Hello,
Your problem is nto reproducible without the complete "a" dataset.
Regards,
Pascal
Le 23/07/2012 09:49, Ario Ario a ?crit :> Hi all,
>
> I have problem to estimate a SETAR model. I always get an error message.
> Here is the code:
>
> ## there are 4175 observation in the series (a).
>
>> a[1:10,1] [1] 1.496498 1.496602 1.496636 1.496515 1.496515 1.496463
1.496429 1.496549 1.496480
> [10] 1.496498
>
>> library("tsDyn")
>
>> selectSETAR(a, m=2)Using maximum autoregressive order for low regime:
mL = 2
> Using maximum autoregressive order for high regime: mH = 2
> Searching on 1552 possible threshold values within regimes with
> sufficient ( 15% ) number of observations
> Searching on 6208 combinations of thresholds ( 1552 ), thDelay ( 1
> ), mL ( 2 ) and MM ( 2 )
> Results of the grid search for 1 threshold
> thDelay mL mH th pooled-AIC
> 1 0 2 2 1.674402 -43590.12
> 2 0 2 2 1.674218 -43588.81
> 3 0 2 2 1.673758 -43588.24
> 4 0 2 2 1.674011 -43588.19
> 5 0 2 2 1.674480 -43587.85
> 6 0 2 2 1.673988 -43587.62
> 7 0 2 2 1.673666 -43587.56
> 8 0 2 2 1.674471 -43587.16
> 9 0 2 2 1.673620 -43586.51
> 10 0 2 2 1.673574 -43585.83
>
>> mod.star <- setar(a, m=2, steps=5, thDelay=0, th=1.674402)Error in
rep(NA, length(x) - length(reg)) : invalid 'times' argument
>
>
> Would someone tell me the meaning of this error message? and how to solve
> the problem?
>
>
> Kind Regards,
> Ario
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
>