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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: too good to be true : lr test in mlogit?


From   John Litfiba <cariboupad@gmx.fr>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: too good to be true : lr test in mlogit?
Date   Mon, 16 May 2011 16:09:01 +0200

Hello Joerg,

Thank you for your answer

My data is organized as follows (simplified)

id1 year1 age type outcome
id1 year1 age type outcome
id1 year2 age type outcome
id1 year3 age type outcome
id2 year4 age type outcome
id3 year2 age type outcome
id3 year5 age type outcome


For example, lets say the outcome is a trading decision (Buy or Sell)
and I want to estimate the effect of age and type (Good or Bad) on
that decision.
Some individuals may trade just once and others may trade several
times per year. The total number of trade thus vary per individuals
(in the above example individual 1 has made 4 trade, while individual
1 juste one)

The outcome is the same for each individuals (Buy or Sell)
Type vary with the observation (today I can be BAD and tomorrow GOOD)
but it is likely that type is correlated within clusters of id...
Age vary of course with year

Applying a mlogit with "mlogit outcome age type" , cluster(id) works
fine but I cannot run xtlogit (I write before that the command XTSET
id in order to make stata understand the panel dataset)
What do you think ?

Best Regards,


On 16 May 2011 15:38, Joerg Luedicke <joerg.luedicke@gmail.com> wrote:
>
> Hi John,
>
> Could you explain a little bit what your data looks like? It looks as
> if you have observations nested within subjects, correct? What are
> those observations and what are your subjects then? I have a slight
> hunch that you want to run a 2-level model (Level 2 being whatever
> your variable "id" is referring to, and Level 1 the however structured
>  observations within "id") and that you are trying to predict an
> outcome on Level 2 with Level 1 predictors or something like that.
>
> J.
>
> On Mon, May 16, 2011 at 7:11 AM, John Litfiba <cariboupad@gmx.fr> wrote:
> > Dear Maarten yes the variable is correctly coded with 1 and 0 (you
> > probably miss my previous mail ;-) )
> > Thank you for the advice, I will contact the tech support to see whats
> > wrong here
> >
> > Best Regards,
> >
> >
> > On 16 May 2011 12:30, Maarten Buis <maartenlbuis@gmail.com> wrote:
> >> On Mon, May 16, 2011 at 12:02 PM, John Litfiba <cariboupad@gmx.fr> wrote:
> >>> Well, when I run a xtlogit (I first type xtset id, where id is the
> >>> unique id for each of my individual in my database) with on year of
> >>> data (1million) observations I get the message
> >>>
> >>> Yvar is categorical (Yes=1, No=0) and Xvar is also categorical
> >>> (type1=1, type2=2)
> >>
> >> I would recode Xvar to such that type1 = 0 and type2 = 1:
> >> gen byte type2 = Xvar - 1
> >>
> >> Remember that with fixed or random effects models you are making an
> >> additional model for the group specific constants. It often helps when
> >> these group specific constant refer to groups that actually occur in
> >> the data.
> >>
> >> the logic of calling this variable type2 rather than Xvar is that the
> >> value 1 is often associated with "true" and 0 with "false", so I think
> >> of a variable named type2 as posing a question to each observation
> >> "are you type2?", the answer being either true (1) or false (0).
> >>
> >> If recoding your explanatory variable does not work I would contact
> >> Stata's techsupport, as these results suggest that there is something
> >> logically wrong with the model you are trying to estimate, so ad-hoc
> >> solutions like sampling from your data are not advisable until you
> >> understand where the problem comes from. For how to contact Stata's
> >> techsupport, see: http://www.stata.com/support/tech-support/
> >>
> >> Hope this helps,
> >> Maarten
> >>
> >> --------------------------
> >> Maarten L. Buis
> >> Institut fuer Soziologie
> >> Universitaet Tuebingen
> >> Wilhelmstrasse 36
> >> 72074 Tuebingen
> >> Germany
> >>
> >>
> >> http://www.maartenbuis.nl
> >> --------------------------
> >> *
> >> *   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/

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