Research Methods

Problem Definition
&
Theoretical Framework

Problem Discovery and Definition

First

step
Problem, opportunity, or monitor operations
Discovery before definition
Problem means management problem

PROBLEM DEFINITION (applied

research)

Problem : Situation where gap exists b/w actual

and the desired ideal state
Any undesired situation
Well-defined problem is half solved symptoms are
not the real problems.
From interview & literature review researcher is in
the position to narrow down the problem & define it
more precisely from broad base. Problem should be
unambiguously stated to conduct further research.
Not necessarily it is situation that requires
immediate solution.

The formulation of
the problem is often
more essential than its
solution.
Albert Einstein

Problem
Definition
indication
of a specific business decision

The

area that will be clarified by answering some

research questions.

Defining Problem Results in

Clear Cut Research Objectives
Symptom Detection
Analysis of
the Situation
Problem Definition
Statement of
Research Objectives

Exploratory
Research
(Optional)

Determine the Relevant

Variable
Anything

that may assume different

numerical values.
A variable is any thing that can take different
values. Eg. Age, Income, Death rate etc there
are 05 types of variables .

Types of Variables
1.
2.
3.
4.
5.

Dependent
Independent
Moderating
Intervening
Extraneous

Types of Variables
Dependent

Variable-DV-(Criterion
Variable): It is the basic issue of
interest. The real problem to be solved
and the core area of research. Goal of
researcher is to predict and explain
variability in dependent variable

The

Outcomes of a Research Study

Depends on the experimental
treatment
Eg

Sales, employees turnover, Age etc

Types of Variables

Independent IV- (Predictor Variable): It is the variable

that influences the dependent variable in either positive
or negative way. When independent variable is present
the dependent variable is also present. And with each
unit change there is change in dependent variable.
Treatments or conditions under control of the
researcher
Levelsat least two different values of the IV must be
present
Example: Success of new product depends on advertising
campaign.

dependent Variable

Independent variable

Types of Variables

Moderating Variable-MV: People also call it second

independent variable. A variable that has a strong
contingent (compounding) effect on the Dependent-Independent relationship. That is; presence of third
variable (moderating) modifies the originally expected
relationship b/w independent & dependent variable
If we assume that students performance is dependent
on the amount of effort they exert, and teaching
competence of instructor has also an effect then
:Skilled Teacher (MV)

Types of Variables

Intervening Variable: The factor that

theoretically affects the observed phenomenon,
but cannot be seen, measured or manipulated.
Its effects must be inferred from the effects of
independent and moderating variables on the
observed phenomenon.
This Variable appears between the time
independent variables operate to influence the
dependent variable. Intervening variable
appears as a function of independent variable
(s) operating in a situation.
If it is believed that diverse workforce
contributes to the org effectiveness that in
result increases creative synergy then:

Theoretical Framework & Hypothesis

t1---------------------t2-----------------------t3

Workforce
Diversity

Creative
synergy

Org.
effectiven
ess

Types of Variables
Relationship

Creative
synergy
IVV

Workforce
Diversity
IV
Managerial
expertise
MV

Org.
effectiveness
DV

Types of Variables

Extraneous Variables: Infinite number of

variables that have no or little impact on the
situation can be safely ignored ( or controlled) as
they have random impact. Some of these can be
treated as independent or moderating variables
but most of them can be ignored or excluded from
the study. For example imposition of sales tax,
local elections etc.
However certain extraneous variable might look
important and can be controlled for example
nature of work in a study.

Types of Variables

In routine office work (control extraneous), the introduction

of four-day workweek (IV) will lead to improve productivity
per worker per week (DV) especially among young workers
(MV) by increasing job satisfaction (IVV).

Job
Satisfaction
(IVV)

Four-day
workweek
(IV)

Age
(MV)

Productivity
(DV)

VARIABLESA SUMMARY
Type of
Variable
Dependent

Independent

Definition

A variable that is measured to see whether the treatment or

manipulation of the independent variable had an effect
A variable that is manipulated to examine its impact on a
dependent variable

Other Terms You

Might See
Outcome

variable
Results variable
Criterion variable
Treatment
Factor
Predictor

variable

Extraneous

A variable that is related to the dependent variable or

independent variable that is not part of the experiment

Threatening

Moderator

A variable that is related to the dependent variable or

independent variable and has an impact on the dependent
variable

Interacting

variable

variable

Theories
Theories are nets cast to catch what we call
the world: to rationalize, to explain, and to
master it. We endeavor to make the mesh
ever finer and finer.
Karl R. Popper

Theory
A

set of systematically interrelated

concepts, definitions and propositions
that are advanced to explain and predict
phenomenon (facts).
A coherent set of general propositions
used as principles of explanation of the
apparent relationships of certain
observed phenomena.

Two Purposes Of Theory

Prediction
Understanding

Concept (or Construct)

A

generalized idea about a class of objects,

attributes, occurrences, or processes that has
been given a name
Construct is a specially developed term for a
particular research study.
leadership, productivity, and morale
gross national product, asset, and
inflation Chiselers, Rate busters

Proposition
Statement

about concepts that may be

judged as true or false if it refers to
observable phenomena.

When

a preposition is formulated for

empirical testing it is called hypothesis.

Scientific Business
Researchers Operate at Two
Levels

Abstract

level

concepts
propositions

Empirical

level

variables
hypotheses

Definitions
Abstract

level -In theory development, the

level of knowledge expressing a concept that
exists only as an idea or a quality apart from
an object.
Empirical level -Level of knowledge
reflecting that which is verifiable by
experience or observation.

Theories
Propositions
Concepts
Observation of objects
and events (reality )

Increasingly more abstract

Theory Building A Process Of

Increasing Abstraction

Theoretical Framework.
It

is a logically developed, described and

elaborated network of associations among
variables that have been identified through
interviews, observation and literature survey.

Theoretical Framework & Hypothesis

1.
2.
3.

4.

5.

Following five basic elements/features should be

found in a theoretical framework:
Variables should be clearly identified
How related are variables with each other
Discuss whether the relationship would be positive
or negative in nature.
Clear explanation that why we would expect these
relations to exist.
A schematic diagram of the framework so that
reader can visualize the relationships.

Theoretical Framework & Hypothesis

Relationship

Performance
(Grade) (DV)

Students
effort (IV)
Skilled
Teacher
(MV)

Hypothesis
An

unproven proposition
A possible solution to a problem
Guess

Hypothesis Development

Hypothesis: when a proposition (statement about

concepts) is formulated for empirical testing it is called
hypothesis. As a declarative statement, a hypothesis
is of a tentative and conjectural in nature. It is a
statement in which we assign variables to cases ( a
case is an entity or thing the hypothesis talks about).
(William Emory& Cooper)
Logically conjectured relationship b/w two or more
variables expressed in the form of a testable
statement. Results of these tests give clues as to what
could be changed in the situation to solve the problem.
Using statistical tools we check our hypothesis.

Hypothesis Development
Hypothesis
Descriptive

Relational

Correlation

Causal

Hypothesis Development
Descriptive

Hypothesis: these are

statements that typically state the existence,
size, form or distribution of some variable.
Example; Current unemployment rate is 12%
in Pakistan.
or
Local governments are facing budget deficit.

Hypothesis Development
Relational

Hypothesis: These are the

statements that describe relationship
between two or more variables with respect
to some case.
For example; Foreign cars are perceived by
the consumers to be of better quality then the
domestic cars.

Hypothesis Development
Correlational Relationship: States merely
that the variables occur together in some
specified manner without implying that one
causes the other.
We use these when we dont have sufficient
evidence to claim a strong causal relationship.
Eg.
Are smoking, chewing tobacco and drinking
related with cancer.

Hypothesis Development
Causal

or Explanatory Hypothesis: In
these hypotheses there is an implication that
the existence of, or change in one variable
(IV) causes or leads to an effect on the other
variable (DV).
An increase in advertising leads to sales
increase.
An increase in family income results in
increase of disposable income.

Hypothesis Development

Directional Hypothesis:
If in stating a
relationship b/w two variables or comparing two
groups terms such as >, <, +ve. Or ve are used
that is a direction has been shown
The greater the job stress, the lower the job
satisfaction.
H0: P>50
H1: P<50
These are also called one tail tests.

Hypothesis Development
Non-directional

Hypothesis: these
hypotheses do tell a relationship or difference
between variables bur dont indicate direction
as > or <. Also called two tailed tests.
Eg. There is a difference between the
performance of boys and girls.
H0:
1=2
H1:
1=2

Hypothesis Development

Null Hypothesis: it is the hypothesis, which is

checked for possible rejection or nullification under
the assumption that it is true. it states that population
correlation between two variables is equal to zero or
that the difference between two means is zero or
some definite number. States that there is no
relationship between the independent and
dependent variables under study
Ho : 1 = 2

Ho: Null hypothesis

1: Theoretical average of population 1
2: Theoretical average of population 2

Alternative Hypothesis
(the research hypothesis)
Opposite

of the null hypothesis; states a

relationship between two variables or
difference between two groups. It is
researchers hypothesis.

statement of inequality

Alternative Hypothesis
(the research hypothesis)
A

relationship exists between the

independent and dependent variables

H1: X1 X2
H1: Research hypothesis
X1: Theoretical average of population 1
X2: Theoretical average of population 2

Hypothesis Development

Type I error: Rejecting true null hypothesis when it is

actually true.
Type II error: Accepting H0 when H1 is true.
Level of significance: of a test is the maximum
probability of committing type-I error.
Level of confidence:
Probability of accepting
true null hypothesis.

If you do not know where you are going,

any road will take you there.

DIRECTIONAL VS. NONDIRECTIONAL

RESEARCH HYPOTHESES

Nondirectional Research Hypothesis

Groups are different, but direction is not specified

H1: X1

X2

Directional Research Hypothesis

Groups are different, and direction is specified

H1: X1 > X2

H1: X1<

X2

PURPOSE OF RESEARCH
HYPOTHESIS
Directly

tested during research process

To compare against Null hypothesis

DIFFERENCES BETWEEN NULL

AND
RESEARCH
HYPOTHESES
Null
Research

Equality between
variables
Refers to population
Indirectly tested
Stated using Greek
symbols ()
Implied

Inequality between
variables
Refers to sample
Directly tested
Stated using Roman
symbols ( )
X
Explicit

WHAT MAKES A GOOD

HYPOTHESIS?

Stated in declarative form

Posits a relationship between variables
Reflects theory or literature
Brief and to the point
Testable

SAMPLES AND POPULATIONS

The

SAMPLE is a representative portion of a

POPULATION
The POPULATION is the entire group of
interest
Results from the SAMPLE should generalize
to the POPULATION

SIGNIFICANCE
Observed

differences (PROBABLY) result

from the treatment and not from chance
Why?
Influences

other than the treatment

Significance

level = risk associated with not

being 100% certain that Null hypothesis is
incorrect

Hypothesis Development
Tests of Significance

Parametric Tests
(More powerful as data are
Derived from ratio and interval scales)
Z distribution
t distribution
F Test

Non-Parametric Tests
(nominal and ordinal data)
Chi-Square tests
Mann-Whitney Test

CRITERIA FOR JUDGING A

Is the review of previous research complete and recent?
RESEARCH
STUDY
Are the problem and purpose clearly stated?

Are the research hypotheses clearly stated?

Is it clear how the study was conducted?
Was the sample representative of the population?
Are the results and discussion relevant to the statement of problem
and purpose?
Are the references complete and current?
Do you have any criticisms of either the content or style?