Scribd
Upload
200 views

Class Factor Analysis

The document provides an overview of factor analysis, including its uses, associated statistics, and how to conduct a factor analysis. It discusses using factor analysis for data reduction, identifying underlying dimensions, and replacing original variables with fewer derived variables. The key steps outlined are determining the method, extracting factors, rotating factors, interpreting results, calculating factor scores, selecting surrogate variables, and determining model fit.

Uploaded by

rahul
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
200 views

Class Factor Analysis

The document provides an overview of factor analysis, including its uses, associated statistics, and how to conduct a factor analysis. It discusses using factor analysis for data reduction, identifying underlying dimensions, and replacing original variables with fewer derived variables. The key steps outlined are determining the method, extracting factors, rotating factors, interpreting results, calculating factor scores, selecting surrogate variables, and determining model fit.

Uploaded by

rahul
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 21

19-1

Presentation on Factor Analysis


Content

1) Factor Analysis
2) Use and application
3) Statistics Associated with Factor Analysis
4) Conducting Factor Analysis
5) Applications of Common Factor Analysis
6) Example: Life Insurance
19-3

Factor Analysis
 Factor analysis:For data reduction and summarization.
 Factor analysis:Interdependence technique: No distinction between dependent and
independent variables.

 Factor analysis is used in the following circumstances:


 To identify underlying dimensions or factors.

 To identify a new, smaller, set of uncorrelated variables to replace…. (Reg. &DA)

 For MA:a smaller set of salient variables from a larger set.


19-4

Application in Market Research

Market segmentation : Economy , Performance,


Comfort.

Product design:Brand attributes.

Pricing studies: Characteristics of price sensitive


customer.
Statistics Associated with Factor 19-5

Analysis
 Bartlett's test of sphericity: Identity matirx
 Correlation matrix.
 Communality.
 Eigenvalue.
 Factor loadings..
 Factor loading plot. A factor loading plot is a plot
of the original variables using the factor loadings as
coordinates.
 Factor matrix. Loadings of all the variables on all the
factors extracted.
 Factor scores:Composite scores-- on derived factors.
Statistics Associated with Factor 19-6

Analysis
 Kaiser-Meyer-Olkin (KMO) measure of
sampling adequacy. An index used to
examine the appropriateness of factor
analysis.
 Percentage of variance. The
percentage of the total variance attributed
to each factor.
 Residuals .
 Scree plot. Eigenvalues Vs. number of
factors in order of extraction.
19-7

Conducting Factor Analysis


Problem formulation
Varia.&SS

Construction of the Correlation Matrix

After 2 tests-Method of Factor Analysis

Determination of Number of Factors

Rotation of Factors

Interpretation of Factors

Calculation of Selection of
Factor Scores Surrogate Variables

Determination of Model Fit


19-8
Conducting Factor Analysis
Determine the Method of Factor Analysis
 In principal components analysis,
(1)The total variance in the data is considered.
(2) PCA is recommended .
when the primary concern is to determine the minimum
number of factors that will account for maximum variance
in the data for use in subsequent multivariate analysis.

 In common factor analysis:


(1)The factors are estimated based only on the
common variance.
(2) Communalities are inserted in the diagonal of the
correlation matrix.
(3) This method is appropriate when the primary
concern is to identify the underlying dimensions and the
common variance is of interest.
Determination of Number of 19-9

Factors

Smaller no of factors : To Summarize the


information.
How many
1. A priori: researcher knowledge.
2. Determination based on eigenvalue:- More than
1.
3. Determination based on % of variance:at least
60%
4. Determination based on Split-Half
Reliability:Only factors with high
correspondence of factor loading across the two
sub sample are retained.
Determination of Number of 19-10

Factors
5. Determination based on scree plot :. Factors Eigenvalue
1 2.731
3 2 2.218
E
I
3 .442
G 4 .341
E 5 .183
N
1.5 6 .085
V
A
L
U

E 0
1 2 3 4 5 6
Component number
Results of Principal Components 19-11

Analysis

Amount of variance a variable shares.

Communalities
Variables I nit
Total variance associated with the factor

V1 1.0
I nitial Eigen values
V2 1.0
V3 1.0
Results of Principal Components 19-12

Analysis

Extraction Sums of
Contains F Ls of all the variables on all the factors
extracted

Factor Matrix
Factor Eigen value
1
Variables 2.731
Fa
2 2.218
V1
19-13

Rotate factor
•Rotation: Factor matrix is transformed into simple one that
is easier to interpret
•Rotation does not effect communalities and % of total
variance.
•Types of rotation:
Orthogonal:
Varimax- minimize no of variables with high loading on
a factor
Oblique:
•Rotation changes % of variance accounted by each
factor.

Rotation Sums of Sq
Conducting Factor Analysis
Interpret Factors

(1) A factor can then be interpreted in


terms of the variables that load high
on it.
(2)Another useful aid in interpretation
is to plot the variables
Results of Principal Components 19-15

Analysis
V1-Prevents cavity
V2-Shiny teeth

Rotated Factor
V3-Strengthen gums
V4-Freshens breath
V5-Prevention of tooth
decay is not an
important thing.
V6-Attractive teeth
Variables Fa
Factor
V1 Score C
V2
Variables
V3
19-16
Conducting Factor Analysis
Interpret Factors
 (1)A factor can then be interpreted in terms of
the variables that load high on it.

 (2)Another useful aid in interpretation is to plot


the variables
Plot
19-17

Component Plot in Rotated


Space Component 1

1.0 V4 ∗∗ ∗ V6
V2

Component 2
0.5

0.0
V1∗
∗ V5 V3∗
-0.5

-1.0

1.0 0.5 0.0 -0.5 -1.0


19-18
Conducting Factor Analysis
Calculate Factor Scores

The factor scores for the i th factor may be


estimated
as follows:
 
Fi = Wi1 X1 + Wi2 X2 + Wi3 X3 + . . . + Wik Xk

Fi = estimate of ith factor


Wi = factor score coefficient
Xi = ith standard variable.
Results of Principal Components 19-19

Analysis
The lower left triangle contains the reproduced
correlation matrix; the diagonal, the communalities;
the upper right triangle, the residuals between the
observed correlations and the reproduced
correlations.

Facto
Variables V1
19-20
Conducting Factor Analysis
Select Surrogate Variables
 Selection of S/S variable, involves singling out some
of the original variables for use in subsequent analysis
& interpret the result in terms of original variables
rather than factor scores.
 By examining the factor matrix, one could select for
each factor the variable with the highest loading on
that factor. That variable could then be used as a
surrogate variable for the associated factor.
 However, the choice is not as easy if two or more
variables have similarly high loadings. In such a case,
the choice between these variables should be based
on theoretical and measurement considerations.
19-21
Conducting Factor Analysis
Determine the Model Fit

 If there are many large residuals, the factor


model dies not provide a good fit to the data
and the model should be reconsidered .

You might also like