mkcorr, available at SSC, can output summary statistics in addition to
itss main purpose of correlation tables.
Sent from my iPhone
On Mar 15, 2009, at 7:27 PM, Roy Wada <[email protected]> wrote:
>
>> Can I ask a question? Is there a similar output command as
>> outreg for Summary? I want to first use command summary and
>> then output selected items (such as mean median p1 p99 STD)
>> for many variables.. Is there a such output command?
>>
>> Many thanks in advance!
>
> An interesting question. There is always -outsum- by Kerry Papps
> that will creat a summary stats like -outreg- does.
>
> Then there is the latest version of -outreg2- that will handle
> some summary statistics. I think it will do some tabulation as
> well.
>
> It should be up on SSC whenever Kit Baum gets to it.
>
> Incidently, -outreg2- is now byable (I forgot to mention this
> in the help file). The latest version will also run under version 7
> of Stata (this one I remembered; see the bottom of the help file for
> limitations).
>
> reg headroom trunk weight length
> version 7: bys foreign :outreg2 using myfile, sum excel seeout replace
>
> You can obviously place summary stats next to the regression output.
>
> outreg2 using myfile, replace
> outreg2 using myfile, sum excel seeout
>
> By design, the -sum- option will only report summary stats for
> variables and observations used in the last regression. Hence it
> will only run after a regression command.
>
> I now see Martin wanted the detailed stats as well. The following
> option is currently undocummented (because I will probably change it).
> This is for the whole sample.
>
> reg headroom trunk weight length
> outreg2 using c:\myfile, sum(detail) excel seeout replace
>
> The follwoing is just for sd without the whole enchilada.
>
> outreg2 using c:\myfile, sum(detail) excel seeout replace eqkeep(sd)
>
> The current limitation of -sum- option is that it cannot handle a
> large number of variables (something to do with the matsize
> limitation).
>
> It was easier to write it this way, but I guess I will have to rewrite
> it properly to be able to work with a large number of variables. I
> might
> be able to get to it some time this year.
>
> Roy
>
> _________________________________________________________________
> Hotmail® is up to 70% faster. Now good news travels really fast.
> http://windowslive.com/online/hotmail?ocid=TXT_TAGLM_WL_HM_70faster_032009
> *
> * 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/
*
* 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/
