Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

st: Re: estout and test statistics

From   nshephard <[email protected]>
To   [email protected]
Subject   st: Re: estout and test statistics
Date   Fri, 22 Oct 2010 01:25:07 -0700 (PDT)

Rodrigo Briceño-4 wrote:
> quietly regress liq sap ndvenc pprom pemi mes if isin=="XS0185150165"
> estimates store m15, title(XS0185150165)
> quietly estat imtest, white
> local hettest = r(chi2)
> local hetprob = r(p)
> estadd scalar hettest = `hettest'
> estadd scalar hetp = `hetprob'
> estout * using modelo.txt, cells(b(star fmt(%9.3f)) se(par))
> stats(r2_a N hettest hetp, fmt(%9.3f %9.0g %9.3f %9.3f)
> labels(R-squared)) legend label collabels(none) varlabels(_cons
> Constant)
> Can somebody please tell me where can I put the "star" option for this
> hettest?

Not the advice you want, but personally I'd avoid stars and just have the
p-values presented.

Nick Cox has posted an excellent critique of the practice previously...

View this message in context:
Sent from the Statalist mailing list archive at

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index