[R] error in mixed logit model using mlogit function

danielle martidan at umich.edu
Wed May 14 09:26:57 CEST 2014


Dear all,

I am trying to estimate an mlm with 8 alternatives, but I received the
following error message:

Error in `colnames<-`(`*tmp*`, value = "disto.disto") : 
  attempt to set colnames on object with less than two dimensions

My data look like this:

> head(dtb)
  votechoice disto.CVP disto.FDP disto.GPS disto.LPS disto.PBD  disto.SP
disto.SVP  disto.VL risk
1        GPS 1.3797308 2.1734424 0.7447605 2.7584803 2.1036997 1.2393141 
4.320573 0.7027443    9
2        SVP 1.6202692 0.8265576 3.7447605 0.2415197 0.8963003 4.2393141 
1.320573 2.2972557    2
3        CVP 0.6202692 0.1734424 2.7447605 0.7584803 0.1036997 3.2393141 
2.320573 1.2972557    3
4        SVP 4.6202692 3.8265576 6.7447605 3.2415197 3.8963003 7.2393141 
1.679427 5.2972557    9
5        SVP 2.6202692 1.8265576 4.7447605 1.2415197 1.8963003 5.2393141 
0.320573 3.2972557    6
6        GPS 2.3797308 3.1734424 0.2552395 3.7584803 3.1036997 0.2393141 
5.320573 1.7027443    4

When I estimate a simple logit model it is working:

rpl2 <- mlogit(votechoice ~ disto | risk,data=newdtb, shape =
'wide',varying=2:9,	correlation=T,
	halton = NA,R = 10, tol = 10, print.level = 0);summary(rpl2)

but when I am trying to estimate an mlm, I get the following: 

> rpl2 <- mlogit(votechoice ~ disto | risk,data=newdtb, shape =
> 'wide',varying=2:9,correlation=T,
+ rpar=c(disto='l'),halton = NA,R = 10, tol = 10, print.level = 2)

Error in `colnames<-`(`*tmp*`, value = "disto.disto") : 
  attempt to set colnames on object with less than two dimensions


I would be grateful for any help, thanks for reading this post.
danielle







--
View this message in context: http://r.789695.n4.nabble.com/error-in-mixed-logit-model-using-mlogit-function-tp4690489.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list