R help - Sep 1998 - R-beta: port of bicreg package to R?

R version: 0.62.1  (June 15, 1998)

I just very naively attempted to grab the 'bicreg' package for
Bayesian model selection from the StatLib library, and get it running
under R.

I've hit a brick wall very quickly, and as an R novice I'm not sure
where to go next.

Here's what happened:
> bicreg(as.matrix(hiv[,c(-17,-18)]),as.matrix(hiv[,18]))
Error: invalid formula
> traceback()
[1] "stop(\"invalid formula\")"
[2] "switch(mode(x), NULL = structure(NULL, class = \"formula\"),
character = formula(eval(parse(text = x)[[1]])), "
[3] "\t    call = eval(x), stop(\"invalid formula\"))"
[4] "formula.default(cdf)"
[5] "model.matrix(formula(cdf), data = cdf)"
[6] "bicreg(as.matrix(hiv[, c(-17, -18)]), as.matrix(hiv[, 18]))"
The relevant lines of code in 'bicreg' would appear to be

[...]
  cdf <-cbind.data.frame(y=y,x)
  mm <- model.matrix(formula(cdf),data=cdf)[,-1,drop=F]
[...]

It appears to me that applying formula() to the matrix is a no-no. Is
this an incompatibility between Splus and R?

Has anyone already succeeded in porting this package to R?

Or am I just doing something silly?

thanks in advance,

Malcolm
--
Malcolm Gillies <M.B.Gillies at pharm.uu.nl>
PhD student, computational medicinal chemistry
Dept Medicinal Chemistry, Faculty of Pharmacy,
Utrecht University, The Netherlands
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

On Tue, 22 Sep 1998, Malcolm Gillies wrote:
> R version: 0.62.1  (June 15, 1998)
> 
> I just very naively attempted to grab the 'bicreg' package for
> Bayesian model selection from the StatLib library, and get it running
> under R.
> 
> I've hit a brick wall very quickly, and as an R novice I'm not sure
> where to go next.
> 
> The relevant lines of code in 'bicreg' would appear to be
> 
> [...]
>   cdf <-cbind.data.frame(y=y,x)
>   mm <- model.matrix(formula(cdf),data=cdf)[,-1,drop=F]
> [...]
> 
> It appears to me that applying formula() to the matrix is a no-no. Is
> this an incompatibility between Splus and R?
Here's a formula method for data.frame that you can put in the function to
allow formula(cdf)

 formula.data.frame<- function (df) 
{
            nm <- sapply(names(df), as.name)
            lhs <- nm[1]
            if (length(nm) > 1) {
                    rhs <- nm[-1]
            }
            else {
                    rhs <- nm[1]
                    lhs <- NULL
            }
            ff <- parse(text = paste(lhs, paste(rhs, collapse =
"+"),
                    sep = "~"))
            eval(ff)
}


	-thomas

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._