Hi,
I was wondering about finding possible multicollinearity relationship among the categorical independent variables. I thought it would be VIF. But, VIF didn't provide me good result (all were VIF < 5) even if I have put intentional collinear variables.
So, which method should be applied for checking collinearity for categorical and how to apply it in SPSS?
Thank you
Take a look at this link. Hope it helps. Best, D. Booth
https://www.google.com/search?q=collinearity+categoical+independent+variables&rlz=1C1CHBF_enUS874US874&oq=collinearity+categoical+independent+variables&aqs=chrome..69i57j0.44142j1j8&sourceid=chrome&ie=UTF-8
For categorical variables, multicollinearity can be detected with Spearman rank correlation coefficient (ordinal variables) and chi-square test (nominal variables).
For a categorical and a continuous variable, multicollinearity can be measured by t-test (if the categorical variable has 2 categories) or ANOVA (more than 2 categories).
Mukaram Ali Khan Thanks for your reply. But, I couldn't understand, if for nominal variables I perform chi2 test, then how can I understand that, there exists any collinearity between (two) variables?
Because, from Spearman rank correlation coefficient, I will understand the existing collinearity if the value of 'r' of two variables is near to +1.
But, for chi2, I am really confused.
Would you please clear me this confusion of mine (As I am at a beginner's level)?
Use below-mentioned link for your further query please
https://discuss.analyticsvidhya.com/t/how-to-use-chi-square-test-to-find-multicollinearity/64878
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS