FACTOR ANALYSIS

Factor Analysis
• Factor analysis is a general name denoting
a class of procedures primarily used for
data reduction and summarization.
• Factor analysis is an interdependence
technique in that an entire set of
interdependent relationships is examined
without making the distinction between
dependent and independent variables.
• Metric data
Background
• Factor analysis is a data reduction
technique
• Used when variables are many
• And correlated
• No point when variables are
uncorrelated
Factor Analysis
Also known as PRINCIPAL COMPONENT ANALYSIS

Objective is DATA REDUCTION, and DATA

SUMMARIZATION

To analyze the underlying ‘structure’ in a given

data set (or a set of variables)

To reduce the number of variables

To group similar (or correlated) variables

• Lots of correlated variables are there

• After FA, unmanageable no. of variables gets reduced to a few
manageable factors
Managerial applications
• Scale construction- used to develop concise
multiple item scales for measuring various
constructs. Ex . Job satisfaction.
• Establish antecedents- ex safety clause in a
mutual fund.
• Psychographic profiling- to identify personality
type.
• Segmentation analysis –Marketing Studies- new
product development, product acceptance
research .ex. Identify the characteristics of price-
sensitive customers.
Steps in FA

• Formulate the problem

• Collect data, enter them
• Subject them to FA using SPSS/SAS/Minitab
• Extract the factors
• Rotate the factors, if necessary
• Name the factors
 Conducting Factor Analysis
Formulate the Problem
• The objectives of factor analysis should be identified.

• The variables to be included in the factor analysis

should be specified based on past research, theory,
and judgment of the researcher. It is important that
the variables be appropriately measured on an
interval or ratio scale.

• An appropriate sample size should be used. As a

rough guideline, there should be at least four or five
times as many observations (sample size) as there
are variables.
Conducting Factor Analysis
Construct the Correlation Matrix

• The analytical process is based on a matrix of correlations between the

variables- Correlation matrix
• Bartlett's test of sphericity can be used to test the null hypothesis that
the variables are uncorrelated in the population. To test whether the
correlations among the variables is adequate (and significant) –
significance should be <0.05).
• Another useful statistic is the Kaiser-Meyer-Olkin (KMO) measure of
sampling adequacy. Small values of the KMO statistic indicate that the
correlations between pairs of variables cannot be explained by other
variables and that factor analysis may not be appropriate. (should be
>0.50). Values below 0.5 imply that factor analysis may not be
appropriate.
Statistics Associated with Factor Analysis
• Communality. Communality is the amount of variance a variable shares
with all the other variables being considered. This is also the proportion of
variance explained by the common factors.
• Eigenvalue. The eigenvalue represents the total variance explained by each
factor.
• Factor loadings. Factor loadings are simple correlations between the
variables and the factors.
• Factor matrix. A factor matrix contains the factor loadings of all the
variables on all the factors extracted.
• Factor scores. Factor scores are composite scores estimated for each
respondent on the derived factors.
• Percentage of variance. The percentage of the total variance attributed to
each factor.
• Scree plot. A scree plot is a plot of the Eigenvalues against the number of
factors in order of extraction.
Conducting Factor Analysis
Extraction of factor actors

• In principal components analysis, the total variance in

the data is considered. The diagonal of the correlation
matrix consists of unities, and full variance is brought
into the factor matrix.
• Determines the minimum number of factors that will
account for maximum variance in the data for use in
subsequent multivariate analysis. The factors are called
principal components.
• The first factor explains the largest variance and is
called first principal factor
Statistics Associated with Factor Analysis

• No: of factors to be extracted:

1. Based on theory
2. Based on eigen value ( eigen value should be at
least 1)
3. Scree plot
4. Percentage of variance explained
Conducting Factor Analysis
Determine the Number of Factors
• A Priori Determination. Sometimes, because of prior
knowledge, the researcher knows how many factors to expect
and thus can specify the number of factors to be extracted
beforehand.
Determination Based on Eigenvalues. In this approach, only
factors with Eigenvalues greater than 1.0 are retained. An
Eigenvalue represents the amount of variance associated with
the factor. Hence, only factors with a variance greater than 1.0
are included. Factors with variance less than 1.0 are no better
than a single variable, since, due to standardization, each
variable has a variance of 1.0. If the number of variables is less
than 20, this approach will result in a conservative number of
factors.
Conducting Factor Analysis
Determine the Number of Factors
• Determination Based on Scree Plot. A scree plot is a plot of
the Eigenvalues against the number of factors in order of
extraction. Experimental evidence indicates that the point at
which the scree begins denotes the true number of factors.
Generally, the number of factors determined by a scree plot
will be one or a few more than that determined by the
Eigenvalue criterion.

• Determination Based on Percentage of Variance. In this

approach the number of factors extracted is determined so
that the cumulative percentage of variance extracted by the
factors reaches a satisfactory level. It is recommended that the
factors extracted should account for at least 60% of the
variance.
 Scree Plot
3.0
Fig. 19.3

2.5

2.0
Eigenvalue

1.5

1.0

0.5
0.0

1 2 3 4 5 6
Component Number
Case Analysis 16.1

A study was carried out to understand and

analyse the investment behaviour of the
employees of public sector units and
governments. A sample of 80 respondents were
drawn. The level of agreement or disagreement
on the following parameters risk awareness,
returns, insurance cover, tax rebate, maturity
time, credibility of the financial institution and
easy accessibility while making investment were
asked on five point likert scale.
Metric data
No: of variables= 7
Sample size= 80 is greater than 7*4= 28

KMO is 0.591 and thus factor analysis can be used for the
data set
Bartlett test of sphericity is significant as the p value is
0.000 which is less than 0.05 level of significance and thus
the variables are highly correlated
SCREE PLOT
Factor loadings and
computation of eigen values a
Component Matrix

Component

1 2

Score on Risk Averseness -.176 .753

Score on Returns .527 .160
Score on Insurance Covers .335 -.707
Score on Tax Rebate .309 .125
Score on Maturity Time .765 -.198
Score on Credibility of
.570 .633
Financial Institution
Score on Easy Accessibility .793 .047

Extraction Method: Principal Component Analysis.

a. 2 components extracted.

• The correlation coefficient between the factors score and the variables
included in the study is called factor loading (factor matrix/ component
matrix)
• Eigen value of factor 1 = (-.176)2 +(.527)2+(.335)2+(,309)2+(.765)2+(.570)2+
(.793)2 =2.054
• Eigen vlaue of factor 2= (-.753)2 +(.160)2+(-.707)2+(.125)2+(-.198)2+
 Total variance accounted by
the extracted factors
Total Variance Explained

Component Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 2.054 29.346 29.346 2.054 29.346 29.346 2.010 28.708 28.708
2 1.551 22.160 51.506 1.551 22.160 51.506 1.596 22.798 51.506
3 .970 13.857 65.363
4 .848 12.109 77.472
5 .711 10.151 87.622
6 .490 7.003 94.626
7 .376 5.374 100.000
Extraction Method: Principal Component Analysis.

• The percentage of variance explained by each of the factor can

be computed using the eigenvalues.
• 29.346 percentage of variance explained by factor 1
• 22.16 percentage of variance explained by factor 2
• 51.506 total variance explained by both factors
Communality
Communalities

Initial Extraction
Score on Risk Averseness 1.000 .598
Score on Returns 1.000 .304
Score on Insurance Covers 1.000 .612
Score on Tax Rebate 1.000 .111
Score on Maturity Time 1.000 .624
Score on Credibility of
1.000 .725
Financial Institution
Score on Easy Accessibility 1.000 .631

Extraction Method: Principal Component Analysis.

• The communality of the first variable is 0.598 which means

59.8 per cent of the variance of the first variable (risk
awareness) is explained by the two factors. Similarly
communalities for the other variable s could be computed.
 Conducting Factor Analysis
Rotate Factors

• Although the initial or unrotated factor matrix indicates the

relationship between the factors and individual variables, it
seldom results in factors that can be interpreted, because the
factors are correlated with many variables. Therefore, through
rotation the factor matrix is transformed into a simpler one that
is easier to interpret.
• In rotating the factors, we would like each factor to have
nonzero, or significant, loadings or coefficients for only some of
the variables. Likewise, we would like each variable to have
nonzero or significant loadings with only a few factors, if
possible with only one.
• The rotation is called orthogonal rotation if the axes are
maintained at right angles.
Conducting Factor Analysis
Rotate Factors
• The most commonly used method for rotation
is the varimax procedure. This is an
orthogonal method of rotation that minimizes
the number of variables with high loadings on
a factor, thereby enhancing the interpretability
of the factors. Orthogonal rotation results in
factors that are uncorrelated. .
Rotation of factors
• Cut off point generally taken above 0.5
• A variable which appears in one factor does
not appear in other
• Refer rotated component matrix in the spss
output
 Rotation of factors
a
Rotated Component Matrix

Component
1 2
Score on Risk Averseness .057 -.771
Score on Returns .551 .004
Score on Insurance Covers .109 .775
Score on Tax Rebate .332 -.027
Score on Maturity Time .671 .417
Score on Credibility of
.732 -.435
Financial Institution
Score on Easy Accessibility .771 .192
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 3 iterations.
Labelling or Naming the factors

• Using 0.7as cut-off point the two variables

corresponding to factor 1 having a factor
loading above 0.7 are credibility of the
financial institution and ease of
accessibility. The variables corresponding
to factor 2 are risk awareness and
insurance cover.
• A variable which appears in one factor
does not appear in other.
• Naming these factors
• Factor 1 could be named as Perceived value of service and
factor 2 could be named as Security factor.
• Ex 16.11(aerated software drinks)
• Ex.16.22 (Purchase of B segment cars)