You will need to write your own functions for likelihood. Then AIC and BIC are 
straight forward once you have log-likelihood. This will be a pretty tedious 
process as for GBM log-likelihood will be straight forward, for 
mean-reversion… its in principal similar to arma, however never had to do it 
myself, don't think its easy. Anyways, I would recommend comparing simulated 
distributions rather than log-likelihoods.


Kind regards,--  
Dominykas Grigonis


On Saturday, 15 June 2013 at 17:24, ousbens wrote:

> I would like to find out if a GBM (Geometric Brownian motion) process or a
> mean reverting Ornstein-Uhlenbeck (OU) process fits better to a time series.
>  
> To determine this I would like to calculate the AIC, BIC and Log Likelihood
> values for the GBM and OU processes (and also for a simple Jump diffusion
> process).
>  
> How can this be done in R?
>  
> Many thanks.  
>  
>  
>  
> --
> View this message in context: 
> http://r.789695.n4.nabble.com/How-to-calculate-AIC-and-BIC-for-GBM-and-OU-processes-in-R-tp4669607.html
> Sent from the Rmetrics mailing list archive at Nabble.com (http://Nabble.com).
>  
> _______________________________________________
> [email protected] (mailto:[email protected]) mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions 
> should go.
>  
>  



        [[alternative HTML version deleted]]

_______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should 
go.

Reply via email to