[R] how to fit a copula using real data?

From: Xiaoheng Zhang <zhangx_at_tcd.ie>
Date: Sat, 29 Mar 2008 19:30:53 +0000


Dear all,

I just came to R a few days ago. Now I have a problem that I have two correlated variables and want to first fit a Gaussian copula, then sample it to generate simulated variables. I have spent last two days looking at R archive and copula help file but couldn't find what I need. If my understanding is correct, all examples I saw work in this way: a man-made copula -> simulated data -> fit the same copula. But what I need to do is: real data (bivariant) -> fit a Gaussian copula -> simulate variants from this copula -> transform variants into marginal distribution -> using inverse CDF to generate new data (variants) . Suppose I have two continuous variables N and S for 263 companies, N is the number of subsidiaries, and S is size. How can I do it? Thank you in advance if you may show me some sample codes.

-- 
Greetings,

Xiaoheng Zhang (Kevin)
Department of Economics
Trinity College Dublin
Republic of Ireland

	[[alternative HTML version deleted]]

______________________________________________
R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Received on Sat 29 Mar 2008 - 19:35:28 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sat 29 Mar 2008 - 20:30:56 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive