1
$\begingroup$

I was planning to construct a model with around 19 explanatory variables and one response variable. I have some confusion on following thing:

If transformation is required in case of explanatory variables, do I transform first and then check for collinearity or the other way round

Sorry if the question is not correct or vague.

Thanks

$\endgroup$
  • 1
    $\begingroup$ When you have two questions, you should ask them as two separate questions here! As for the second question, checking for colinearity must of course be done with the variables you are actually using in your model, so after transformation. $\endgroup$ – kjetil b halvorsen Jan 26 '15 at 14:08
1
$\begingroup$

At the end of the day, the model that you use ought to have as little collinearity as possible because collinearity makes interpretation of your predictors difficult or even meaningless. So, after you've selected a model (with any transformations) you ought to check for collinearity. If transformation is required, transform and then check for collinearity because this is the way the variables will be used in the model.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.