Skip to content

estimating non-linear state space models

7 messages · Brian G. Peterson, Robert Iquiapaza, Andreas Betz +1 more

#
Andreas wrote:
You might try posting your code here, and being very specific about what 
help you need.  That way everyone can benefit from an implementation of 
these models in R.

Regards,

   - Brian
#
Just for those interested. The final version of that paper was published in 
Review of Financial Studies 2008 21(1):233-264; doi:10.1093/rfs/hhm049.
Regards

Robert Iquiapaza
ri2162 at columbia.edu

--------------------------------------------------
From: "Brian G. Peterson" <brian at braverock.com>
Sent: Wednesday, July 23, 2008 10:03 AM
To: "r_sig_finance" <r_sig_finance at greenmail.ch>
Cc: <r-sig-finance at stat.math.ethz.ch>
Subject: Re: [R-SIG-Finance] estimating non-linear state space models
#
I had to clean up my EKF code first, after trying many different ideas I ended up with a huge mess... It's still heavily under development, but I think it could serve as a starting point.

 

As I wrote before, state estimation seems to run OK given the true parameters.

 

When I try to estimate the parameters by maximizing the likelihood, I end up with rather random results depending on the initial parameters I start optimizing with.

 

I don't know if there's an error in the calculation of the likelihood, or if I'm just overstraining the ML-method by estimating model parameters and noise variances at the same time. Is this even possible? Or maybe I'm just expecting too precise results...

 

Regards

Andreas

 

 


________________________________

Von: Robert Iquiapaza [mailto:rbali at ufmg.br]
Gesendet: Do 24.07.2008 03:21
An: Andreas
Cc: r-sig-finance at stat.math.ethz.ch
Betreff: Re: [R-SIG-Finance] estimating non-linear state space models



Just for those interested. The final version of that paper was published in
Review of Financial Studies 2008 21(1):233-264; doi:10.1093/rfs/hhm049.
Regards

Robert Iquiapaza
ri2162 at columbia.edu

--------------------------------------------------
From: "Brian G. Peterson" <brian at braverock.com>
Sent: Wednesday, July 23, 2008 10:03 AM
To: "r_sig_finance" <r_sig_finance at greenmail.ch>
Cc: <r-sig-finance at stat.math.ethz.ch>
Subject: Re: [R-SIG-Finance] estimating non-linear state space models
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20080724/b25169e1/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ekf.R
Type: application/octet-stream
Size: 6166 bytes
Desc: ekf.R
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20080724/b25169e1/attachment.obj>
3 days later
#
Have you looked at the 'dlm' package for "Bayesian and Likelihood 
Analysis of Dynamic Linear Models"?  It has optional parameters 'JFF', 
'JV', 'JGG', 'JW', and 'X' to support nonlinear modifications of the 
standard Kalman terms 'm0', 'C0', 'FF', 'V', 'GG', 'W'.  Moreover, it 
has a vignette that helps learning its capabilities.  This should 
support your needs provided the (standardized) residuals can plausibly 
be assumed to be normally distributed. 

      Hope this helps. 
      Spencer
Andreas wrote: