Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Christopher F Baum <baum@bc.edu> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | re:RE: st: Multiple nonlinear equations regression with categorical |
Date | Thu, 6 Jan 2011 14:27:12 -0500 |
<> I was trying to avoid transforming the data since that would change the assumptions about variance. Or does it not matter for the predictor variables? The only assumption made in regression about measurement of the predictor variables is that the elements of the matrix X'X are finite and that the matrix is positive definite.* Assumptions about variance of the error term are not affected by whether you include x, x^2, log(x), sqrt(x), exp(x) as a predictor variable. * OK, if this is a time series context, there are a few more, but I don't think that's where you're coming from. Kit Kit Baum | Boston College Economics and DIW Berlin | http://ideas.repec.org/e/pba1.html An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/