Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Rép. : st: RE: Bug in star display (t value in regression coefficients)?


From   smerryman@kc.rr.com
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: Rép. : st: RE: Bug in star display (t value in regression coefficients)?
Date   Thu, 04 Nov 2004 07:18:49 -0600

The critical value for t-statistic will depend on the degrees of freedom. 

For example, in:

. sysuse auto

. keep in 1/5

. reg price mpg

the t-stat on mpg is 3.01 but it is not statistically significiant at the 
5% level because the critical value (with 3 df) is 3.182.

I would suspect your df is less than 40.

Hope this helps,
Scott

----- Original Message -----
From: Herve STOLOWY <stolowy@hec.fr>
Date: Thursday, November 4, 2004 6:46 am
Subject: Rép. : st: RE: Bug in star display (t value in regression coefficients)?

> I must precise my question. The problems does not appear in the 
> Stata output (where stars are not displayed) but in the outreg 
> command.
> After a linear regression ('regress' command), I type:
> 
> outreg using results, replace
> 
> without any other precision.
> 
> One of the t values of the regression coefficients is 2.02 (I have 
> it in the Stata output).
> 
> In the excel file obtained through outreg, this coefficient is not 
> marked with a star (whereas all other significant coefficients are 
> automatically marked with one (0.05 level) or two stars (0.01 level).
> 
> Is then a problem with outreg? Or do I misuse outreg?
> 
> Best regards and thanks again
> 
> Hervé
> 
> ***********************************************************
> HEC Paris
> Département Comptabilité-Contrôle de gestion / Dept of Accounting 
> and Management Control
> 1, rue de la Liberation
> 78351 - Jouy-en-Josas
> France
> Tel: +33 1 39 67 94 42
> Fax: +33 1 39 67 70 86
> stolowy@hec.fr
> http://campus.hec.fr/profs/stolowy/perso/home.htm
> >>> n.j.cox@durham.ac.uk 04/11/04 13:03 >>>
> Please specify which program and give an example. 
> 
> Nick 
> n.j.cox@durham.ac.uk 
> 
> Herve STOLOWY
> 
> > I noticed a strange thing concerning the t values of the 
> > regression coefficients.
> > 
> > A star should be displayed if the coefficient is significant 
> > at the 0.05 level. In my mind, the threshold t value for this 
> > level was 1.96. I have a coefficient of 2.02 in a regression 
> > and no star is displayed. Am I wrong somewhere? Is there a bug?
> 
> *
> *   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/
> 
> 
> *
> *   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/
> 


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index