3.5. Multicollinearity
One of the nice things about logit analysis is that it’s so much like ordinary linear regression analysis. Unfortunately, some of the less pleasant features of linear regression analysis also carry over to logit analysis. One of these is multicollinearity, which occurs when there are strong linear dependencies among the explanatory variables.
For the most part, everything you know about multicollinearity for ordinary regression also applies to logit regression. The basic point is that, if two or more variables are highly correlated with one another, it’s hard to get good estimates of their distinct effects on some dependent variable. Although multicollinearity doesn’t bias the coefficients, it does make them more unstable. ...
Get Logistic Regression Using SAS®: Theory and Application now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
