Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

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

From |
"Swanquist, Quinn Thomas" <qswanqui@utk.edu> |

To |
"statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |

Subject |
RE: st: comparing coefficients across models |

Date |
Fri, 3 Aug 2012 14:03:53 +0000 |

I agree with David and others. You should be cautious if your results are sensitive when 'correcting' for the collinearity 'problem'. Collinearity does not cause inconsistent estimators. Wooldridge compares the multicollinearity issue with that of small sample sizes, that is it arises from lack of power. If you have a large n it is likely not a problem. What are the vifs on your original model? Quinn Swanquist qswanqui@utk.edu -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of David Hoaglin Sent: Thursday, August 02, 2012 9:33 PM To: statalist@hsphsun2.harvard.edu Subject: Re: st: comparing coefficients across models Hello, Dalhia. Others have already given a useful suggestion for comparing the two coefficients. You should investigate the reason(s) for the collinearity problem that you are reporting. If x1 and x2 are continuous variables, it may be helpful to center them (at their mean or at some other convenient value). What was the actual model that produced the collinearity problem? David Hoaglin On Thu, Aug 2, 2012 at 4:41 PM, Dalhia <ggs_da@yahoo.com> wrote: > > Hello, > I have two groups and need to run the same regression model on both > groups (number of observations differ but variables are all the same). > I am interested in the difference in the coefficients for one > particular variable. > > here are the two models I am running: > > xtreg y x1 x2, fe robust if group==1 > xtreg y x1 x2, fe robust if group==2 > > I cannot put the two groups together, and run the model with an > interaction with dummy variable for group, because then the model > becomes highly multicollinear, and the coefficients are not stable. > > Is there a test that can help me check if the coefficient on x2 differs significantly across the two groups? * * 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/

**References**:**Re: st: Odd behaviour of wordcount function***From:*"Seed, Paul" <paul.seed@kcl.ac.uk>

**st: comparing coefficients across models***From:*Dalhia <ggs_da@yahoo.com>

**Re: st: comparing coefficients across models***From:*David Hoaglin <dchoaglin@gmail.com>

- Prev by Date:
**Re: st: What is the effect of centering on marginal effects?** - Next by Date:
**Re: st: string variable** - Previous by thread:
**RE: st: comparing coefficients across models** - Next by thread:
**st: specifying a single value in xlabel while leaving the rest as-is** - Index(es):