Dear All,
I am looking for some references and / or advice as to how to
a) interpret significant correlations
b) interpret significant covariates using regression analysis techniques
when the sample size is very large, 1000+ observations.
I understand that the large sample size will cause significant correlations
and also significant covariates, regardless of their relationship to the
dependent variable. If this is the case, does anyone know of an alternative
method to assess multicollinearity other than calculating correlation
coefficients?
Many Thanks,
Lohita.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|