Scribd
Upload
27 views4 pages

Factor Analysis 1. For Manifest Variables (OP1, OP2, ......., OP6) Correlation Matrix

The document discusses factor analysis conducted on 6 manifest variables. It is determined that: 1) There is significant correlation between the variables to proceed with analysis. 2) Two factors were extracted explaining 65.3% of variability. 3) Factor 1 relates to variables OP2, OP4, OP6 and factor 2 relates to OP1, OP3, OP5. 4) The factor analysis model shows agegp3 and tlifesat significantly impact the factor model while education and sex do not.

Uploaded by

Akshit Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
27 views4 pages

Factor Analysis 1. For Manifest Variables (OP1, OP2, ......., OP6) Correlation Matrix

The document discusses factor analysis conducted on 6 manifest variables. It is determined that: 1) There is significant correlation between the variables to proceed with analysis. 2) Two factors were extracted explaining 65.3% of variability. 3) Factor 1 relates to variables OP2, OP4, OP6 and factor 2 relates to OP1, OP3, OP5. 4) The factor analysis model shows agegp3 and tlifesat significantly impact the factor model while education and sex do not.

Uploaded by

Akshit Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

FACTOR ANALYSIS

1. For manifest variables (OP1, OP2, ......., OP6)


A)
Correlation
Matrixa

a.
Determinant =
.171

As the value of determinant is 0.171 which is more than 0.00001, we can conclude that there
is a significant correlation in variables and we can proceed further.

As KMO test result is more than 0.6, so the sampling is adequate and we are progressing in
the correct way for the analysis and also Significance (P-value) is 0.001 which is less than
0.05, so the model is right to proceed.

 At least 1 significant correlation between 2 of our variables.


 A total of 2 factors have been extracted from 6 variables(op1-op6). First factor is
explaining 51.088% and second factor is explaining 14.261% of the variability. Both
the factors together ate giving a Cumulative variability of 65.349% which is more
than the threshold value 60%.
 Also, based on the extraction sum of squared loading, factor 1 explains 43.057% of
the variability, and factor 2 explains 7.164% of the variability.
b) Factor Loading model

Figure is displaying the factor loading model for manifest variables (op1, op2 ……. Op6)
According to the factor loading model, there are two latent factors namely, factor 1 and 2.

Here, factor 1 is related to three manifest variables OP2, OP4, OP6. Similarly factor 2 is

related to three manifest variables namely OP1, OP3, OP5.

According to rotated factor matrix, there is no significant correlation between the two latent
factors for a single manifest variable. we can conclude that OP6, OP4 and OP2 variables are
loaded in factor 1 Whereas OP5, OP3, OP1 are loaded in factor 1. There is no cross loading
in the model between the factors.

d)
Tests of Between-Subjects Effects
Dependent Variable: REGR factor score 1 for analysis 1
Source Type III Sum df Mean Square F Sig.
of Squares
Model 84.164a 39 2.158 3.381 .000
sex .157 1 .157 .246 .621
educ 5.331 5 1.066 1.670 .141
agegp3 4.508 2 2.254 3.531 .030
tlifesat 68.899 30 2.297 3.598 .000
Error 196.602 308 .638
Total 280.766 347
a. R Squared = .300 (Adjusted R Squared = .211)

 Looking at the significance of less than 0.05, our conclusion is that agegp3 and tlifesat
is showing significance less than 0.05 which means that these factors have a
significant impact on our factor model whereas education and sex does not play a
significant role in that.
 R squared value for the model is .300 which explains that about 30% of the factor
model variances can be explained by the applied factors in the model.

You might also like