[Scilab-users] Grocer - Markov Switching model estimation

[Éric Dubois]

Hello Christian.

The fact that your data are annuel does not have any influence except for the definition of the bounds if your data are Grocer Time series and you do not want to use the maximum time span.

If your data are called mydata and whethrer they are Grocer Time series or a vector, then you may run:
--> r=ms_var('all',1,mydata,2,2,1)

(Run : Help ms_var for détails)

Éric

Envoyé de mon iPhone

> Le 13 juin 2015 à 01:53, Cristian <c_rabanal0 at yahoo.com.ar> a écrit :
> 
> Hello everyone, I try to estimate a MS with Grocer . I have *annual data*. I
> have read the chapter 23 (manual), where I found an perfect example for
> quartely data. Even though, I have alredy a doubt. 
> 
> The chapter 23 gives us an example to etimate a MS-AR(3). The specification
> is the following:
> 
> r=ms_reg('100*(lpbi-lagts(2,lpbi))',['100*(lagts(1,lpbi)-lagts(3,lpbi))';...
> -->'100*(lagts(2,lpbi)-lagts(4,lpbi))';'100*(lagts(3,lpbi)-lagts(5,lpbi))'],'cte',nb_states,switch_var,var_opt,'transf=stud',...
> -->'prt=initial;final')
> 
> So, the question is: How should I modify that expression in order to
> estimate a MS-AR(1) with anual data? 
> 
> Thanks in advance
> 
> Cristian
> 
> 
> 
> --
> View this message in context: http://mailinglists.scilab.org/Grocer-Markov-Switching-model-estimation-tp4032440.html
> Sent from the Scilab users - Mailing Lists Archives mailing list archive at Nabble.com.
> _______________________________________________
> users mailing list
> users at lists.scilab.org
> http://lists.scilab.org/mailman/listinfo/users