Re: st: qcount convergence

[Alfonso Miranda <A.Miranda@ioe.ac.uk>]

Dear Barbara,

I did not added a convergence check after the quantile regression...thanks
for the point. It should be easy to add this feature and then tell qcount to
discard the current draw if it the quantile regression does not converge.

I'll fix this problem soon...it may take some time though as at the moment I
have to meet some tight deadlines.

Best wishes,

Alfonso.






On 05/01/2011 16:12, "Grave, Barbara" <barbara.grave@rwi-essen.de> wrote:

> Dear Statalist,
> 
> I am using qcount, a command that estimates quantile regression for discrete
> data (the command is based on quantile regression models for count data using
> the jittering method
> suggested by Machando and Santos Silva (2005), Quantiles for Counts, Journal
> of the American Statistical Association 100, 1226-1237.
> The idea is to add a random variable to the discrete outcome to smooth the
> distribution.
> I have a problem with the replications. In some estimations for at least one
> replication no convergence can be reached. I know that for the bootstrap
> command there exists a subcommand that solve the problem by excluding
> replications that do not converge. Is there also a solution for the qcount
> command?
> 
> Thanks,
> Barbara
> 
> Rheinisch-Westfälisches Institut für Wirtschaftsforschung e.V. (RWI)
> Hohenzollernstr. 1-3
> D-45128 Essen
> 
> Phone: +49-201-8149-0
> Fax: +49-201-8149-200
> Web: www.rwi-essen.de
> 
> Executive Board/Vorstand: Prof. Dr. Christoph M. Schmidt, (Präsident),
> Prof. Dr. Thomas K. Bauer (Vizepräsident), Prof. Dr. Wim Kösters
> Registration-No./VR 1784 beim Amtsgericht Essen
> 
> *
> *   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/