Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Bug in margins
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: Bug in margins
Date
Tue, 03 Sep 2013 13:31:41 -0500
At 11:48 AM 9/3/2013, Sue Kay wrote:
Thanks both of you,
I must have missed that one when I checked the statalist. I still
cannot see it in the help file though, or maybe I am misinterpreting
some of the description.
Sometimes I just wish the help files are a little more clear for a
layman like me.
The help for margins could use a little customization for individual
commands. I just searched the ME manual for "fixedonly" and I didn't
see a nice explicit statement that you needed to use it if you wanted
to use margins. Maybe you are supposed to be smart enough to figure
that out for yourself, but a few nice clear sentences could save a
lot of work. Maybe there could be a FAQ about what you can and cannot
do when using margins after specific commands that require some
special treatment.
On 9/1/13 7:10 PM, Ariel Linden, DrPH wrote:
See the response that was given to me when I posted the same question last
month
http://www.stata.com/statalist/archive/2013-08/msg00451.html
From William Buchanan <[email protected]>
To "[email protected]" <[email protected]>
Subject Re: st: Bug in margins
Date Sun, 1 Sep 2013 19:46:00 -0500
Check the help file again, in particular the -fixedonly- option. This was
also recently discussed on the Statalist. The problem is due to the random
effects.
Sent from my iPhone
On Sep 1, 2013, at 19:37, Sue Kay <[email protected]> wrote:
Hi,
I don't know whether it is due to a bug, or I am missing something, but I
have some problems with margins command after I run my model with meqrlogit
(with two random slopes).
Even I add the prefix i. to the factor variables in my model, I still got
the dreaded "default prediction is a function of possibly stochastic
quantities other than e(b)" message (which I get only if I don't use i.
prefix with the variable I try to calculate my margins after xtlogit)
Here is a sample of what I do:
meqrlogit y i.x1 i.x2 i.x3 x4 x5 x6 x7 || cluster: x1 x2
And when I try to do this:
margins x1
I receive:
default prediction is a function of possibly stochastic quantities other
than e(b)
I tried running my model using xtlogit (just with random intercept of
course), and the margins command works without a problem.
Am I missing something?
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/