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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: list coefficient estimations


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: list coefficient estimations
Date   Thu, 14 Apr 2011 15:31:12 +0100

I think this desire is statistically ridiculous, frankly, but just
looking at the help for -matrix list- would show that you can tune the
display. You could also use hexadecimal format to see every last bit
that Stata is holding for you.

. sysuse auto
(1978 Automobile Data)

. gen gpm = 1 / mpg

. regress gpm weight

. mat li e(b)

e(b)[1,2]
       weight      _cons
y1  .00001407  .00770767

. help matrix

. mat li e(b), format(%23.18f)

e(b)[1,2]
                  weight                 _cons
y1  0.000014070444284905  0.00770766777955807

. mat li e(b), format(%21x)

e(b)[1,2]
                   weight                  _cons
y1  +1.d8203232cddfdX-011  +1.f921350aa8958X-008

On Thu, Apr 14, 2011 at 3:23 PM, Max Fotbollen <praktiskbox@live.se> wrote:
> This is what I get for my coefficients;
>  mat li e(b)
> e(b)[1,2]
>       Storks      _cons
> y1  4.4352163   1401.127
> Which is by the way the same nember of decimal points that you get in the output directly after running the model.
> Corresponing figure from SPSS storks' coefficient is 4.434216270161429.
>
>
>
> And here is what I ANOVA figures, which are ok.
>
>  ereturn list
> scalars:
>                  e(N) =  16
>               e(df_m) =  1
>               e(df_r) =  14
>                  e(F) =  226.840002418306
>                 e(r2) =  .9418701218260083
>               e(rmse) =  415.5066042516718
>                e(mss) =  39162959.66552542
>                e(rss) =  2417040.334474576
>               e(r2_a) =  .9377179876707231
>                 e(ll) =  -118.1067415323327
>               e(ll_0) =  -140.8673454765096
>               e(rank) =  2
>
>
> ----------------------------------------
>> Date: Thu, 14 Apr 2011 15:12:34 +0100
>> Subject: Re: st: list coefficient estimations
>> From: njcoxstata@gmail.com
>> To: statalist@hsphsun2.harvard.edu
>>
>> I don't what that means. Perhaps you mean a large number of decimal
>> places. e-class results typically contain far more decimal places than
>> anyone really needs or even wants.
>>
>> On Thu, Apr 14, 2011 at 3:08 PM, Max Fotbollen wrote:
>>
>> > As in SPSS you may get the full decimalpoints for the estimations. That is what I need, full decimalpoints estimations.
>>
>> From: nshephard@gmail.com
>>
>> >> On Thu, Apr 14, 2011 at 2:40 PM, Max Fotbollen wrote:
>> >> > Hi,
>> >> > I need to retrive and also save OLS estimates. I use return list, don't get any resopnses, not even error response. Use rreturn list, then I get some results in the output, but not the regression coefficients.
>> >> >
>> >>
>> >> What was wrong with the suggestions from Nick Cox?
>> >>
>> >> http://www.stata.com/statalist/archive/2011-04/msg00709.html

*
*   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