Statalist


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

RE: st: RE: RE: AW: Taking mata views of ereturn stats?


From   "Martin Weiss" <[email protected]>
To   <[email protected]>
Subject   RE: st: RE: RE: AW: Taking mata views of ereturn stats?
Date   Fri, 18 Dec 2009 19:24:40 +0100

<>

" V[7..42,7..42]"

This is the manual solution, I was wondering whether there is an automatic
one because the zeroes for the base outcome are not really informative...


HTH
Martin


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Skipper Seabold
Sent: Freitag, 18. Dezember 2009 19:21
To: [email protected]
Subject: Re: st: RE: RE: AW: Taking mata views of ereturn stats?

On Fri, Dec 18, 2009 at 1:14 PM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> Let`s make being "pedantic" a little more worthwhile: How can Skipper get
> rid of the zeroes in his varcov representing the base outcome in -mlogit-?
>
>

V[7..42,7..42] was what I went with...  If we're having a tutoring
session though, what I'd really like is to have is

sqrt(diagonal(V[7..42,7..42]))

without the row labels and the "box", ie., purely numeric (possibly
even a rowvector), but I figure I should do my homework before
bothering you very helpful people!

Skipper
*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index