Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | DE SOUZA Eric <eric.de_souza@coleurope.eu> |
To | "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: RE: regress with vce(robust) and hascons |
Date | Mon, 13 Dec 2010 17:54:35 +0100 |
This is what is happening in my opinion. In an ordinary least squares regression with homoscedastic errors, when the hascons option is specified,Stata (i) estimates the coefficients, staandard errors, etc as if the nocons option were effective, (ii) but then takes into account the implicit or explicit presence of a constant in the model when calculating overall F test and R2. However, when the robust option is specified, Stata has no way of undertaking step (ii) above, and proceeds throughout as if the nocons option were specified. Eric de Souza College of Europe BE-8000 Brugge (Bruges) Belgium -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Steven Samuels Sent: 13 December 2010 16:13 To: statalist@hsphsun2.harvard.edu Subject: Re: st: RE: regress with vce(robust) and hascons According to the manual pages that Eric referenced, with the -hascons- option, the F test should test for the difference in intercepts. Michael's question is: why does the addition of the -vce(robust)- option alter this? It looks like a bug to me, but only someone from StataCorp can tell us for sure. Steve sjsamuels@gmail.com On Dec 13, 2010, at 8:56 AM, DE SOUZA Eric wrote: I still have to digest the information, but there is a discussion linked to the issue you raise in the manuals See page 1521 of -regress- for a comparison of hascons and nocons and page 1524 of -regress- for a discussion of F tests with and without hascons Combining these two should provide the answer. Eric de Souza College of Europe BE-8000 Brugge (Bruges) Belgium -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu ] On Behalf Of Michael N. Mitchell Sent: 13 December 2010 09:43 To: Statalist Subject: st: regress with vce(robust) and hascons Greetings I am puzzled by the behavior of Stata when I include the - vce(robust)- option along with the -hascons- option. Consider the example below in which I estimate a model predicting - price- from -foreign- but do so using a cell means model by specifying ibn.foreign and thus include the -hascons- option. I further want robust standard errors so specify the -vce(robust)- option. . sysuse auto, clear (1978 Automobile Data) . regress price ibn.foreign, vce(robust) hascons Linear regression Number of obs = 74 F( 2, 72) = 165.64 Prob > F = 0.0000 R-squared = 0.0024 Root MSE = 2966.4 ------------------------------------------------------------------------------ | Robust price | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------- -------------+------ foreign | 0 | 6072.423 431.2084 14.08 0.000 5212.825 6932.021 1 | 6384.682 553.6754 11.53 0.000 5280.95 7488.413 | _cons | (omitted) ------------------------------------------------------------------------------ The omnibus F test shows 2 degrees of freedom, but I only expected 1 df. The omnibus F test appears to be testing the joint hypothesis that each of the cell means is 0 (see below). . test 0.foreign 1.foreign ( 1) 0bn.foreign = 0 ( 2) 1.foreign = 0 F( 2, 72) = 165.64 Prob > F = 0.0000 But because I specified -hascons- I expect it to test the equality of the cell means. This is the case when I omit the -vce(robust)-, as shown below. . regress price ibn.foreign, hascons Source | SS df MS Number of obs = 74 -------------+------------------------------ F( 1, 72) = 0.17 Model | 1507382.66 1 1507382.66 Prob > F = 0.6802 Residual | 633558013 72 8799416.85 R-squared = 0.0024 -------------+------------------------------ Adj R-squared = -0.0115 Total | 635065396 73 8699525.97 Root MSE = 2966.4 ------------------------------------------------------------------------------ price | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------- -------------+------ foreign | 0 | 6072.423 411.363 14.76 0.000 5252.386 6892.46 1 | 6384.682 632.4346 10.10 0.000 5123.947 7645.417 ------------------------------------------------------------------------------ In this case, the omnibus F test matches the test of the equality of the cell means. . test 0.foreign = 1.foreign ( 1) 0bn.foreign - 1.foreign = 0 F( 1, 72) = 0.17 Prob > F = 0.6802 Perhaps someone can help me understand where I am askew in my thinking about this. Many thanks, Michael N. Mitchell Data Management Using Stata - http://www.stata.com/bookstore/dmus.html A Visual Guide to Stata Graphics - http://www.stata.com/bookstore/vgsg.html Stata tidbit of the week - http://www.MichaelNormanMitchell.com * * 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/ * * 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/