I'm trying to learn how to use the dse-package. Doing a stabilitytest on a
model.
I run the test on two models that are identical except for
Model 1: TREND=0
Model 2: TREND=NULL
and find the following difference in output unexpected:
library(dse)
AR=array(c(1,-0.8,-0.15),c(3,1,1))
model=ARMA(A=AR,B=1,TREND=0)
stability(model)
#> Distinct roots of det(A(L)) and moduli are:
#> [,1] [,2]
#>[1,] 1.0000000 1.0000000
#>[2,] 1.0451762 1.0451762
#>[3,] -6.3785096 6.3785096
#>Trend not taken into account: The system is NOT stable.
#>[1] FALSE
#>attr(,"roots")
#> Inverse of distinct roots of det(A(L)) moduli
#>[1,] 1.0000000 1.0000000
#>[2,] 0.9567764 0.9567764
#>[3,] -0.1567764 0.1567764
#>Advarselsbesked:
#>In roots.ARMA(obj, fuzz = fuzz, randomize = FALSE) :
#> Unit roots may need to be added for non-zero trend elements.
AR=array(c(1,-0.8,-0.15),c(3,1,1))
model=ARMA(A=AR,B=1,TREND=NULL)
stability(model)
#>Distinct roots of det(A(L)) and moduli are:
#> [,1] [,2]
#>[1,] 1.0451762 1.0451762
#>[2,] -6.3785096 6.3785096
#>The system is stable.
#>[1] TRUE
#>attr(,"roots")
#> Inverse of distinct roots of det(A(L)) moduli
#>[1,] 0.9567764 0.9567764
#>[2,] -0.1567764 0.1567764
I am using:
R version 3.0.3 (2014-03-06) "Warm Puppy"
Best Regards
Jesper Hybel Pedersen
Denmark
[[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.
