[R] multinomial conditional logit models

[John Hendrickx]

--- Friedrich.Leisch at univie.ac.at wrote:
> >>>>> On Wed, 29 Jan 2003 11:57:20 -0800 (PST),
> >>>>> John Hendrickx (JH) wrote:
> 
[snip]
>   > To estimate an MCL model, the data must be restructured into a
>   > person-choice file. 
> 
>   > * Each case must be duplicated "ncat" times ("ncat" is the
> number of
>   > categories of the dependent variable)
>   > * Each case must be identified by a strata variable (id)
>   > * Each duplicate must be identified by a variable indexing the
>   > choices (newy)
>   > * A dichotomous variable must indicate which duplicate
> corresponds
>   > with the respondent's choice (didep)
> 
> I'm not completely sure if I understand your target format
> completely,
> but it sounds like reshape() could do all you want:
> 
> 
> R> df3
>   id age dose1 dose2 dose4
> 1  1  40     1     2     3
> 2  2  50     2     1     3
> 3  3  60     1     2     3
> 4  4  50     2     1     3
> 
> 
> 
> R> reshape(df3, direction = "long", idvar=1,
>            varying=list(dose=c("dose1", "dose2", "dose4")))
> 
>     id age time dose1
> 1.1  1  40    1     1
> 2.1  2  50    1     2
> 3.1  3  60    1     1
> 4.1  4  50    1     2
> 1.2  1  40    2     2
> 2.2  2  50    2     1
> 3.2  3  60    2     2
> 4.2  4  50    2     1
> 1.3  1  40    3     3
> 2.3  2  50    3     3
> 3.3  3  60    3     3
> 4.3  4  50    3     3
> 
What I want can be done using "reshape" in conjunction with "rep". My
data structure isn't wide but can be made so using "rep". For
example:

> dataset=matrix(1:6,3,2)
> dset<-data.frame(dataset)
> dset
  X1 X2
1  1  4
2  2  5
3  3  6
> c<-as.data.frame(rep(dset,2))
>
reshape(c,direction="long",varying=list(x1=c("X1","X1"),x2=c("X2","X2")))
    time X1 X2 id
1.1    1  1  4  1
2.1    1  2  5  2
3.1    1  3  6  3
1.2    2  1  4  1
2.2    2  2  5  2
3.2    2  3  6  3

This is what I want to do when creating a person-choice file. The
only problem though is the last step, specifying a list of varying
variables. It should be possible to generate this from "names(dset)"
but I can't get it right. "as.list(rep(names(dset),2))" produces a
list with four elements rather than a list with 2 components each
containing two elements. "dim()" gives a matrix as a result. Could
someone show me how to create "list(x1=c("X1","X1"),x2=c("X2","X2"))"
from "names(dset)"?

Advance thanks for any help,
John Hendrickx