mlogit

Looks like a problem that the maintainer should be copied with:

 > maintainer("mlogit")

[1] "Yves Croissant <yves.croissant at let.ish-lyon.cnrs.fr>"

Not sure why it should affect your systems and not mine, but here is my
sessionInfo() if it helps:

 > sessionInfo()

R version 2.10.1 RC (2009-12-09 r50695)
x86_64-apple-darwin9.8.0

locale:
[1] en_US.UTF-8/en_US.UTF-8/C/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] splines stats graphics grDevices utils datasets methods
[8] base

other attached packages:
[1] mlogit_0.1-2 maxLik_0.6-0 mgcv_1.6-1 gdata_2.6.1
[5] Design_2.3-0 Hmisc_3.7-0 survival_2.35-7 chron_2.3-33

loaded via a namespace (and not attached):
[1] cluster_1.12.1 grid_2.10.1 gtools_2.6.1 lattice_0.17-26
[5] Matrix_0.999375-32 nlme_3.1-96 tools_2.10.1

On Mar 7, 2010, at 12:50 PM, Peter Ehlers wrote:

On 2010-03-07 10:30, David Winsemius wrote:

On Mar 7, 2010, at 12:06 PM, cmc wrote:

I am trying to follow this example for multinomial logistic regression

http://www.ats.ucla.edu/stat/r/dae/mlogit.htm

However, I cannot get it to work properly.

This is the output I get, and I get an error when I try to use the
mlogit
function. Any ideas as to why this happens?

mydata <-
read.csv(url("http://www.ats.ucla.edu/stat/r/dae/mlogit.csv"))
attach(mydata)
names(mydata)

[1] "brand" "female" "age"

library(mlogit)

Loading required package: Formula
Loading required package: statmod

mydata[1:10,]

brand female age
1 1 0 24
2 1 0 26
3 1 0 26
4 1 1 27
5 1 1 27
6 3 1 27
7 1 0 27
8 1 0 27
9 1 1 27
10 1 0 27

mydata$brand<-as.factor(mydata$brand)
mldata<-mlogit.data(mydata, varying=NULL, choice="brand",
shape="wide")

mldata[1:10,]

You do not get the same result as the example page, (while I do). You
need to see if you have other objects with names that may be confusing
the interpreter. I did not attach() mydata, which despite the UCLA's use
of it is considered bad practice in R programming because of frequent
obscure bugs that trip up newbies such as us. The errors do not occur
when the next commands are run.

I do get the same error (I didn't use attach() either), but I
can avoid the error if I don't call the mlogit.data() output
'mldata'. This seems to be a hardcoded name in mlogit() which
appears to cause the problem. This works:

mdata<-mlogit.data(mydata, varying=NULL, choice="brand", shape="wide")
mlogit.model<- mlogit(brand~1|female+age, data = mdata, reflevel="1")

-Peter Ehlers

brand female age
1.1 TRUE 0 24
1.2 FALSE 0 24
1.3 FALSE 0 24
2.1 TRUE 0 26
2.2 FALSE 0 26
2.3 FALSE 0 26
3.1 TRUE 0 26
3.2 FALSE 0 26
3.3 FALSE 0 26
4.1 TRUE 1 27

mlogit.model<- mlogit(brand~1|female+age, data = mldata, reflevel="1")

Error in as.data.frame.default(data) :
cannot coerce class "call" into a data.frame

summary(mlogit.model)

Error in summary(mlogit.model) : object 'mlogit.model' not found

--

David Winsemius, MD
West Hartford, CT

--
Peter Ehlers
University of Calgary

David Winsemius, MD
West Hartford, CT