Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | Re: st: How to Interpret Coefficients when DV is square-rooted |
| Date | Wed, 3 Aug 2011 08:10:31 +0100 |
-glm- with square root link may help. NickOn 2 Aug 2011, at 21:48, "springathens@gmail.com" <springathens@gmail.com > wrote:
Dear Stata Listers I am estimating turnover ratio using OLS. I found heteroskedasticity, and as recommended in the textbook (Wooldridge, 2006) I transformed turnover rates using square root. After transformation, heteroskedsticity problem is solved. However, the next problem occurs: how do I interpret the beta coefficients for each independent variable?If I square both sides, the equation in the right hand side becomes messy.There are multiple recommendations to solve a heteroskedsticity problem (such as using weighted least squares, or robust standard error and so on), but I am now curious how to interpret coefficients of independent variables when dependent variable is square rooted
* * 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/