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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Marginal Effects: CLogit


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Marginal Effects: CLogit
Date   Sun, 7 Oct 2012 08:47:44 +0100

As said, yes. You can get marginal effects for continuous predictors,
but you must spell out what you want. There is a brief introduction to
-margins- in [U]. Otherwise there really is no subsitute for reading
the help and the manual entry.

Nick

On Sat, Oct 6, 2012 at 8:55 PM, Wameq Raza <wameq.r@gmail.com> wrote:
> Dear Nick,
> Thank you very much for the clarification, I'm not sure how I missed
> that. As I previously mentioned,
> I'm just trying to get the marginal effects of the variables from the
> estimated model.
> Am I going about this the wrong way?
> Wameq
>
> On Sat, Oct 6, 2012 at 7:09 PM, Nick Cox <njcoxstata@gmail.com> wrote:
>> The help for -margins- starts off
>>
>> margins [marginlist] [if] [in] [weight] [, response_options options]
>>
>>     where marginlist is a list of factor variables or interactions that
>>     appear in the current estimation results.
>>
>> That means what it says: so, you are asking something -margins- can't
>> do it if you offer up continuous variables _as if_ they were factor
>> variables. That just won't work.
>>
>> The real questions are thus exactly what you want out of -margins-;
>> whether that makes sense, and how else to get it, on which others can
>> advise better than I can.
>>
>> Nick
>>
>> On Sat, Oct 6, 2012 at 5:51 PM, Wameq Raza <wameq.r@gmail.com> wrote:
>>
>>> I was wondering if someone could kindly help me figure out how to get
>>> the marginal effects of my conditional logit model.
>>> The syntax I'm using:
>>>
>>> clogit hw cost_ time_ wait_,group(id)
>>> margins cost_ time_ wait_, predict(xb)
>>>
>>> These are logged alt specific variables, but the error STATA keeps on
>>> throwing back at me is:
>>> "cost_:  factor variables may not contain noninteger values"
>>>
>>> However, these are continuous variables and not factor vars. I'm not
>>> sure how exactly to proceed.
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index