Is "B" a reserve word in vars package?
I tried to run an SVAR-AB model by SVAR function and find the IRF in vars
package. The problem is that when B matrix is named by "B", an error
message occurs. However, if the same matrix is named by "Bm", then things
run smoothly. What's wrong? Is "B" a reserve word in vars package?
> Amatexo
[,1] [,2]
[1,] 1 0
[2,] NA 1
> Bm
[,1] [,2]
[1,] NA 0
[2,] 0 NA
> B<-Bm
> B
[,1] [,2]
[1,] NA 0
[2,] 0 NA
> svar.Aexo<-SVAR(var_dl, estmethod ="direct", Amat=Amatexo,
Bmat=Bm,hessian=TRUE)
Warning message:
In SVAR(var_dl, estmethod = "direct", Amat = Amatexo, Bmat = Bm, :
The AB-model is just identified. No test possible.
> irf.svaraexo<-irf(svar.Aexo, boot=TRUE, n.ahead=12)
There were 50 or more warnings (use warnings() to see the first 50)
> svar.Aexo<-SVAR(var_dl, estmethod ="direct", Amat=Amatexo,
Bmat=B,hessian=TRUE)
Warning message:
In SVAR(var_dl, estmethod = "direct", Amat = Amatexo, Bmat = B, :
The AB-model is just identified. No test possible.
> irf.svaraexo<-irf(svar.Aexo, boot=TRUE, n.ahead=12)
Error in determinant.matrix(x, logarithm = TRUE, ...) :
'x' must be a square matrix
In addition: Warning message:
In optim(start, logLc, ...) :
one-dimensional optimization by Nelder-Mead is unreliable:
use "Brent" or optimize() directly
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
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.
