A problem of impulse response function about S-VAR

Dear All,

I would like to use the package "vars" to get a impulse response function of
a Structural VAR model.
However, I got a wrong message and cannot deal with it.
Here is my code:

library(vars)

data  <- read.table("data.txt", header=T)
y1    <- data[,c("log_x1","log_x2","log_x3","log_x4","log_x5","log_x6")]

var01 <- VAR(y1, p=3) 

A <-

as.matrix(rbind(c(NA,0,0,0,0,0),c(NA,NA,0,0,0,0),c(0,0,NA,0,0,0),c(NA,0,NA,NA,0,0),c(NA,NA,NA,0,NA,NA),c(NA,NA,NA,NA,0,NA)))

B <-

as.matrix(rbind(c(NA,0,0,0,0,0),c(0,NA,0,0,0,0),c(0,0,NA,0,0,0),c(0,0,0,NA,0,0),c(0,0,0,0,NA,0),c(0,0,0,0,0,NA)))

svar01 <- SVAR(var01,estmethod="scoring", Amat=A ,Bmat=B) 

svar01.irf <- irf(svar01, response="log_x3", n.ahead=24)

But here is the error message:
 
   `diag<-`(`*tmp*`, value = 1) : 
    only matrix diagonals can be replaced

So I cannot get the impulse response function of  this S-VAR model. 
How should I deal with it?

Many thanks for your time and help!


Chu, Hao-pang
97258031 at nccu.edu.tw
 



--
View this message in context: http://r.789695.n4.nabble.com/A-problem-of-impulse-response-function-about-S-VAR-tp4642990.html
Sent from the R help mailing list archive at Nabble.com.