Dear all
I am working on a paper where I am analysing energy-non energy substitution
possibilities in a manufacturing sector. In this case, I am estimating a
translog cost function jointly with factor share equations under SUR
modeling.
The estimation requires me to impose linear homogeneity restrictions, where
coefficients of price variables are required to sum to one as other
coefficients sum to zero. Below are my R commands for this estimation:
D<-c("q1_lnPk + q1_lnPl + q1_lnPe =1", "q1_lnq + q1_lnPklnPk + q1_lnPllnPl
+ q1_lnPelnPe + q1_lnqlnq + q1_lnPklnPl + q1_lnPklnPe + q1_lnPllnPe +
q1_lnPklnq + q1_lnPllnq + q1_lnPelnq=0")
z<-plm(list(q1=lnTC ~ lnPk + lnPl + lnPe + lnq + lnPklnPk + lnPllnPl +
lnPelnPe + lnqlnq + lnPklnPl + lnPklnPe + lnPllnPe + lnPklnq + lnPllnq +
lnPelnq,
q2= Sl ~ slnpl +slnpe +lnq,
q3= Se ~ slnpl+ slnpe+ lnq), Surpanel, effect = "twoways",
restrict.matrix = D, model="pooling" )
summary(z)
The first line of the commands indicates the matrix of restrictions, the
second line indicates the formula and the third line indicates the summary
of findings.
However, after running the commands, I am getting the following error:
*Error in rep(0, nrow(restrict.matrix)) : invalid 'times' argument*
Please help me in getting a solution to this error.
Regards,
Kigundu Ken
[[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.
