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.

# RE: st: Bias corrected p-values after bootstrap

 From Nick Cox To "'statalist@hsphsun2.harvard.edu'" Subject RE: st: Bias corrected p-values after bootstrap Date Mon, 14 Nov 2011 19:25:28 +0000

```Wrong tick.

. regress mpg foreign

Source |       SS       df       MS              Number of obs =      74
-------------+------------------------------           F(  1,    72) =   13.18
Model |  378.153515     1  378.153515           Prob > F      =  0.0005
Residual |  2065.30594    72  28.6848048           R-squared     =  0.1548
Total |  2443.45946    73  33.4720474           Root MSE      =  5.3558

------------------------------------------------------------------------------
mpg |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
foreign |   4.945804   1.362162     3.63   0.001     2.230384    7.661225
_cons |   19.82692   .7427186    26.70   0.000     18.34634    21.30751
------------------------------------------------------------------------------

. local t =  _b[foreign]/_se[foreign]

. di 2*ttail(e(df_r),abs((`t')))
.00052542

You need char(39).

Nick
n.j.cox@durham.ac.uk

Sunday Clark

Following the steps outlined by Buis in The Stata Journal
(http://www.stata-journal.com/article.html?article=st0137), I have
been able to obtain the t statistic using the following: di
_b[var1]/_se[var1]

When I try the following to obtain the P value:
. local t = _b[var1]/_se[var1]
. di 2*ttail(e(df_r),abs(`t´))

I get the following error:
`t´ invalid name
r(198);

I am doing something wrong, but I can't seem to identify the problem.
I am using Stata 12. I would appreciate any help.

Thank you,
Sunday

2011/11/7 Jorge Eduardo Pérez Pérez <perez.jorge@ur.edu.co>
>
> After -bootstrap-, the point estimates are stored in e(b) and the bias
> is stored in e(bias). So you can get the bias corrected point
> estimates:
>
> matrix bc=e(b)-e(bias)
>
> After that, you can compute your p-values using these new point
> estimates and the standard errors, see:
>
> http://www.stata-journal.com/article.html?article=st0137
>
> Hope this helps,
> _______________________
> Jorge Eduardo Pérez Pérez
>
>
>
>
> On Mon, Nov 7, 2011 at 9:40 AM, Sunday Clark <sunday.clark@gmail.com> wrote:
> > Hello,
> >
> > I saw this question posted in the archives four years ago, but did not
> > see an answer. I am wondering if new information is available that
> > might help answer the question. I there a way to obtain bias corrected
> > p-values in addition to the bias corrected confidence intervals after
> > running a bootstrap? I used the following to obtain the confidence
> > intervals: estat bootstrap, all or.

*
*   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/
```