Beginners Guide to TikTok for Search - Rachel Pearson - We are Tilt __ Bright...
Data base and research methodology
1. DATA BASE AND RESEARCH METHODOLOGY
Factor Analysis: It is a general name denoting a class of procedures primarily used for data
reduction and summarization. Relationship among set of many interrelated variables are
examined and represented with the help of factor analysis. The approach used in the factor
analysis is “Principle Component Analysis”. In this component analysis, the total variance in
the data is considered. The diagonal of the correlation matrix consists of unities and full
variance is bought in to factor matrix. It determines the minimum number of factors that will
account for maximum variance in the data for use in subsequent multivariate analysis. The
factors are also called principal components. 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. Hence
the variance explained by each factor is redistributed by rotation. The method used for
rotation in this study is “Varimax”. It is a method of factor rotation that minimizes the
numbers of variables with high loading on a factor, thereby enhancing the interpretability of
the factors.
2. TABLE 1: Shows the list of variables along with their description:
VARIABLES DESCRIPTION
X1 Adequate
X2 Tax deduction
X3 Issue of clearance
X4 Schemes
X5 E - filling
X6 Restricted
X7 Honest
X8 Social welfare
X9 Joint filling
X10 Agriculturist
X11 Senior citizen
X12 Liability
Before the application of factor analysis the reliability of scale items were tested by applying
cronbach’s alpha. The value of all factors ranges between 0.81 to 0.91, indicating the
presence of internal consistency. Further to test the sampling, Kaiser-Meyer-Olin measure of
sampling adequacy is computed which is found to be 0.628. It indicates that sample is good
enough for sampling.
3. Total Variance Explained
Extraction Sums of Squared Rotation Sums of Squared
Initial Eigenvalues Loadings Loadings
% of Cumulative % of Cumulative % of Cumulative
Component Total Variance % Total Variance % Total Variance %
1 2.134 17.780 17.780 2.134 17.780 17.780 1.939 16.158 16.158
2 1.512 12.598 30.378 1.512 12.598 30.378 1.444 12.031 28.189
3 1.383 11.527 41.905 1.383 11.527 41.905 1.403 11.695 39.884
4 1.328 11.064 52.968 1.328 11.064 52.968 1.391 11.593 51.477
5 1.092 9.102 62.070 1.092 9.102 62.070 1.271 10.593 62.070
6 .893 7.439 69.509
7 .824 6.864 76.373
8 .765 6.379 82.752
9 .741 6.175 88.926
10 .518 4.313 93.239
11 .485 4.041 97.280
12 .326 2.720 100.000
Extraction Method: Principal Component Analysis
It is observed from table that only 5 factors has Eigen value more than one, so accordingly
we preceded with these factors. The total variance explained by factor 1, 2, 3, 4 and 5 is
16.158, 12.031, 11.695, 11.593, 10.593, 62.070 percent of variance, whereas the cumulative
variance explained by all these factors is 62.070 percent and rest of the variance is due to
the factors which are beyond the scope of the study.
Rotation Method: Varimax with Kaiser Normalization. a Rotation converged in 11 iterations.
The table 3 shows that each statement corresponding to the highlighted factor loading is
correlated with the factor corresponding to that factor loading. Higher the factor loading,
stronger is the correlation between the factors and statement. On the basis of rotated
component matrix the factor extraction table has been prepared which is as:
4. Rotated Component Matrixa
Component
1 2 3 4 5
x1 .048 .371 .155 .748 .043
x2 -.182 .008 .661 -.262 .154
x3 .552 -.026 .321 .091 -.083
x4 -.043 -.093 -.199 .692 .074
x5 .138 .040 .676 .024 -.196
x6 -.152 -.143 -.115 .112 .760
x7 .206 -.207 .568 .471 .048
x8 -.260 -.142 -.054 -.020 -.674
x9 -.095 .826 -.022 -.058 .208
x10 .838 .105 -.044 -.076 .097
x11 .842 -.047 -.041 .053 .027
x12 .157 .719 -.026 .171 -.329
The below table 4 stated factors are in the order of degree of importance i.e. factor 1 is more
important than factor 2; factor 2 is more important than factor 3 and so on. The factor 1 and 2
has 16.158%, and 12.031%of variance which is the highest variance as compared with factor
3, 4, and 5 where % of variance is 11.695, 11.593, and 10.593. Hence it is found that issue of
clearance, age of senior citizen and agriculturist brought under tax shows high variance as
compare to other factors.
5. Extraction Method: Principal Component Analysis
TABLE 4: ROTATED COMPONENT MATRIX
FACTORS % OF VARIANCE FACTOR VARIABLES INCLUDED LOADING
INTERPRETATION IN FACTOR
F1 16.158 Issue of clearance clearance x3 .552
,agriculturist Agriculturist x10 .838
brought under tax, Citizen x11 .842
liability of tax,
senior citizen
F2 12.031 While calculating liability x12 .719
tax liability and joint filling x9 .826
joint filling married
couple.
F3 11.695 Honesty tax payers Honest x7 .568
and tax deduction Tax deduction x2 .661
help in tax
reducing.
F4 11.593 Link with social Social welfare x8 -.020
welfare, schemes Schemes x4 .692
role to reducing the Adequate x1 .748
evasion and tax
payers program are
adequate in India
F5 10.593 e-filling should not Restricted x6 .760
restricted