On Fri, 21 Oct 2011, Matthew Wild wrote: > I'm intrigued to know if gretl 1) does this out of the box (I suspect > I'd be too lucky) or 2) can help implement this thing, or 3) is > completely in the wrong domain for this kind of application.
1) No 2) Yes, definitely I suspect that the most difficult problem in your case is formalising the statistical approach and building a solid statistical model for your data. For example: is it possible, at least in principle, that stream A can be affected by what happened in stream B _in the past_? In which way? Once you have a suitable statistical model, writing the code (in C or possibly in hansl) to implement estimation and forecasting doesn't seem so hard, and (lib)gretl should definitely be up to the job. Riccardo (Jack) Lucchetti Dipartimento di Economia Università Politecnica delle Marche r.lucchetti(a)univpm.it http://www.econ.univpm.it/lucchetti
