Hi all,
I have a continuous dependent variable varying between 0 and 1. There are lots of zeros, too:
Array
When I run a regular OLS, I receive negative fitted values. So I decided to run a GLM to make sure the fitted values are in the right place. I've read lots of things about the selection of family and link selection but I still don't understand the mechanism behind it. Residuals from the OLS are normally distributed. Can I use Gaussian family and log link? This combination gives me all positive predicted values.
Many thanks.
Related Posts with Family and link selection in GLM
Using Mata*Inside Stata Program LoopHello, I am attempting to write a Stata/Mata program which formats excel files using Mata, by loopi…
Preserve/Restore with GlobalsIf I preserve, establish globals, and then restore, will the globals I established in the preserve/r…
Trouble configuring use of whereis with Word for Mac and markstat in Stata 16Hello all, I very happily developed a .do file on a Windows 10 machine using markstat with pandoc a…
Running regression with time indicator interactionHello, I am running regressions for daily exchange rate data and using Brexit-related news to see t…
Grand margin is ouside range given by margins at specified values of covariatesI have a problem understanding -margin results, even after reading Clyde Schechter's clarifications.…
Subscribe to:
Post Comments (Atom)
0 Response to Family and link selection in GLM
Post a Comment