Dear All,
I am running the mvProbit model to estimate five equation probit models. In
my data all the dependent variables are dichotomous with values 0/1 and
lables TRUE/FALSE. The explanatory variables are composed of catagorical
and countinous variables. I specified the model as follows
Result<-mvProbit( cbind(y1,y2,y3,y4,y5) ~ x1+x2+x3+......+.x11,data=mydata)
summary(Result)
However, i get an error message "...Error in mvProbit(cbind(y1,y2,y3,y4,y5)
~:all dependent variables must be either 0,1,TRUE, or FALSE)
I have checked all the dependent variables and it is coded 0/1 and lables
TRUE/FALSE.
Ofcourse there are two missing observation and I attempted to handle that
with na.action=na.omit but even that didnt solve the problem. My second
attempt was to tell r that the dichotomous dependent variables and the
catagorical independent variables as factor as follows
mydata$y1<-factor(mydata$y1)
...
...
..
.
mydata$x3<-factor(mydata$x3)
But still problem not solved. How would I solve this problem?
Thank you!
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
