Re: st: ...test after panel model estimates...

[Richard Williams <Richard.A.Williams.5@nd.edu>]

At 04:37 PM 4/19/2004 +0200, fabiopericolini@fastwebnet.it wrote:
> Hi all,
> I have performed a panel model and I would test some hypothesis like 
> homegeneity,
> collinearity .... but the usuals commands I use with the linear regression
> (hettest, whitetst , vif......) don't be allowed for the panel model in
> Stata. How I can do??
There was a discussion of multicollinearity diagnostics when not using OLS 
back on Dec. 10; it starts at

http://www.stata.com/statalist/archive/2003-12/msg00333.html

I don't know if panel data raises any unique issues, but in other cases you 
handle multicollinearity pretty much the same way regardless of whether you 
are using OLS, probit, logit, etc.  Multicollinearity involves the Xs, not 
the Y.  So, you could run the user-written routine -collin-.  Or, you could 
even just use regular OLS (ignoring the parameter estimates) and use 
commands like -vif- afterwards.  That thread suggested other options as well.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   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/