7/9/2024

Type of Variables

Types of Variables (Causal Model)

General Variables
• Independent/change variable/Predictor/antecedent variable
• Dependent/outcome variable/Criterion/ outcome variable
Third variables
• Moderating Variable
• Mediating Variable (is also known as Intervening variable)
• Confounding Variable are extraneous variables (it influence
both the IV and DV). This variable may create false impression
of a relationship by being related to both the IV and DV.

1
 7/9/2024

What is the need for Third Variable

The third variable could be:
• Moderator and Mediator
Researchers focus only on direct relationship and ignore mediating or
moderating effect completely. This can heavily bias the interpretation
of the result when a variable has no direct effect because its effect is
mediated by another variable.

Mediating Variable
Mediating variable is also known as Intervening Variable:
Research Area: Employee stress level
Hypothesis: Work-life balance programs reduce employee stress, which
in turn increases productivity.

Mediator
• Work life • Increased
balance • Reduced Productivity
Stress

Independent dependent

2
 7/9/2024

Examples
Example:
In a study examining the effect of training programs on employee
performance. It is found in research that the training program increases
motivation, which in turn improves performance.

Draw conceptual model

Moderating variable
A moderating variable influences the strength or direction of the relationship
between an independent variable (IV) and a dependent variable (DV). The
main aim is to understand the conditions under which the IV-DV relationship
changes.
• Moderating variable help us understanding Contextual Influences: How
situational factors affect relationships.
• Moderating variable also help Improving Theory and Models: Refine
theoretical models with boundary conditions.
• It also help Identifying Interaction Effects: Find where the IV-DV
relationship varies.
• Tailoring Interventions: Design effective interventions targeting specific
conditions.

3
 7/9/2024

Moderating variable
How to Use Moderating Variables.
1.Identify Potential Moderators:
• Identification of moderator will be made based on theory or empirical
observations.
• For instance, Research Question: How does Job satisfaction as a
moderator between motivation and performance.Job
satisfaction

Motivation Employee
performance

Moderating variable
2.Formulate Hypotheses:
Specify how the moderating variable will influence the IV-DV
relationship.
Example of Hypotheses:
H1: Higher motivation leads to higher performance.
H2: Relationship is stronger with high job satisfaction.

4
 7/9/2024

Confounding Variable
A confounding variable is an extraneous factor that is related to both the
independent and dependent variables, potentially distorting the true
relationship between them. Identifying and controlling for confounding
variables is crucial to ensure the accuracy and validity of research findings.

Direct Effect: Exercise might lead to weight

loss.
Confounding Effect: Diet is related to both exercise and weight loss. People
who exercise might also follow a healthy diet, which independently
contributes to weight loss.

Moderating variable
When to use moderator:
1. Researcher wants to assess whether two variables have the same relation across groups.
2. The relationship between IV and DV depends on the value of the moderator (Z). If the relation between IV
and DV is different at different values of Z, then Z is a moderating variable.
3. There is an unexpectedly weak or inconsistent relation between an IV and DV across studies (Baron &
Kenny, 1986; Frazier et al., 2004). The moderator either strengthens or weakens the relationship.
How to Identify Potential Moderators?
• Inconsistent findings from the literature about the effect of the same antecedent (IV) on the outcome (DV)
can also be a strong case for testing a moderator.
• Discussion with experts in the same field and key informants in the relevant industry can be another useful
technique to brainstorm and identify the potential moderators.
• Attending the right conferences is also pivotal to discussing with and learning from the informed experts and
delegates.
• To explore and propose potential moderating effect when a contextual variable is found pertinent but has
not been empirically tested in the same field of study.

10

5
 7/9/2024

Moderating variable
Hypothesize a Moderating Relationship Andersson et al. suggest the
following steps to Conceptualize/Hypothesize a Moderating
Relationship.
1. Identify the theory or theories that are used to explain the direct
and moderating effects.
2. Apply the selected theory to the research question and explain the
direct effect and the mechanisms behind it.
3. Provide a theoretical justification for the choice of moderator
variable.

11

Moderating variable
4. Explain the direct effect, if any, of the moderator variable on the
dependent variable so that it is clear how this direct effect differs from
the interaction effect.
5. Explain how the interaction changes the mechanisms that explain
the direct relationship.
6. Theoretically rule out the reverse interaction in which the X (IV) is
moderating the relationship between the moderating variable Z and Y
(DV).
7. Return to theory when interpreting the results and explain them
from a theoretical viewpoint.

12

6
 7/9/2024

Example of Moderation
Example 1.
Relationship between free time and social media usage.
• For younger individuals, free time will lead to more usage of social
media. However, this might not be true for older people. Thus, age
moderate relationship between free time and social media usage.

Age

Social
Free time Media
Usage

13

Example of Moderation
Example 2.
• A teacher researcher may not be merely interested in knowing
whether a new instructional method leads to a better learning
outcome. But also, the application of parental involvement in the
relationship of IV and DV.

Parental
Involvement

New Better
Instructional Learning
Method

14

7
 7/9/2024

Example of Moderation
Example 3:
The relationship between customer satisfaction and customer loyalty may
not be the same for all customers but may differ depending on moderators
such as income, age, or switching costs. As such, moderation can (and
should) be viewed as a means of accounting for heterogeneity in the data.

Income or
age or
switching
cost

Customer Customer
Satisfaction Loyalty

15