Bookmark and Share

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]

Re: st: outreg2 and beta coefficients


From   John Luke Gallup <jlgallup@pdx.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: outreg2 and beta coefficients
Date   Fri, 12 Aug 2011 13:24:52 -0700

Rado,

It looks like you want a table with the beta coefficients with stars for significance levels, but no other statistics including t statistics or standard errors.  

This is possible with the new version of -outreg-.  I am not sure about whether this is possible with -outreg2-.  -outreg- can be downloaded with -ssc install outreg, replace-.

The following code will report beta coefficients with stars next to them for the significance level of _regular_ coefficients (not beta coefficients).  

sysuse auto, clear
regress mpg weight turn, vce(robust) beta
outreg, stats(beta) starloc(1)

In -regress-, Stata does not report standard errors or t statistics of beta coefficients.  -outreg- also does not calculate the standard errors of beta coefficients, so it cannot report significance stars for a test that the beta coefficients are different from zero.  I am pretty certain that -outreg2- does not either.

By the way, what the point of beta coefficients, and who uses them?

John


On Aug 12, 2011, at 10:02 AM, rado645-bg@yahoo.de wrote:

> Hello,
> 
> is there a way to make outreg2 reporting the significance of beta coefficients 
> attached as asterisks?  
> 
> 
> 
> I need to report standardized beta coefficients after running ols regressions. I 
> use the standard command:
> 
> regress var1 var2, vce(robust) beta
> 
> and then I use outreg2 command in the following way: 
> 
> outreg2 using word, stats(beta)
> 
> 
> However I receive table output with beta coefficient estimates 1)in brackets 
> only and 2)without any asterisks marking significance. 
> 
> 
> Is there an option to mark the significance?Many thanks in advance. 
> 
> Rado
> 
> *
> *   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/


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