FACTOR ANALYSIS
OBJECTIVES
1. It is a multivariate data analysis technique of inter dependence type meant chiefly
for the data reduction.
2. In the present study, factor analysis was performed in order to explore the factors
that are considered by the Performance Appraisal in pentagon garments
VALIDITY OF FACTOR ANALYSIS
Before identifying the factors, Bartlett's Test was used to verify whether the
Factor Analysis is valid. Another useful static is the Kaiser Meyer- Oikin (KMO) test of
sampling adequacy. The correlation matrix was examined carefully and the two test namel,
Bartlett’s and KMO test were undertaken to ascertain whether it is valid to perform factor
analysis.
H0: The Factor Analysis is not valid
H1: The Factor Analysis is valid
KMO and Bartlett's Test
Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .703
Bartlett's Test of Sphericity Approx. Chi-Square 322.421
Df 78
Sig. .000
The p- value (0.000) is less than the assumed significance value 0.05; so the null
hypothesis H0 is rejected, the alternate hypothesis H1 is accepted and hence the factor analysis is
valid. Next, the KMO coefficient to cross check bartlett’s test. It can be seen 0.703 is more than
0.5, so this agrees with Bartlett ‘s test that the factor analysis is valid and the sampling adequacy
is sufficient.
Total Variance Explained
Componen Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared
t Loadings Loadings
Tota % of Cumulativ Tota % of Cumulativ Tota % of Cumulativ
l Varianc e% l Varianc e% l Varianc e%
e e e
1 3.74 28.793 28.793 3.74 28.793 28.793 2.58 19.887 19.887
3 3 5
2 1.69 13.043 41.836 1.69 13.043 41.836 1.93 14.864 34.751
6 6 2
3 1.21 9.328 51.164 1.21 9.328 51.164 1.81 13.948 48.699
3 3 3
4 1.07 8.239 59.403 1.07 8.239 59.403 1.39 10.705 59.403
1 1 2
5 .953 7.331 66.735
6 .797 6.128 72.862
7 .756 5.814 78.676
8 .663 5.098 83.775
9 .603 4.639 88.414
10 .537 4.128 92.541
11 .407 3.127 95.669
12 .316 2.434 98.103
13 .247 1.897 100.000
ROTATED COMPONENT MATRIX:
In stage 2 of factor analysis, rotation of principal components is performed
by Varimax Totation method. After initial extraction, the plot has to rotated
(Varimax method) to get a better analysis, In practice, the best results are obtained
by principal component extraction and varimax Totation. The results of varimax
rotation of principal component are presented in the following table. The factor
matrix gives the loading of each variable in relation of each factors. The purpose is
to ascertain variables which have a high loading on a certain factors, but low
loading on the other factor
Rotated Component Matrixa
Component
1 2 3 4
Light sensitive vision .832
Increased heart rate and respiration .747
Muffled hearing
Inability to rest, relax or down
Headaches
Difficulty Communication .760
Change in eating habits .728
Change in activity Performance
Change in sleep patterns .687
Change in Activity levels .671
Feeling uncoordinated
Decreased efficiency and effectiveness .867
Increased sense of humor gallows humor .525
Rotation converged is 13 iterations.
Table exhibits the rotated factor loading for the 13 statements (variables) that
have been reduced to four factors, F1, F2, F3 and F4. These four factors with
suitable names such as given below.
TABLE-1
FACTOR-1: SENSITIVE FACTOR
S. NO Variables Factor Eigen value Percentage
loading variance
1
Light sensitive vision 2.585 19.887
.832
2 Increased heart rate
and respiration .747
Source: result computed through SPSS
The two variables have been loaded on factor-1. The factor is named as sensitive
vision on the basic of loading. The eigen value for the above factor 1 was 2.585
and the percentage variance was 19.887
TABLE-2
FACTOR-2: COMMUNICATION FACTOR
S. NO Variables Factor Eigen value Percentage
loading variance
1
Difficulty 41.836 34.751
.760
Communication
2
Change in eating
.728
habits
Source: result computed through SPSS
The two variables have been loaded on factor-1. The factor is named as
communication on the basic of loading. The eigen value for the above factor 1 was
41.836 and the percentage variance was 34.751
TABLE-3
FACTOR-3: BEHAVIORAL HABITATION
S. NO Variables Factor Eigen value Percentage
loading variance
1
Change in sleep 51.164 48.699
.687
patterns
2
Change in Activity
.671
levels
Source: result computed through SPSS
The two variables have been loaded on factor-1. The factor is named as sleep
patterns on the basic of loading. The eigen value for the above factor 1 was 51.164
and the percentage variance was 48.699
TABLE-4
FACTOR-4: HUMOR FACTOR
S. NO Variables Factor Eigen value Percentage
loading variance
1
Decreased efficiency 59.403 59.403
.867
and effectiveness
2
Increased sense of
.525
humor gallows humor
Source: result computed through SPSS
The two variables have been loaded on factor-1. The factor is named as
effectiveness on the basic of loading. The eigen value for the above factor 1 was
59.403 and the percentage variance was 59.403
OVERALL FACTOR
Factor Name of extracted Selected statement Factor loading
Factor (variable)
Light sensitive vision Sensitive Factor .832
F1
Difficulty .687
F2 COMMUNICATION
Communication
FACTOR
F3 Change in sleep Behavioral .687
patterns
Habitation
F4 Decreased efficiency Humor Factor .867
and effectiveness
It is evident from the table that the statement, the type of private life with
factor loading of .832, Work hours with factor loading of .687, My personal life
with factor loading of .687, My work with factor loading of .867, are the statement
with higher loading factor of F1, F2, F3 and F4 respectively. Therefore, these the
are the identified four variable, which greater influence over the relative factor that
the respondents are mostly facing importance of emotional intelligence of teacher
