1 of 14

FACTOR ANALYSIS��PRESENTATION BY-�SAIF S

FMS/MBA/21-23/039��

2 of 14

INTRODUCTION

  • Factor analysis is a technique that is used to reduce a large number of variables into fewer numbers of factors.

​

  • It reduces attribute space from a large no. of variables to a smaller no. of factors

​

  • Factor analysis is a way to condense the data into few variables.

​

​

3 of 14

Operation�

Management Objectives

Customer Objectives

Project Objectives

Implementation Plan

Schedules

Tasks

Resources

4 of 14

OBJECTIVES OF THE PRESENTATION

  • To explain the Methodologies of FA and its approaches.

​

  • To demonstrate its FA’s mechanism.

​

  • How FA enables researchers to investigate concepts that cannot easily be measured directly

​

5 of 14

Objective of Factor Analysis�

MARKET ANALYSIS

TECHNICAL ANALYSIS

FINANCIAL ANALYSIS

ECONOMIC ANALYSIS

PSYCHOLOGICAL

ANALYSIS

Factor analysis has been used to develop things such as perception maps, advanced SWOT analyses, etc..

It is a multivariate statistical technique for data reduction. It has many applications in

Management & Researches

.

FA attempts to simplify complex & diverse relationships that exist among a set of observed variables

FA is a powerful data reduction technique that enables researchers to investigate concepts that cannot easily be measured directly.

To capture some psychological states of customers

6 of 14

PROCESS OF FACTOR ANALYSIS

S 1: Selecting & Measuring a set of variables in a given domain.

S 2: Data screening in order to prepare the correlation matrix.

S 3: Factor Extraction.

S 4: Factor Rotation to increase interpretability.

S 5: Interpretation.

S 6: Validation and Reliability of the measures.

​

7 of 14

Methods of Factor Analysis�

FA

Principal component analysis

Common Factor Analysis

Centroid method

Maximum Likelihood Method

Image Factoring

Rotation method

8 of 14

EXAMPLE WITH THE CASE STUDY

Suppose, a number of supervisors are asked to rate the relevance of six personality characteristics to effective job performance by subordinates. The characteristics assessed are organized, systematic, careless, creative, intellectual, and imaginative.

​

Variable

1

2

3

4

5

6

1.Organized

1.00

 

 

 

 

 

2.Systematic

.72

1.00

 

 

 

 

3.Careless

-.63

-.55

1.00

 

 

 

4.Creative

.00

.00

.00

1.00

 

 

5.Intellectual

.00

.00

.00

.56

1.00

 

6.Imaginative

.00

.00

.00

.48

.42

1.00

Table: Hypothetical Correlation Matrix Observed Variables

9 of 14

Observed Variable

Factor 1

Conscientiousness

Factor 2

Intellect

Communality(h2)

Uniqueness (1-h2)

1.Organized

.90

0.00

.81

.19

2.Systematic

.80

0.00

.64

.36

3.Careless

-.70

0.00

.49

.51

4.Creative

.00

.80

.64

.36

5.Intellectual

.00

.70

.49

.51

6.Imaginative

.00

.60

.36

.64

Sum of squared loadings

1.94

1.49

 

 

Proportion of variance

1.94/6

=.32

1.49/6=.25

.32+.25=.57

1-.57=.43

Table: Factor pattern Matrix with Communalities and Uniqueness for Hypothetical Data

10 of 14

Spss Link With Demonstration�

  1. Principal Component Analysis
  2. Common Factor Analysis

TWO MAIN ANALYSIS

Five Variable listed based on the personality and relationship is analyzed among them.

Correlation among similar variable shows 1 diagonally.

11 of 14

  • Total Variance contains Initial Eigenvalues & 5 variables.

​

  • Variable 1 & 2 shows Eigenvalue more than 1.

​

  • Data reduced from 5 variable to 2.

​

  • % of variance can be seen near 63% which is considered good.

​

  • Sum of Eigenvalues= No of Components

​

  • Two Components can be seen in Component Matrix.

12 of 14

  • Rotated Component Matrix comes into play when there is more than one component.

​

  • As we have two component we can see Rotated Component Matrix

13 of 14

Conclusion�

It helps to make sense of large data with interlinked relationships

.

To determine the extent to which each variable in the dataset is associated with a common theme or factor.

To definitively understand how many factors are needed to explain common themes amongst a given set of variables.

Factor analysis attempts to discover the unexplained factors that influence the co-variation among multiple observations.

To provide an interpretation of the common factors in the dataset

To point out relationships that may not have been obvious

14 of 14

THANK YOU