Hi,
I am trying to use mlogit in R to analyse a block design choice experiment
dataset. The 12 choice sets/cards have been randomly assigned to 3
different blocks and each respondent answers all sets from one block (i.e.
each respondent chooses from 4 choice sets). In total I have 2336 rows of
data from 292 respondents. The data looks like this (2 of the three
blocks):
ID Sex Age Block Card Alt x1 x2 x3 x4 choice
1 0 65 1 4 1 0 1 1 1 0
1 0 65 1 4 2 0 0 0 0 1
1 0 65 1 7 1 1 0 1 0 0
1 0 65 1 7 2 1 2 0 1 1
1 0 65 1 10 1 1 1 0 1 1
1 0 65 1 10 2 0 2 1 0 0
1 0 65 1 12 1 1 2 0 0 0
1 0 65 1 12 2 1 0 1 1 1
2 1 35 2 2 1 0 2 0 0 0
2 1 35 2 2 2 0 0 1 1 1
2 1 35 2 8 1 0 1 0 1 1
2 1 35 2 8 2 0 1 1 0 0
2 1 35 2 9 1 0 1 0 1 0
2 1 35 2 9 2 1 1 0 0 1
2 1 35 2 11 1 0 0 1 0 0
2 1 35 2 11 2 1 2 0 1 1
I have tried the following codes to set the data for mlogit and run the
model:
T1m<-mlogit.data(T1,shape="long",choice="choice",alt.var="Alt")
m1=mlogit(choice~x1+x2+x3+x4|Age+Sex, data=T1m)
I am getting the following error:
Error in if (abs(x - oldx) < ftol) { : missing value where TRUE/FALSE
needed
I have gone through the data and found no missing values.
Please advice if the codes I have used are appropriate and what is going
wrong.
Thanks in advance,
abimoss
[[alternative HTML version deleted]]
