tag:blogger.com,1999:blog-35364652.post4439815452413862014..comments2017-03-23T08:14:03.840-04:00Comments on Quantitative Trading: Predicting volatilityErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comBlogger96125tag:blogger.com,1999:blog-35364652.post-17933082794858282002016-04-17T19:47:49.398-04:002016-04-17T19:47:49.398-04:00Rob,
QuantCon will make available the videos (at a...Rob,<br />QuantCon will make available the videos (at a price) soon.<br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-50670919790598921792016-04-17T18:35:20.217-04:002016-04-17T18:35:20.217-04:00Thanks for the quick reply! I was too late to sign...Thanks for the quick reply! I was too late to sign up for this year's QuantCon, and unfortunately registration it is now closed, and I don't think it's possible to see your talk through their website. If it is saved somewhere, could you provide me with a link that I can use to view your talk?Rob Gnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-32045677672572263422016-04-17T15:45:53.805-04:002016-04-17T15:45:53.805-04:00Hi Rob,
Thank you for your kind words!
Actually, ...Hi Rob,<br />Thank you for your kind words!<br /><br />Actually, upon further research, I have determined that on average, there is zero correlation between changes in implied vs. realized volatility on the SPX. However, there is a negative correlation on days when there is positive return on SPX. So I agree with your calculations.<br /><br />However, I don't think I wrote in my article that I computed the correlation between the change realized volatility and the change in VXX. I only stated that we can buy VXX if we predict that realized volatility is going down. Which turns out to be wrong without an additional prediction on the direction of the SPX price change.<br /><br />Check out my talk at QuantCon 2016. It has the correct reasoning, and a few suggested strategies to take advantage the contango of VX futures. But the upshot is that it is no longer straightforward to trade VX after 2013.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-89095711820259570382016-04-17T13:26:53.346-04:002016-04-17T13:26:53.346-04:00Hi Ernie,
To start off, I wanted to mention that ...Hi Ernie,<br /><br />To start off, I wanted to mention that "Algorithmic Trading" was a great read, and very clearly written. It was the first book I read on algo trading, and it inspired me to start trading a personal account (I use IB with backtests in Matlab, and I'm currently working on setting up a C# platform to systematically suggest trades). For that, I thank you, and I'm eagerly awaiting your next book!<br /><br />With regard to this post, perhaps there's something that I'm missing here, but my understanding of the strategy is the following:<br />This strategy hinges the assumption that, more often than not, an increase in realized S&P volatility is accompanied by a decrease in implied S&P volatility. Thus, if you can somewhat accurately predict increases in realized S&P volatility (e.g. by fitting a GARCH model), then you can use this as a trading signal to short implied volatility.<br /><br />If my above summary is correct, then my question is thus: why are you using VXX as a proxy for implied S&P volatility? Wouldn't you want to use the actual VIX index? (i.e. modify the strategy so that when GARCH predicts a vol increase, short 1 VX future or something). <br />I suggest this because VXX holds a varying allocation to M1 and M2 VIX futures contracts. Contango of VIX futures contracts causes the VXX to decay over time. This is why VXX returns have a significantly lower (more negative) skew than VIX returns.<br /><br />The reason why this additional contango-driven drag on VXX returns is relevant here, is that the main assumption of the strategy breaks down when we use the VIX as a proxy for implied vol (which I would argue is a more appropriate measure). In fact, over most of the time periods that I looked at (happy to provide more detail if you like), increases in realized S&P volatility are accompanied by virtually equal numbers of positive and negative movements in the VIX. I've found the following:<br /><br />- Of the days in which we experience an increase in realized S&P Volatility (i.e. " "abs(ret(t)) > abs(ret(t-1))"), around 57% of those days show a negative VXX return, which one could argue is an acceptable percentage to base a strategy on.<br />- Of that same subset of days, around only 51% of those days show a negative VIX return. I would probably not want to base a strategy on 51%, especially if my realized S&P Vol predictions are only 58% accurate. <br /><br />For this strategy to work, my GARCH model needs to be an accurate prediction of realized S&P Vol on the same days that realized S&P Vol is an accurate prediction of implied S&P Vol.<br /><br />My guess is that this strategy is not profitable due to of the ability of RV to predict IV (which isn't significant if we use the VIX index as our measure of IV). In stead, I believe it is profitable for the same reason that so-called "convexity capture" strategies are profitable: because outright shorting ETFs with negative drag on returns tends to yield decent risk-adjusted returns, especially if we add a hedge.<br /><br />Let me know if you notice any holes in my logic. I'm not 100% sure of my analysis, as I'm still relatively new to the world of systematic investing :).Rob Gnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-7072429743110757102016-03-31T10:57:58.350-04:002016-03-31T10:57:58.350-04:00We currently trade event-driven stock models in ou...We currently trade event-driven stock models in our fund.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-53111452782863309942016-03-31T10:53:50.563-04:002016-03-31T10:53:50.563-04:00Hi Ernie,
Thank you for quick response.
May I as...Hi Ernie,<br /><br />Thank you for quick response.<br /><br />May I ask what kind of trading strategies for stocks your fund are still using?<br /><br />Thanks.<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-33730434891618718132016-03-31T09:03:30.688-04:002016-03-31T09:03:30.688-04:00Hi Evil Speculator:
Agreed! That's for pointi...Hi Evil Speculator:<br /><br />Agreed! That's for pointing that out - indeed, VIX uses OTM options with 23-37 days tenor for averaging these days. (See http://www.cboe.com/micro/vix/vixwhite.pdf)<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-55724160515144002472016-03-31T08:23:15.640-04:002016-03-31T08:23:15.640-04:00Apologies in advance if someone already mentioned ...Apologies in advance if someone already mentioned this above (long thread). But Anonymous above said this:<br /><br />"Many tend to forget that the VIX is implied volatility for ***only ATM options***, so going for it VIX, is actually betting on the middle of the distribution which means missing the tails, and missing the convexity effect that leverages the volatility jump for you! It means almost going linear.."<br /><br />Actually that is not true - what Anonymous is talking about is the old VIX. Since Sept 22 2003 the formulate changed and the old VIX became the VXO. Lifted off the CBOE:<br /><br />"New Formula for Calculation of VIX. ****The new formula that will take into account a broader range of strike prices (rather than using only near-the-money strikes as the original-formula index did)****. Each strike price will be weighted, with at-the-money strikes having the most weight. The new formula is intended to make VIX a better index for investors who manage risks associated with the growing markets for volatility and variance swaps"<br /><br />Here's the VXO:<br /><br />"The CBOE is continuing to calculate and disseminate the volatility index introduced in 1993 based on trading of S&P 100 (OEX) options. This index has a price history dating back to 1986, which remains the same. As of September 22, 2003, the name was modified -- the original-formula index is now known as the CBOE S&P 100 Volatility IndexSM and is now disseminated under the new ticker symbol VXO (prior to September 2003 it was the "original" VIX Index)."<br /><br />On top of that the VIX is comprised of the VIN and VIF - they are not using the front month contract, but I'm certain most of you are aware of that ;-)<br />Evil Speculatorhttp://evilspeculator.comnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-60769385949990688492016-03-31T08:19:24.437-04:002016-03-31T08:19:24.437-04:00Since I haven't trade stock pairs for a while,...Since I haven't trade stock pairs for a while, I would not want to speculate on whether other traders are still successful with this strategy.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-3129429475683922992016-03-31T04:02:48.728-04:002016-03-31T04:02:48.728-04:00Hi Ernie,
Can stocks pairs trading still make pro...Hi Ernie,<br /><br />Can stocks pairs trading still make profit?<br /><br />Thanks.<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-137010272518656652016-03-25T08:31:51.158-04:002016-03-25T08:31:51.158-04:00No, we are assuming that parameters analogous to V...No, we are assuming that parameters analogous to Ve or delta are constant, not time varying.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-75766282862447411462016-03-24T21:49:41.883-04:002016-03-24T21:49:41.883-04:00Hi Ernie,
Thank you for the information.
To crea...Hi Ernie,<br /><br />Thank you for the information.<br /><br />To create the model via ssm class in MATLAB's Econometrics Toolbox, do we need to refer to "Implicitly Create Time-Varying State-Space Model"?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-88475360558996341432016-03-24T20:01:19.702-04:002016-03-24T20:01:19.702-04:00Delta and Ve can be found in the same MLE optimiza...Delta and Ve can be found in the same MLE optimization (i.e. multivariate optimization).<br /><br />For details, please google MATLAB's Econometrics Toolbox's documentation on State Space Models.<br /><br />Ernie<br /><br />Ernie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-27361757778350136982016-03-24T00:48:00.925-04:002016-03-24T00:48:00.925-04:00Hi Ernie,
Would you please give more details abou...Hi Ernie,<br /><br />Would you please give more details about estimation of Ve?<br /><br />Is this estimation procedure independent of choosing delta?<br /><br />So we can pick Ve first, then optimizing delta.<br /><br />Thanks.<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-31264118786934218652016-03-23T18:12:49.790-04:002016-03-23T18:12:49.790-04:00I don't think Ve=1 will work in our case, and ...I don't think Ve=1 will work in our case, and frankly, I don't know how he come up with that initial value. I would use MLE to estimate Ve.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-21973740802334654022016-03-23T15:56:42.647-04:002016-03-23T15:56:42.647-04:00Hi Ernie,
In Montana's paper, at page 2825, V...Hi Ernie,<br /><br />In Montana's paper, at page 2825, Ve is fixed at 1.<br />At page 2828, in the beginning of section 6,Experimental results, he wrote "We<br />have tested the system using a grid of values for the<br />smoothing parameter delta described in Section 3,"<br /><br />It seems he only optimized delta ( which controls the speed of change of beta), and set Ve = 1.<br /><br />Thanks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-65921781761958919012016-03-23T10:37:35.835-04:002016-03-23T10:37:35.835-04:00What other method is there to "fix" Ve e...What other method is there to "fix" Ve except to feed past data into a model?<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-67784287997035501692016-03-23T09:05:28.392-04:002016-03-23T09:05:28.392-04:00Hi Ernie,
Thank you for quick response.
However,...Hi Ernie,<br /><br />Thank you for quick response.<br /><br />However, according to Montana's paper you mentioned, it seems we can fix Ve, and then optimize delta between 0 and 1.<br /><br />Thanks.<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-47773720193001516192016-03-23T07:48:28.287-04:002016-03-23T07:48:28.287-04:00You can certainly enter based on a multiple of sqr...You can certainly enter based on a multiple of sqrt(Q), ie. entryZscore*sqrt(Q).<br />Yes, the strategy as written is quite sensitive to the initial guess Ve. MATLAB's Econometrics Toolbox has state space model functions that allow you to optimize Ve quite easily.<br /><br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-53452949516422746922016-03-22T19:58:04.490-04:002016-03-22T19:58:04.490-04:00Hi Ernie,
In Algorithmic Trading, at page 80, you...Hi Ernie,<br /><br />In Algorithmic Trading, at page 80, you wrote that if e(t) < -sqrt(Q), we long, and if e(t) > sqrt(Q), we short.<br /><br />Could we do normalization first, to have e(t)/sqrt(Q), then setting threshold as numbers?<br /><br />I find the threshold could be much bigger than 3. I think it depends on how we set Ve. You set Ve = 0.001 here.<br /><br />Thanks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-82739697694008040172016-03-21T08:01:14.547-04:002016-03-21T08:01:14.547-04:00The last 2 chapters of the HFT book is particularl...The last 2 chapters of the HFT book is particularly useful.<br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-13516204479581775612016-03-21T02:24:02.500-04:002016-03-21T02:24:02.500-04:00Ernie have you found anything useful in the HFT al...Ernie have you found anything useful in the HFT algo book you mentioned? A lot of Calculus. Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-25189322811668503652016-03-14T06:54:36.969-04:002016-03-14T06:54:36.969-04:00While I haven't used BBG's fundamental dat...While I haven't used BBG's fundamental data, I don't see why it should be inferior to Compustat.<br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-58231562096295184382016-03-14T06:17:04.416-04:002016-03-14T06:17:04.416-04:00Hi Ernie,
Is fundamental data from Bloomberg ok t...Hi Ernie,<br /><br />Is fundamental data from Bloomberg ok to use, compared with compustat database?<br /><br />Thanks.<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-17190037994507519392016-03-11T02:34:01.131-05:002016-03-11T02:34:01.131-05:00Hi HK,
If your pair is supposed to be mean reverti...Hi HK,<br />If your pair is supposed to be mean reverting, you can certainly run an ADF on it to verify that before backtesting. You can also compute half life of mean reversion using methods described in my 2 books, and see if it is too long for practical trading.<br />ErnieErnie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.com