I have conducted factor analysis to identified seven hidden factors.
Now I wish to do correlation test or run logistic regression using these hidden factors individually with the intended correlated variable.
However, I don't know how I can take each hidden factor as One Unit to compare with the correlated variable.
E.g. The hidden factor 1 has underneath 3 measures (A, B, C), how I can group A, B and C into factor 1 as a unit to compare with the other variable?
Thanks very much!
Using the loadings for factor1 you'll figure out the formula for it; ie
Factor 1 = laodingA*A + loadingB*B + loadingC*C
The statistical software should give you the factor structure matrix which is the correlation matrix between the variables and the factors.
Dear Danny,
In SPSS it is even easier than what Faye has suggested. In the factor analysis dialog there's an option to save the regression model for each factor, then you can just put them all into a bivariate correlation.
You can use SPSS and Factor 10.1 for your aim. In SPSS, you should save factor's scores by scores option then you can compute correlations for factors. If you use Factor 10.1, it computes automatically correlations between factors.
You can create summated score for factors and do the correlation analysis using SPSS.
- Badges
- Science topic
- Similar topics
- Engineering
- Modeling