A Data Science Central Community
Tags:
I have the same issues with this stat. I think it is sample size issue.
I used VIF option under proc reg to make sure those variables entered into logistic model do not highly correlated. So correlation is not an issue.
My logistic model also has very high KS value.
I suspect it is binning issue when dealing with very small group of responders. Sometime, low respond % also tends to generates logstics model with high KS. H-L test is like Chi-square test performed on 10 group of bins.
1 responder falling into a different bin can change a lot outcome on this chi-square test if responders are very thin.