Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: AW: confidence interval of a ratio of coefficients
From
Arne Risa Hole <[email protected]>
To
[email protected]
Subject
Re: st: AW: confidence interval of a ratio of coefficients
Date
Fri, 9 Apr 2010 17:52:56 +0100
Rodolphe's suggestion calculates a parametric bootstrap CI, so this is
essentially the same as using the -krinsky- option of -wtp-. The two
approaches will not give *exactly* the same results, however, as the
draws from the multivariate normal distribution are not generated in
the same way.
Arne
On 9 April 2010 16:34, Rodolphe Desbordes
<[email protected]> wrote:
> Oops... the "qui" are of course unnecessary...
>
> Rodolphe
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Rodolphe Desbordes
> Sent: vendredi 9 avril 2010 16:26
> To: '[email protected]'
> Subject: RE: st: AW: confidence interval of a ratio of coefficients
>
> Martin and Nick,
>
> Very true:
>
> ***
> sysuse auto, clear
> set seed 2940688
> logit foreign price weight rep78
>
> preserve
>
> drawnorm b1-b4, n(20000) means(e(b)) cov(e(V)) clear
>
>
> gen ratio=-(b2)/(b1)
>
> qui sum ratio,meanonly
>
> dis "ratio: " r(mean)
>
> qui _pctile ratio, p(2.5,97.5)
>
> dis "ll: " r(r1)
> dis "ul: " r(r2)
>
>
>
> restore
>
> ***
>
> Rodolphe
*
* 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/