[R-SIG-Finance] How to estimate SV type models in R more efficiently?

[qqjwl]

I have attached the code what have made to deal with two factor SV model.
It takes me about 87 minites to finish 2000 interations with 1000 data which is too slow compare with other people who have done this kind of model with other language. I don't know why and very confused about it. Looking forward to get your help. Thank you very much! 
 
Yours,
Liya



在2009-12-23，"Brian G. Peterson" <brian at braverock.com> 写道：
>qqjwl wrote:
>> Hello everyone,
>>     It seems that the estimation of the stochastic volatility model is inefficient in R. 
> > Is there a function in R to estimate these kind of model such as the paper
> > of Kim and Shephard(1998) "Stochastic volatility: likelihood inference and 
>comparison with ARCH models" ?
> > Thank you for your attention.
>
>Liya,
>
>What, specifically, have you tried that seems to you to be inefficient?
>
>Please provide references to code and packages that you have tried.  That makes 
>it much easier for someone else to help you out.
>
>I do not immediately recall the paper you reference, but I have estimated many 
>different kinds of volatility models in R, and have usually been able to 
>accomplish what I needed to.  There are a multitude of [G/AP]ARCH models 
>available in R, which ones have you tried? What specific problems did you 
>encounter?
>
>Regards,
>
>     - Brian
>
>-- 
>Brian G. Peterson
>http://braverock.com/brian/
>Ph: 773-459-4973
>IM: bgpbraverock
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20091224/5894b476/attachment.html>
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: Two scale SV model.txt
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20091224/5894b476/attachment.txt>