[R] Fitting a modified logistic with glm?

Rubén Roa-Ureta rroa at udec.cl
Sun Nov 9 15:01:09 CET 2008

Mike Lawrence wrote:
> On Sat, Nov 8, 2008 at 3:59 PM, Rubén Roa-Ureta <rroa at udec.cl> wrote:
>> ...
>> The fit is for grouped data.
>> ...
> As illustrated in my example code, I'm not dealing with data that can be
> grouped (x is a continuous random variable).
Four points:
1) I've showed you an approach that you can follow in order to fit a 
modified (custom-made) logistic model, it's up to you to follow this 
approach and modify it accordingly, it was never my intention to give 
you the precise code for your problem (obviously),
2) If you do follow this approach and you keep your predictor 
continuous, you have to change the line of the likelihood definition,
3) If it is really true that your predictor is a *random* variable, then 
you have not a simple glmn (you may have a glmm), and
4) You can always make your continuous predictor categorical, for 
example, as when you make a histogram of said predictor.

More information about the R-help mailing list