st: Re: nested logit with only individual characteristics

["R.E. De Hoyos" <redeho@hotmail.com>]

Dear Fanwell,

You can estimate the -nlogit- transforming the data in a way that it is 
suitable for -clogit- and then using a set of dummy variable interactions as 
explained in:

http://www.ats.ucla.edu/stat/stata/examples/greene/greene19.htm

However I think you should reconsider if -nlogit- is the model that fits 
best your data. For a similar exercise estimating British poverty entry 
rates, see:

Cappellari and Jenkins (2002) "Who stays poor? Who becomes poor? Evidence 
from the British household panel survey", The Economic Journal, 112(478)

Best,
Rafa


----- Original Message ----- 
From: "Fanwell Kenala Bokosi" <fanwellbokosi@onetel.net>
To: <statalist@hsphsun2.harvard.edu>
Sent: Tuesday, December 20, 2005 3:54 PM
Subject: st: nested logit with only individual characteristics



> Dear Listers,
>
> I am trying to estimate a nested logit with data that has only indivudual 
> characteristics.
>
> I have a data set of 291 households with househoold characteristics and 
> their poverty statsu in two period.
>
> The dependent variable is 1=poor and 0=non poor for both years. I want to 
> estimate the probaliity of being poor in the secons period given the 
> povery status of the first period.
>
> The tree structure is as follows:
>
> pooryr1 (pooryr2, nonpooryr2)
> Nonpooryr1(pooryr2, nonpooryr2)
>
> The household characteristics include rnd1qno ageh hhize landarea children 
> etc
>
> the group variable is rnd1qno
>
> I do not know how I should set the command since I do not have any choice 
> related independent variables
>
> Please help
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/