4

I want to restrict some cofficients in plm model in R. For example, if I have such a model:

library(plm) 
data("Produc", package = "plm")
zz <- plm(log(gsp) ~ log(pcap) + log(pc) + log(emp) + unemp,
      data = Produc, index = c("state","year"))

How I can set coefficient of log(pcap) to -0.05?
There are arguments like restrict.matrix and restrict.rhs in plm, but they do not work.
I have allready written codes that I extensively use for data modeling - plm object is used for forecasting and testing, so I would like a solution, that works with plm object directly and could be used further in my codes.

Thanks ahead of time for any help!

bluecat
  • 41
  • 4
  • Can you say what you mean when you say that `restrict.matrix` and `restrict.rhs` "do not work"? I have been experimenting with them, and they do not seem to do anything at all. Plus the documentation says almost nothing about them. – randy Oct 05 '15 at 23:47
  • "Do not work": do not produce any results; do not have any effect on model coefficients. – bluecat Oct 22 '15 at 06:33
  • From personal correspondence with the author of plm(): "You're right, restrict.matrix is only implemented in plm for system of equations (especially for SURE models), and not for single equations in plm. I'll try to implement this feature as soon as possible" – randy Feb 07 '16 at 19:51
  • Any updates on this feature? – RegressForward Nov 07 '22 at 19:34

0 Answers0