[R] Modelling Question

[Jim Lindsey]

> 
> Hello:
> 
> I want to fit a model to count data where many counts are zero.  I would
> like to posit that the baseline value of an immunologic marker impacts
> whether or not a patient experiences any events at all, and the conditional
> (on being  > 0) expectation of the remaining counts as a function of the
> percent inhibition of the immunologic marker.  I guess I want to use a
> logistic model for the probability of experiencing any events, and a Poisson
> model for the conditional expectation.  This sounds like it should be a
> familiar problem.  Before I try writing down and maximizing the likelihood
> myself, can someone point me in a simpler direction?  Thanks in advance for
> any help.

The fmr function in my gnlm library
(www.luc.ac.be/~jlindsey/rcode.html)
does a two-point finite mixture where you can have a logistic model of
having an event or not combined with Poisson for the number of events.
  Jim

> 
> Tom Richards
> 
> P.S., Sorry about a potential cross-posting to S-news, but I just got a
> weird "stalled, non-member posting" message from there.  I thought I was a
> member of S-news, but apparently something went wrong recently for me.
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
> 

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._