Is there somebody who could, in a reasonably general way, explain "lateral collinearity" and its practical implication in logistic regression? Does lateral collinearity necessarily imply strong correlation? I have a binary outcome variable and four binary explanatory variables, of which one is very similar to the outcome variable (outcome: "interest" (yes/no) explanatory: "enthusiasm" (yes/no)
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Since I posted the question, I have found this reference: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2152644 but it seems to be the only paper on "lateral collinearity" that is to be found...