Research: Issues to Consider


Complexity of Social Data
Problems of Concepts
Problems in Interpreting Relationship between Cause
and effect:
Dynamic Nature of Social Phenomena
Problem of maintaining objectivity
Unpredictability
Difficulty in the Verification of the Inferences
Difficulty in the Use of Experimental Method
Incapability of being dealt through empirical method
Problems of inter-disciplinary research

Social Science Research:


Methodology and Methods
Methodology is broader and envelops
methods:
Methodology => understanding the entire
research process, including its socialorganizational context, philosophical assumptions,
ethical principles and impact of new knowledge

Methods => collection of specific techniques


we use in a study to select cases, measure and
observe social life, gather and analyze data and
report on results.

Triangulation
(McGrath, 1982)
According to McGraths words, it is not possible to do an
unflawed study. Any research method chosen will have inherent
flaws and the choice of that method will limit the conclusions that
can be drawn.
Its therefore, eventual to obtain corroborating evidence from
using variety of methods
Triangulationis a powerful technique that facilitates validation
of data through cross verification from two or more sources. In
particular, it refers to the application and combination of
severalresearchmethods in the study of the same phenomenon.

Triangulation (Contd.)
(McGrath, 1982)
Triangulation is an approach to research that
uses a combination of more than one research
strategy in a single investigation.
Triangulation can be a useful tool for qualitative
as well as quantitative researchers.
Used with care, it contributes to the
completeness and confirmation of findings
necessary in qualitative research investigations.

Types of
Triangulation
Data Triangulation
Time, space, person

Method Triangulation
Design
Data collection

Benefits of
Triangulation
Improves ability of
researchers to draw
conclusions for their
studies

Investigator Triangulation
Recommend their
Theory Triangulation
Multiple Triangulation

superiors with greater


clarity & confidence.

Triangulation Research Strategies


by McGrath, 1982
Formal Theory
Sample Surveys
Lab Experiments
Judgement Tasks
Computer Simulations
Experimental Simulations
Field Studies
Field Experiments

Research Methodology:
Validity
Every research must successfully pass
through the following validities
Internal Validity
External Validity
Construct Validity
Statistical Conclusion Validity

Internal Validity
Internal validity of a research is concerned
about the causality.
A cause and effect relationship can only be
asserted if theres a true co-ordination
between the variables under investigation
Data collection procedures used to
demonstrate that the cause preceded the
effect and alternative explanations have
been discarded

External Validity
External validity refers to generalising
across times, settings and individuals.
External validity relies upon establishing
a true representation of the relationship
between two constructs and establishing
that the relationship is generalised to
different populations, measures and
circumstances

Construct Validity
Concerns how well the measures
employed fit the theories for which a test
is designed.
Researcher must test his research work
for measurement flaws.
Measures and manipulations must be
faithful representations of constructs in
order for valid inferences to be made.

Statistical Conclusion Validity


Statistical conclusion validity refers to
ability to draw conclusions on the basis
of co-variation as well as prediction.
The application of the appropriate
statistical test or analytical procedure is
more important for statistical conclusion
validity, scince the underlying
assumptions may limit their
applicability.

Planning for Research and Choosing the Topic


Has it been explored? If so, by whom and how? If not,
why not?
Who are the stakeholder; who may it harm and/or
benefit and how?
Funding, politics and conflicts of interest.
What are the potential consequences of your work?
How can these risks be avoided, negotiated/ minimised
or justified?

Deciding on the methodology


Minimising risks and maximising data
generation
Ethics, validity and triangulation
Action research: data gathering vs.
intervention

Entering the field


If you are deciding to enter someone's 'space',
how are you going to achieve this?
When and where are you going to approach
them?
Again, are there risks involved, and if so, who
does the research place at risk, and how?
What boundaries exist and how can or should
they be overcome?
Do they in fact reveal something more
important?

Explaining work and cooperation


Informed consent
Maintaining informed consent over time
Clarity and adequacy of explanation
Routines, spiels and scripts

Collecting and recording data


Practicalities of fieldwork. How can you
accurately record information,
especially about social events?
Do your respondents know and approve
of what you have recorded?
Non response and room for silence (in
qualitative and quantitative research)

Storing data
Is your data sensitive?
Can it put people at risk if it falls into the
hands of certain people?
How are you going to protect your data,
your interests and the interests of your
informants?

Analysing, interpreting and communicating


findings
-Honesty with data and interpretation (biases,
convenient readings etc)
-Participative inquiry/analysis, source checking
-Presenting identities, personal or 'troubling'
information?
-Sharing your results or conclusions with
individuals or organisations?

Analysing, interpreting and communicating


findings

Anticipating feedback and reactions


Ownership of data and publishing
Implications of research & interpretation

Research Methods
Research methods in social sciences are often
divided into two main types:

Quantitative Research
Methods
Qualitative Research
Methods

Characteristics of quantitative and


qualitative research

Source: Quoted from : Maginn, P.J. (2006) Urban Policy Analysis Through a Qualitative Lens: Overview to Special Issue, Urban Policy and Research, Vol 24(1) pp. 1
Franklin, A. (1986) Ethnography and housing studies, Housing Studies, 5(2), pp. 92111.
Punch, K. (1998) Introduction to Social Research (London: Sage).
Spencer, L., Ritchie, J., Lewis, J.& Dillon, L. (2003) Quality in Qualitative Evaluation: A Framework for Assessing Research Evidence,
Occasional Papers Series No. 2 (London: Government Chief Social Researchers Office).
Winchester, H. P. M. (2000) Qualitative research and its place in human geography, in: I. Hay (Ed.) Qualitative Research Methods
n Human Geography, pp. 122 (Oxford: Oxford University Press).

Quantitative Research
Quantitative research is the numerical
representation and manipulation of
observations for the purpose of describing
and explaining the phenomena that those
observations reflect. It is used in a wide
variety of natural and social sciences,
including physics, biology, psychology,
sociology and geology
Cohen (1980), quantitative research is
defined as social research that employs
empirical methods and empirical statements.

Quantitative Research (Contd.)


Quantitative research is rooted in the
positivistic approach to scientific inquiry
each part of a quantitative design is important
if any part is is deficient, the entire design is
weakened

The notion of causality is examined


one of the main purposes of quantitative
study is to detect casual relationships between
variables.

Answering Questions
Quantitative Research attempts to
answer questions by
ascribing importance (significance) to
numbers or sizes or reactions and results

Objectives of Quantitative Research


Describe how descriptive, casual-comparative,
correctional, and experimental designs differ in
their power to reveal casual relationships
Compare the relative advantages and disadvantages
of the mean and the median
Interpret the meaning of the standard deviation in
relation to the normal curve
Describe how a test of statistical significance is used
to decide whether to reject or accept the null
hypothesis

When do we use quantitative


methods?
The first is when we want a quantitative answer
Numerical change can likewise only accurately be
studied using quantitative methods.
Quantitative research is useful for conducting
audience segmentation.
Quantitative research is also useful to quantify
opinions, attitudes and behaviours and find out how
the whole population feels about a certain issue.
Quantitative research is suitable to explain some
phenomena.
Testing of hypotheses

Pros of Quantitative
Research?
Clear interpretations
Make sense of and organize
perceptions
Careful scrutiny (logical, sequential,
controlled)
Reduce researcher bias
Results may be understood by
individuals in other disciplines

Cons of Quantitative
Research?
Can not assist in understanding
issues in which basic variables have
not been identified or clarified
Only 1 or 2 questions can be studied
at a time, rather than the whole of an
event or experience
Complex issues (emotional response,
personal values, etc.) can not always
be reduced to numbers

Common Approaches to Quantitative


Research
Surveys
Custom surveys
Mail/e-mail/Internet
surveys
Telephone surveys
Self-administered
questionnaire
surveys

Correlation
Trend analysis
Exploratory research
Descriptive research
Experimental
research

Quantitative Research: Statistical Tools for Data


Analysis
Summarizing Data: variables; simple statistics; effect statistics and statistical models;
complex models.
Generalizing from Sample to Population: precision of estimate, confidence limits,
statistical significance, p value, errors.
Data are a bunch of values of one or more variables.
A variable is something that has different values.
Values can be numbers or names, depending on the variable:
Numeric, e.g. year of migration
Counting, e.g. number of natural disasters
Ordinal, e.g. distance of migration destination(values are numbers/names)
Nominal, e.g. sex or age (values are names)

Model/Test

Effect statistics

numeric

numeric

regression

numeric

nominal

T test, ANOVA

nominal

nominal

chi-square

frequency difference or ratio

nominal

numeric

categorical

frequency ratio per

slope, intercept, correlation


mean difference

Quantitative Research: Measurement


Measurement in quantitative research should fulfill

Validity - Are you measuring what you think you are


measuring?

Objectivity - researchers stand outside the phenomena


they study. Data collected are free from bias.

Reliability - if something was measured again using the

same instrument, would it produce the same or nearly the same


results?

Accuracy Are the methods adequate to answer your

questions?; reveal credible information?; convey important


information?

Precision How much trustable, how confident is the result.

Quantitative Research: Statistical


Representations
Quantitative representations of our data
Can be:
Descriptive statistics summarize data.
Inferential statistics are tools that indicate how
much confidence we can have when we generalize
from a sample to a population.

Use of Statistics in Quantitative Research


Descriptive
objectives/
research questions:

Descriptive
statistics

Comparative
objectives/
hypotheses

Inferential
Statistics

Descriptive Statistics
Can be applied to any measurements
(quantitative or qualitative)

Offers a summary/ overview/ description of


data. Does not explain or interpret.

Descriptive Statistics

Number
Frequency Count
Percentage
Deciles and quartiles
Measures of Central
Tendency (Mean,
Midpoint, Mode)

Variability
Variance and
standard deviation
Graphs
Normal Curve

Inferential Statistics
Allows for comparisons across variables
i.e. is there a relation between ones
occupation and their reason for using the
public library?

Hypothesis Testing

Levels of significance
The level of significance is the
predetermined level at which a null
hypothesis is not supported. The most
common level is p < .05
P =probability
< = less than (> = more than)

Error Type

Type I error
Reject the null
hypothesis when it is
really true

Type II error
Fail to reject the null
hypothesis when it is
really false

Probability
By using inferential statistics to make
decisions, we can report the probability
that we have made a Type I error
(indicated by the p value we report)
By reporting the p value, we alert readers
to the odds that we were incorrect when
we decided to reject the null hypothesis

Particular Tests
Chi-square test of independence: two
variables (nominal and nominal,
nominal and ordinal, or ordinal and
ordinal)
Affected by number of cells, number of cases
2-tailed distribution= null hypothesis
1-tailed distribution= directional hypothesis
Cramers V, Phi

Inferential Statistics (Contd.)


Correlationthe extent to which two variables
are related across a group of subjects
Pearson r

It can range from -1.00 to 1.00


-1.00 is a perfect inverse relationshipthe strongest
possible inverse relationship
0.00 indicates the complete absence of a relationship
1.00 is a perfect positive relationshipthe strongest
possible direct relationship
The closer a value is to 0.00, the weaker the relationship
The closer a value is to -1.00 or +1.00, the stronger it is

Spearman rho

More tests
t-test
Test the difference between two sample means for
significance
pretest to posttest
Relates to research design
Perhaps used for information literacy instruction

Analysis of variance
Regression analysis (including step-wise
regression)

More tests
Analysis of variance (ANOVA) tests the
difference(s) among two or more means
It can be used to test the difference between
two means
So use t-test or ANOVA?
KEY: ANOVA also can be used to test the
difference among more than two means in a
single testwhich cannot be done with a t test

More tests
While correlation and regression both indicate
association between variables, correlation
studies assess the strength of that association
Regression analysis, which examines the
association from a different perspective, yields
an equation that uses one variable to explain
the variation in another variable.
Regression is used to predict the value of one
variable by knowing the value of another
variable

Inferential Statistics: uses sample data


to evaluate the credibility of a hypothesis
about a population
NULL Hypothesis:
NULL (nullus - latin): not any no
differences between means

H0 : m1 = m2
Always testing the null hypothesis

H- Naught

Inferential statistics: uses sample data to


evaluate the credibility of a hypothesis
about a population
Hypothesis: Scientific or alternative
hypothesis
Predicts that there are differences
between the groups

H1 : m1 = m2
H- One

Testing of Hypothesis

Statistical inference. Role of chance.

S c ie n t i f ic k n o w le d g e
R e a s o n a n d i n t u it io n

Formulate
hypotheses

E m p ir i c a l o b s e r v a t io n

Collect data to
test
hypotheses

Statistical inference. Role of chance.


Systematic error

Formulate
hypotheses

Collect data to
test hypotheses

CHANCE
Accept hypothesis

Reject hypothesis

Random error (chance) can be controlled by statistical significance


or by confidence interval

Testing of hypotheses
Null hypothesis H0 -

there is no difference

Alternative hypothesis H1 - question explored by


the investigator

Statistical method are used to test hypotheses

The null hypothesis is the basis for statistical test.

Types of Hypothesis
Null Hypothesis:
Denoted with (H0 )
This a statement or pressumption which a researcher
is going to consider it in the research and disprove it.
Its a statement written in a negative or opposite
manner to the alternative hypothesis ( H1)
Now a days, this null hypothesis is being coined in
either of the ways i.e., negative or positive
But, when we consider the null hypothesis being
accepted, in research studies, misleads the actual
intentions of the researchers.

Types of Hypothesis (Contd.)


Alternate Hypothesis:
Denoted with (H1 )
Also known as Research Hypothesis
Alternate Hypothesis is an assumption
which is not null.
Its the assumption in the mind and in
words of researcher, which is going to be
happen or result out or found out in his/her
research.

Testing of Hypothesis: Procedure


For any quantitative research work, in
order to test hypothesis, the following
five steps must be adopted without fail.
1.
2.
3.
4.
5.

Formulate Hypothesis
Fix Level of Significance ()
Calculate Test Statistic
Note Down the Critical Value
Compare the Calculated Test Statistic with
Standard Critical Value and Make Decision

1. Formulate Hypothesis
Frame null and alternate hypothesis for
your research work
Points to consider while framing research
hypothesis
Predictive Statement
Clear, Precise, Simple Terms,
Limited Scope, Capable of Being Tested,
Consistent With Facts, Reasonable Time Frame
Relationship With Variables

2. Level of Significance ()
Denoted by (Alpha; Greek Alphabet)
the probability of rejecting the null
hypothesis in a statistical test when it is true
aka significance level
For example, a significance level of 0.05
indicates a 5% risk of concluding that a
difference exists when there is no actual
difference.

2. Level of Significance () Contd.


The significance
level
determines how
far out from the
null hypothesis
value we'll draw
that line on the
graph. To graph
a significance
level of 0.05,
we need to
shade the 5% of
the distribution
that is furthest
away from the
null hypothesis.

Example of a normal curve showing


how to graph the result of
hypothesis testing and Decision
Making

3. Test Statistic
Every member of the
population has the
same chance of being
selected in the sample
Population

Parameters: Characteristic of Population

estimation

Random sample

Statistic: Characteristic of Samp

3. Test Statistic (Contd.)


Atest statisticis a standardized value that is calculated
from sample data during a hypothesistest. You can
usetest statisticsto determine whether to reject the
null hypothesis. Thetest statisticcompares your data
with what is expected under the null hypothesis.
The test statistic compares your data with what is
expected under the null hypothesis. The test statistic is
used to calculate the p-value.
A test statistic measures the degree of agreement
between a sample of data and the null hypothesis. Its
observed value changes randomly from one random
sample to a different sample.

3. Test Statistic (Contd.)


A test statistic contains information about the data that
is relevant for deciding whether to reject the null
hypothesis.
The sampling distribution of the test statistic under the
null hypothesis is called the null distribution.
When the data show strong evidence against the
assumptions in the null hypothesis, the magnitude of
the test statistic becomes too large or too small
depending on the alternative hypothesis.
This causes the test's p-value to become small enough
to reject the null hypothesis.

3. Test Statistic (Contd.)

Test Statistic =

(Sample Statistic) (Population


Parameter)
Standard Error

4. Critical Value
In hypothesis testing, acritical
valueis a point on the test
distribution that is compared to the
test statistic to determine whether to
reject the null hypothesis. If the
absolutevalueof your test statistic
is greater than the critical value,
you can declare statistical
significance and reject the null
hypothesis.

4. Critical Value (Contd.)


The critical value approach involves determining
"likely" or "unlikely" by determining whether or
not the observed test statistic is more extreme than
would be expected if the null hypothesis were true.
That is, it entails comparing the observed test
statistic to some cut-off value, called the "critical
value." If the test statistic is more extreme than the
critical value, then the null hypothesis is rejected
in favour of the alternative hypothesis. If the test
statistic is not as extreme as the critical value, then
the null hypothesis is not rejected.

4. Critical Value (Contd.)

Right Tailed Curve

Two-Tailed Curve

Left Tailed Curve

5. Decision Making
In hypothesis testing, there are two
ways to determine whether there is
enough evidence from the sample to
reject H0or to fail to reject H0. The
most common way is to compare the
p-value with a pre-specified value of
, where is the probability of
rejecting H0when H0is true.
However, you can also compare the
calculated value of the test statistic

5. Decision Making (Contd.)


Critical Value Approach

1. Plot the value in the graph at given confidence interval.


2. Plot the calculated test statistic value on the same graph.
3. If the calculated test statistic value falls in critical region, we use to
reject the null hypothesis, or vice-versa.

5. Decision Making (Contd.)


P-Value Approach
90

2.5%

80

95%

2.5%

70
60
50
40
30
20
10
0
23.8

28.8

33.8

38.8

43.8

48.8

53.8

58.8

AGE

If our observed age value lies outside the green lines, the probability of getting a value
as extreme as this if the null hypothesis is true is < 5%

5. Decision Making (Contd.)


P-Value Approach
p-value = probability of observing a value more
extreme that actual value observed, if the null
hypothesis is true
The smaller the p-value, the more unlikely the null
hypothesis seems an explanation for the data
Interpretation for the example
If results falls outside green lines, p<0.05,
if it falls inside green lines, p>0.05

Types of Errors in Testing Hypothesis


No study is perfect, there is always the chance for error

- level of significance
PRODUCERS RISK

1- - power of the test


CONSUMERS Risk

Types of Errors in Testing Hypothesis


(Contd.)
=0.05

there is only 5 chance in 100 that the result


termed "significant" could occur by chance
alone

The probability of making a Type I () can be decreased by


altering the level of significance.

it will be more difficult to find a significant result

the power of the test will be decreased


the risk of a Type II error will be increased

Types of Errors in Testing Hypothesis


(Contd.)
The probability of making a Type II () can be
decreased by increasing the level of significance.
it will increase the chance of a Type I error

To which type of error you are willing to risk ?