Jase
Reputation
735
Top tag
Next privilege 750 Rep.
 Jul 18 revised Time-series similarity measures added 102 characters in body Jul 14 awarded Nice Question May 30 answered Time-series similarity measures May 25 comment So many volatility models. Any comparisons of them? So you're saying that we can't compare forecasts from realized models and implied vol because realized models are based on historical prices and implied models deal with current prices? While this is true I'm still not clear why this means that we can't compare the two meaningfully. May 25 comment So many volatility models. Any comparisons of them? What about comparing forecasts from a realized model to the implied vol? May 24 comment So many volatility models. Any comparisons of them? Very nice answer, but could you please elaborate on "it does not make sense to compare standard deviation models with an implied vol model." Why doesn't this make sense? May 23 asked So many volatility models. Any comparisons of them? May 6 comment rugarch: Joint estimation leads to different results Send a link of this thread to the package's author. He's fantastic and responds to my queries within 2 days; I'm sure he'll take a public thread even more seriously. Apr 19 comment Resources for finding scholarly research on topics in quantitative finance? bookos.org is good Apr 9 comment How can I go about applying machine learning algorithms to stock markets? I want to know why there's such a vast sea of machine learning people working at prop firms on LinkedIn if it doesn't work? Isn't this good evidence that it does work persistently in some markets at some frequencies? Apr 8 comment Testing Significance of Correlation Pearson correlation will be significant, assuming no assumptions are violated, when the bivariate time series is fitted well by a linear relationship // straight line. This makes sense because the square of the pearson correlation is the R^2 from the linear model y = a + bx + e. You find out whether it's spurious by seeing if the estimator's assumptions are violated, meaning the finite sample properties of the test statistic will not approximate the asymptotic case well. The Pearson correlation is highly susceptible; bivariate non-normality,hetero,serial corr,etc. Kendall/Spearman is robust. Mar 9 comment Improving GARCH modeling approach @ikh Nice comment. Definitely go for the AR(N) in the mean equation if there's first moment serial correlation. Feb 27 comment Toy models of asset returns I have no idea but perhaps some you could consider: A skewed-t distribution... Or, a gaussian distribution for the centre and generalized pareto distribution (or generalized extreme value distribution) for a parametric distribution of tails (see extreme value theory). Then you just tweak the tail parameter to get whatever tail area you want. You could maybe use a multivariate parametric Vine copula to paste the univariate distributions together and create your economy. Feb 9 comment R ARMA-GARCH rugarch package doesn't always converge i've found that GARCH fails to converge often due to outliers. Try winsorizing the data at 98% and it should converge. If not try asymmetric GARCH. Best is probably to use a new outlier robust GARCH but I don't think rgarch has those yet. This might be the case with datastream data if the market is open on different days to the standard daily dates that Datastream uses, in which case there'll be a large number of zero return days, but I haven't really explored this hypothesis yet (but I suspect it given the type of data that fails to converge that I've played with). Jan 27 accepted Is there a copula that can estimate negative tail dependence? Jan 26 comment Why do low standard deviation stocks tend to have superior future returns? Could you briefly summarize the paper (objectives, main findings) in a few sentences so I can award the answer? Jan 22 comment Is there a copula that can estimate negative tail dependence? Yes very nice!! Jan 22 comment Alternative ways to understand time-varying comovement between two time-series? Answer to the question is that time-varying Kendall's tau can be estimated through a time-varying copula with something like a GJR-GARCH-ARMA-t for the univariate marginal distributions. Jan 22 asked Is there a copula that can estimate negative tail dependence? Jan 19 comment Strategy of Renaissance Technologies Medallion fund: Holy Grail or next Madoff? What are their methods? If you can claim that they're straightforward then that implies that you know what they are.