<r>Hey all,I've been playing around with regime switching pde's as an alternative to stochastic volatility models, but I'm stuck trying to replicate the heston like stock-vol correlation. Essentially a regime switching model has n black scholes pde where each pde has a different vol diffusion parame...

<r>I too am unable to download the paper.Have an account at ssrn... no download options.found it here:<URL url="http://mpra.ub.uni-muenchen.de/23381/1/MPRA_paper_23381.pdf"><LINK_TEXT text="http://mpra.ub.uni-muenchen.de/23381/1/ ... _23381.pdf">http://mpra.ub.uni-muenchen.de/23381/1/MPRA_paper_2338...

<r>I too am unable to download the paper.Have an account at ssrn... no download options.found it here:<URL url="http://mpra.ub.uni-muenchen.de/23381/1/MPRA_paper_23381.pdf"><LINK_TEXT text="http://mpra.ub.uni-muenchen.de/23381/1/ ... _23381.pdf">http://mpra.ub.uni-muenchen.de/23381/1/MPRA_paper_2338...

are there any good resources to read to learn more about the impact of the assumptions to this model?

look at what fama and french did. There is a lot about adding certain factors to your portfolio that improve sharpe ratios. There are also papers on adding momentum as a factor to get a better sharpe. google away!

<t>there's no reason that quant strategies won't do simple things that charting do. If one believes that stock returns aren't iid or that something can be gained from the volatility process then you can create a signal to trade with this. You may use more "quantitative techniques" to come up with nu...

seriously look up poisson process example on google. you will find something that will tell you how to set the lambda parameter to your desired rate of cars passing tress/minute.Good luck

most models do use historical data and more recent data in a certain weighted way. look at Garch for example

http://en.wikipedia.org/wiki/Modern_portfolio_theory

<t>In general I don't think it has anything to do with Normal Distributed returns ( and someone can correct me on this) I think the problem is what the tangency portfolio attempts to optimize.It looks to find the best risk-reward payoff and weights more heavily assets with good sharpe ratio vs bad s...

<t>You should think about why using the historical return isn't the best idea. You are trying to figure out the best tangency portfolio going forward some amount of time. You want to have predictions for return, variance, and correlation for that future.Chances are very good that the mean return isn...

Take a look at mean-variance efficient frontier and tangency portfolio.http://en.wikipedia.org/wiki/Modern_portfolio_theoryThe tangency portfolio is the sharpe-ratio efficent portfolio.

<t>What exactly do you mean? Do you want to make a model that incorporates tail risk to match the implied volatility curve? Or do you think that tail risk isn't being priced into options correctly and you have enough faith on a model you could create to take bets on your model?Either way "tail Risk"...

<t>8 doesn't seem to make a lot of sense to me, wouldn't a large amount of competition in this sphere cause the algorithms to eat each other's profits. and hence cause people to start thinking about "second" order algos to eat the money flowing against the small money. I just don't see how/why all t...

<t>are you willing to assume some things? like geometric brownian motion for the two stocks with some correlation?because then you just have max(ln(m1)-ln(m2) - k) and you'd know the distributions of ln(m1) and ln(m2) . you can back out the correlation from the max(m1-m2) option. Then you can hedge ...