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: How to get P Values for sargan and abond in ereturn

 From Shan Ghimire To statalist@hsphsun2.harvard.edu Subject Re: st: How to get P Values for sargan and abond in ereturn Date Sun, 2 Sep 2012 12:44:43 -0400

```Thank you Nick! More decimal places certainly helps.
Shan

On Sun, Sep 2, 2012 at 12:38 PM, Nick Cox <njcoxstata@gmail.com> wrote:
> I doubt that -esttab- (SSC) contains options for falsifying your
> results. For your purposes you need more decimal places and the help
> for -esttab- tells you options for tuning the format.
>
> Nick
>
> On Sun, Sep 2, 2012 at 4:50 PM, Shan Ghimire <shanmire@gmail.com> wrote:
>> Daniel,
>> That's a big help. Thank you so much. I have another tail question,
>> however. I get the value of psargan to be 0.99964. Now, if I use
>> esttab <model>, sca(psargan), the value for psargan is rounded to
>> 1.000 in the table. I would instead like to report 0.999 without
>> rounding it up. Could you help me with that please?
>> Thank you.
>> Shan
>>
>> On Sun, Sep 2, 2012 at 6:49 AM, daniel klein
>>> Shan,
>>>
>>> Buis (2007) shows how to do this. You already have the test statistic
>>> for -sargan- stored in e(). All you need is the degrees of freedom,
>>> which I guess should be e(zrank) - e(rank) -- I  could be wrong here.
>>> You can then calculate the p-value as
>>>
>>> sca psargan = chi2tail(e(zrank) - e(rank), e(sargan))
>>>
>>> Next you put the scalar into e(), using -estadd-, part of -estout- (Jann, SSC)
>>>
>>> estadd sca psargan = psargan
>>>
>>> -esttab-, also part of -estout- (Jann, SSC).
>>>
>>> esttab <whatever> ,sca(psargan)
>>>
>>> You migth want to use a temporary name for the scalar, or a -local- instead.
>>>
>>> Best
>>> Daniel
>>>
>>>
>>> Buis, Maarten, L. (2007). Stata tip 53: Where did my p-values go? The
>>> Stata Journal, 7(4), pp. 584–586.
>>> (http://www.stata-journal.com/sjpdf.html?articlenum=st0137)
>>>
>>> --
>>> I am running a panel data regression using xtdpdsys. After running the
>>> regression, I perform estat sargan and estat abond and I can see both
>>> the test statistic values and p-values for them in the log window.
>>> However, I would like to get the p-values from ereturn list for these
>>> tests so that I can put these p-values at the end of the regression
>>> table using esttab. The ereturn list gives me  only  the test
>>> statistics - e(sargan) and e(arm2) but not the p-values for them.
>>> Could anybody help me with that please?
>>>
>>> Thank you in advance. Shan
>
> *
> *   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/

--
Shankar
1. "Faith makes everything possible"
2. "It matters how you are going to finish"

*
*   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/
```