Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Compare models for panel data with xtreg fixed effects


From   Madalina Constantin <[email protected]>
To   [email protected]
Subject   st: Compare models for panel data with xtreg fixed effects
Date   Thu, 4 Jul 2013 23:45:02 -0700 (PDT)

I want to compare my models in STATA 12 in order to select the best one. I first run a base model with control variables only, then introduce each independent variable individually and finally run a full model with all variables. 
The problem is that I can not compare them. The AIC-test is only for comparing  maximum likelihood models. But for xtreg with random effects this is not an option. Neither does there exist a R-squared which I can interpret.
Here an example of my regressions:

xtreg div_int_change sales_log risk roa_t1 year_d1 year_d2 year_d3 year_d4 year_d5 , re 
xtreg div_int_change ceo_change sales_log risk roa_t1 year_d1 year_d2 year_d3 year_d4 year_d5 , re
xtreg div_int_change ceo_change ex_change tmt_sz_change sales_log risk roa_t1 year_d1 year_d2 year_d3 year_d4 year_d5,re

Is there any possibility to test the model fit respectively to say if the full model is better than the other models?

Thank you. 

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index