Search results

Hi elfopposwe, if you're aiming to measure integrated vol you've answered yourself and you'll need to use tick data; the usual way we calculate realized vol. If all you have are close to close prices your calculated realized vol will be too wild. Either use a filter with something like the HRS...

I coded up a garch class in C# not too long ago that used either a Simplex or a heuristic search method, unfortunately I'm unfamiliar with OPT++. But if it helps here is my negative log likelihood (no mean eq): //NEGATIVE LOG LIKELIHOOD FUNCTION static public double...

I think a very simple solution works fine, why make it more difficult? [C# pseudocode] class Program { static Int16 x, y; static void Main(string[] args) { ///ask for (x,y) Console.Write("enter integer x: "); x =...

^ I'm wondering if that will compile though? Why not find the type limit and store it in say [z] Then for any values [x,y] type cast their absolute product to an able type and do a comparison with [z], if it's smaller, great, otherwise there's a problem

What are some of the advantages of python? Never used it myself.

ok, after a little more caffeine I wrote-up the Simplex method from NR. Now I'm just unsure on how to proceed with constraints. Do I go about it the same way as with upper/lower bounds? thanks,

Nothing prevents me from coding Powell's routine I'm just a little lazy and I imagine I wouldn't enjoy the experience anyway. I actually already have it within the VNI library, but like I said I need it deployable and licensed library's unfortunately are not. So if someone has done this and...

Hey Alain, as far as I'm concerned R is the greatest thing to come along since sliced bread. The reason is I need it to be deploy-able.

Hi all, Does anyone mind sharing the nelder-mead or powell method implemented in .Net? I've tried using the Nelder-Mead algorithm from numerical recipes but it's still a bit buggy and I'm not positive I'll be able to use it with constraints. Powell's method would be more ideal and I...

Hi viertelasiat, I'm not from the states so I won't give you career or MFE program advice. But on education if I were you I'd make sure to pick up as much math in your selected MFE program as possible. On programming, Matlab (Octave) or S-Plus (R) for data visualization Java or C# for Monte...

Sorry xbuster i read to much into your first sentence about being able to "optimize input parameters". Anyway, I don't recall coming across a library in CS with the performance measures you're looking for (why not write one?). There are a couple measures (Sharpe) in the "tseries" package in R...

Try the SolverFoundation? Microsoft Solver Foundation - Express Edition - Home

Well your best solution is to use the CS IMSL Library: IMSLCS The only downer is you won't be able deploy your solutions to other workstations. If that's a big deal for you, I recommend writing your own optimizer. I came across plenty of examples of the simplex, BFGS, metaheuristics out there.

i believe Mono should run on a Mac? But use what you can to get the job done.

I believe TNT has super-seeded LAPACK. May be wrong cos' i mostly use c#.

In answer to your first question, no you wouldn't use inv(x`x)*x`y, because obviously y is no longer an Nx1 vector but becomes a matrix.

Econometrics is an umbrella term for anything to with both estimation and economics (incl. finance). Quantitative finance is under that unbrella, but so is survey analysis so it really doesn't say much. On your second question, they're one and the same. imo.