Respected Maarten,
Thanks for your kind help. i have some more questions: I am doing
analysis for consumers willingness to pay (WTP) using double bounded
contingent valuation method (CVM). i have used sample N= 80, and i
have 4 subgroups of 20 each. i want to use intreg for this subgroups,
is it possible to use intreg to get mean WTP. i have tried but got
very small log-likelihood value of -8.34 as i said. Is it fine to use
it and how many independent variables i should use. or what other
method i should use.
i know that i am asking too many questions, but i do not have any
option. yours help will be great help for me.
Thanking you,
On Wed, Oct 14, 2009 at 9:32 AM, Maarten buis <[email protected]> wrote:
> --- On Tue, 13/10/09, dk wrote:
>> Can i use interval regression(intreg) for N= 18. i tried to
>> use it and got - 8.3467 log-likelihood value, is it fine if
>> we get this low value.
>
> With only 18 observations I wouldn't do anything other than
> simple describtive statistics, I might do a normal regression
> -regress- with one or maybe two explanatory variables, but
> I wouldn't do anything more complex like -intreg-. Having
> said that, I don't think that a log-likelihood of -8 is an
> exceptionaly small number for a log likelihood, even with
> only 18 observations.
>
> 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/
