RE: st: multicollinerity in panel data

[Cameron McIntosh <cnm100@hotmail.com>]

I second the comment that multicollinearity is generally no reason to panic:

http://www.springerlink.com/content/hjt766336770k46m/ ;

Cam
> Date: Mon, 7 May 2012 00:39:23 +0100
> Subject: Re: st: multicollinerity in panel data
> From: digitalepourpre@gmail.com
> To: statalist@hsphsun2.harvard.edu
> 
> Hi Ozgur,
> 
> Have a look at:
> 
> http://www.ats.ucla.edu/stat/stata/webbooks/reg/chapter2/statareg2.htm
> 
> That said, multicollinearity is usually not a major concern in applied
> work unless you have almost perfect multicollinearity because you
> accidentally entered the same variable twice, .e.g. in a transformed
> and untransformed form.
> 
> When regressors are highly dependent, it is difficult to disentangle
> impacts between the explanatory variables. The SEs will be larger but
> the point estimates are still ok. Endogeneity is a more serious
> problem.
> 
> 
> 
> On 7 May 2012 00:06, Ozgur Ozdemir <ozdemirozgur@hotmail.com> wrote:
> >
> > Hi
> > I am using Stata 10 and doing a panel data analysis. My panel is unbalanced and has 10000 firm year observations. I am using the areg to do my analysis and would like to know how I can test for multicollinerity. in addition, is there any way to find our post areg tests?
> >
> >
> >
> >
> > kind regards
> > Ozgur Ozdemir
> >
> >
> > *
> > *   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/
> 
> *
> *   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/
 		 	   		   		 	   		  
*
*   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/