Bug in loglin with variable called "c" (PR#198)
Summary: loglin will fail if there is a global variable called c. I have fixed this for 0.64.2 and 0.65.
On Sat, 22 May 1999, Cor en Aylin wrote:
Dear Brian, Using the mass library for R (the most recent port dated 16 may 1999) I
Could you give version numbers in such reports please: at the moment there is an official version (5.3pl037) of MASS for R, plus a pre-release of MASS for V&R3, and you seem to be using the latter. That is _not_ the most recent port: it is a different major version (6.1 not 5.3) and please don't use it unless you like testing pre-release software. BTW, the name is MASS, not mass or Mass: it is an acronym.
have encountered a minor problem you might want to be informed about : If used the following command: mydata.loglm <- loglm(n~ s+c+m, mydata) I got an the following error : Error in get(x, envir, mode, inherits) : variable "FUN" was not found traceback() [1] "get(as.character(f), mode = \"function\")" [2] "match.fun(FUN)" [3] "lapply(y, c, x[i])" [4] "subsets(margin[[k]])" [5] "loglin(data, margins, start = start, fit = fitted, param = param, " [6] " eps = eps, iter = iter, print = print)" [7] "loglm1.default(formula, data, ..., start = st)" [8] "loglm1.data.frame(formula, data, ...)" [9] "loglm(n ~ s + m + c, mydata )" Trying to see where the problem sits within loglin I saw that (line 3 of traceback) variable "c" is used in lapply, and since my data-variable also is called "c" mine was used instead (wrongly). I understood the message and I think that I better not use often uses variable-names (a..z) as names for my data-vars.
The problem is not in MASS: it is occurring in the R version of loglin. To reproduce this I have to have a global variable c, not a column c in the dataframe. So that is the workaround: make your variables columns in mydata. Here is a example: library(MASS) data(quine) c <- quine$Eth loglm(Days ~ .^2, quine) To fix this in R, the line in loglin needs to be lapply(y, "c", x[i]). Kurt: do you want explicitly to get c() from package:base here, to be safer, or would that be too restrictive?
Brian D. Ripley, ripley@stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272860 (secr) Oxford OX1 3TG, UK Fax: +44 1865 272595 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-devel 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-devel-request@stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._