[R] How can I do a generic specification in multiple logistic regression

[Juliet Hannah]

Is multinom the function you are looking for?

library(nnet)
library(MASS)

?multinom indicates that this
fits multinomial log-linear models. If you are looking for multiple
logistic regression
you may want to read up on glm or lrm from the Design package.

Could you elaborate on what you mean by a generic coefficient?

Best,

Juliet

On Fri, Aug 14, 2009 at 3:46 AM, Benjamin Geckle<dittogag at yahoo.de> wrote:
> I use the function multinom to estimate a multiple logistic regression. but
> I need one coefficient as generic. How can I do this? Or is it possible to
> do this with an another function?
>
>
>
> As example  this is what I get:
>
>
> Call:
>
> multinom(formula = choice ~ time + costs, data = DATA)
>
>
>
> Coefficients:
>
>  (Intercept)        time             costs
>
> 1    4.79            -0.28          -3.97
>
> 2   -3.30             0.053         0.59
>
> 3    2.10            -0.048        -0.65
>
>
>
> But I would like to get the costs parameters as generic attribute, so that I
> have the following result:
>
> Coefficients:
>
>  (Intercept)        time           costs
>
> 1    4.79            -0.3            -1.8
>
> 2   -3.36             0.4            -1.8
>
> 3    2.10            -0.5            -1.8
>
>
>
>
> Thank you for you help.
>
> Best Regards
>
> Benjamin
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>