I have an interval scale survey data. I have defined the socioeconomic status of the survey site with 5 parameters and wish to create a composite index. I do not have any prior weights for these parameters. Can I use PCA to create an index? My data is satisfying KMO and Bartlett Sphericity test, but for the results to be robust is it important for the data to pass normality and "no non-linearity" tests as well? Some of my parameters are normal while some are not. Please guide.
I think you can use pca. If the sample size is large, e. G. More than 50, do not care about normality as long as the data is normal shape.
PCA for modeling purposes: normality would be ideal.
PCA for data reduction or exploratory purposes: normality is not a strcit requirement.
You can use PCA on your data. The only thing i would recommend to you is that PCA might work better for multivariate normal data.
Thanks for your response Hamid and Efehan. How to check multivariate normality ?
Why don't you try:
http://www.biosoft.hacettepe.edu.tr/MVN/
It is an online app based on the following R package:
https://www.r-bloggers.com/testing-for-multivariate-normality/
Good Luck !
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics