<>
" This can happen, I think, if one of the specified variables is
constant."
Let`s check:
*************
capture which estout
if _rc ssc install estout
sysuse auto, clear
local vars /*
*/ "pri mpg disp tr rep78"
//make rep78 constant
replace rep78=4
pwcorr `vars' ,/*
*/ star(.1) bon
qui estpost correlate `vars', /*
*/ matrix
esttab ., not unstack/*
*/ compress noobs /*
*/ star(* 0.10 ** 0.05 *** 0.01)
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Ben Jann
Gesendet: Montag, 25. Januar 2010 15:04
An: [email protected]
Betreff: Re: st: WG: Star Levels in Correlation Tables
Probably some of the correlations are missing due to data problems.
This can happen, I think, if one of the specified variables is
constant. -estpost correlate- refuses to post the correlations in e(b)
in this case.
ben
On Mon, Jan 25, 2010 at 9:33 AM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> Nishanth complained about an error message to me privately. I cannot
> replicate the problem, even though I intentionally use "rep78" which has
> five missing values:
>
>
> *************
> capture which estout
> if _rc ssc install estout
>
> sysuse auto, clear
>
> local vars /*
> */ "pri mpg disp tr rep78"
>
> pwcorr `vars' ,/*
> */ star(.1) bon
>
> qui estpost correlate `vars', /*
> */ matrix
>
> esttab ., not unstack/*
> */ compress noobs /*
> */ star(* 0.10 ** 0.05 *** 0.01)
> *************
>
>
>
> HTH
> Martin
>
> Von: Nishanth Chari [mailto:[email protected]]
> Gesendet: Montag, 25. Januar 2010 04:43
> An: [email protected]
> Betreff: Star Levels in Correlation Tables
>
> Hello Martin,
>
> I had a question about your response to the post online at
> http://www.stata.com/statalist/archive/2009-06/msg00293.html. When I try
to
> run the commands you've listed, I get the following error message:
> "estimates post: matrix has missing values r(504);" and then when I run
the
> last esttab command all I get is the correlation between my last x
variable
> and itself (i.e. 1). Do you know how I might fix this? Do I simply need to
> make sure that there are no missing values in my data set?
>
> Alternatively, is there any other command that will include the stars
> automatically? The command "mkcorr" does not appear to have this option
but
> I'm wondering if you might know of any other similar command for
correlation
> tables that does..
>
> Thanks for your help,
> Nish
>
> *
> * 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/
*
* 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/
