Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: fracpoly and GAM


From   "Zang Geng" <geng.zang@umontreal.ca>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: fracpoly and GAM
Date   Tue, 6 Nov 2007 13:35:19 -0500

1.fracpoly poisson, which option can help control overdispersion without link to nbreg?
 
2.fracpoly reg, I found my residual follow normal distribution,but the variances are unequal, how to deal with this?
 
3.I did two fits:one is univariate fit,fracpoly reg, y x1, one is multivariate fit fracpoly reg, y x1 x2 x3 x4, I want to see the difference between predicted y and x1 among the two models. How can I plot predicted y and x1 in multivariate models?
 
GAM-generalized additive models 
 
In SAS, proc GAM can do generalized additive models,only confidence limits for each predicted smoothing component are provided, not the predited outcome confidence limits.Can STATA do GAM fit, and giving the predited outcome confidence limits?
 
Thanks,
 
Geng 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index