Tell me more ×
Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. It's 100% free, no registration required.
up vote 17 down vote favorite
8

Are there libraries in R for estimating time-varying joint distributions via copulas?

Hedibert Lopes has an excellent paper on the topic here. I know there is an existing packaged called copula but it fits a static copula.

share|improve this question
2  
if i have time over the summer i can implement this myself it sounds like a good project – pyCthon Mar 5 '12 at 17:42
1  
This was similar stats.stackexchange.com/questions/19431/… but probably not that helpful, as I think Quant Guy actually answered that question! – Feral Oink Mar 7 '12 at 4:16
@FeralOink - ha! Thanks but unfortunately that link isn't a solution – Quant Guy Mar 7 '12 at 4:36
I kind of suspected as much! Would it be useful to you if I listed some R libraries that have been used for the purpose of estimating time varying joint distributions for/ via copulas that I haven't used personally? I have a few in mind, from citations in papers. – Feral Oink Mar 7 '12 at 4:40
1  
So what happened? – Bob Jansen Mar 31 '12 at 16:41
show 2 more comments

2 Answers

up vote 3 down vote accepted
+50

I think an extremely interesting strand of research on this topic is represented by extensions of vine copulas with time-varying parameters.

For vine copulas in general have a look at this site from the Technische Universität München:
Vine Copula Models

One of their research projects, which is the most relevant in this context, is:
Time varying vine copula models

It is well worth keeping an eye on since they implement their research models in R, concerning the current status of the implementation please have a look at this presentation here:
CDVine: An R-package for statistical inference of C- and D-vines

You'll find the respective package CDVine on CRAN: Here

The vignette can be found in the Journal of Statistical Software.

(I will update this post when the new code for the time-varying parameters becomes available.)

share|improve this answer
up vote 2 down vote

Once we start building time-varying copulas like Lopes suggests in that paper, I think we are better off venturing into the world of state space models. When viewed in a bayesian context, the similarities between the approaches are striking to me. The advantage of the copula, as I understand it, is that it is a quick and dirty way to understand the structure of your marginal distributions by simplifying the dependence structure over time.

I did not find anything in the Lopes paper to suggest what algo he uses to estimate the params of his time-varying copulas and marginals, but I expect that this is done using something like a forward/backward algorithm (used in ssm estimation) since he mentions that the marginals and copulas are estimated in the same "step". There are great open source ssm packages that you could extend in R and python, if this approach interests you: sspir, dlm, MARSS, rbugs, pyssm, pymcmc, etc.

share|improve this answer
I think this answer is not very helpful. It is very general (long list of more or less unrelated packages) and doesn't really address the point. At least the links to the packages could have been given. – vonjd Jan 18 at 7:29
@vonjd late better than never ... my point is pretty darn specific :: "time-varying copula" is an academic exercise -- if you want to understand the dependence structure between your variables over time, you are introducing a graphical model. Call it whatever floats your boat. Hopefully my answer will direct others considering this approach to graphical models. Voila two great places to start a search: cran and pypi. – egbutter Feb 9 at 16:06

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.