tag:blogger.com,1999:blog-261139923818144971.comments2020-02-27T12:36:19.339+00:00This Blog is Systematic.Rob Carverhttp://www.blogger.com/profile/10175885372013572770noreply@blogger.comBlogger1812125tag:blogger.com,1999:blog-261139923818144971.post-66014109432148292022020-02-27T01:31:28.801+00:002020-02-27T01:31:28.801+00:00Thank you from your useful information our future ...Thank you from your useful information our future need to be stay alive we should save water through water conservation as water is life and conservatuon our future.FreeFlushhttps://www.blogger.com/profile/14961646852425228758noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-10888127362703586642020-02-23T09:17:49.239+00:002020-02-23T09:17:49.239+00:00I backtest on the contracts I will tradeI backtest on the contracts I will tradeRob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-83665245053757997732020-02-23T06:09:24.159+00:002020-02-23T06:09:24.159+00:00Hi Rob,
one more question about the book. You say ...Hi Rob,<br />one more question about the book. You say for oil you usually trade the december contract as it's a seasonal commodity. For STIR you might trade a contract 3 years out. <br />Do you backtest on these contracts then as well? or is your backtest based on front month contracts?hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-11095121614719426762020-02-22T12:11:05.506+00:002020-02-22T12:11:05.506+00:00Small point size isn't an issue in itself, ind...Small point size isn't an issue in itself, indeed it's a good thing. <br /><br />My suspicon is that you are trading one of the nearer months in Eurodollar, which are very low volatility that translates to large position sizes. Don't do this. It's very dangerous. For this reason I trade Eurodollar 3 years out, where the volatility is much higher.<br /><br />Fed funds I would avoid completely as I don't think it trades out that far.<br /><br />Just avoid stuff with really low vol (the front of most STIR contracts and until recently 2 year bond futures in most places fell into this category).Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-23546045331337559482020-02-21T05:53:05.623+00:002020-02-21T05:53:05.623+00:00Hi Rob,
I'm playing around with my system here...Hi Rob,<br />I'm playing around with my system here mainly based on your "leveraged trading" book (excellent one as always).<br /><br />I got the opposite problem to this article here. What do you do if the futures point value or nominal value are too small? I get excellent results on Eurodollar or Fed Funds Futures for example (both STIRs - GE and ZQ on IB), but the contracts are small with a margin of just $300 per lot. Your system would then recommend a very big allocation to this (~200 contracts in my case) which then generates a lot of comission.<br /><br />Is there any way around that? I see you are trading Eurodollar. Is there a bigger contract I am missing?<br /><br />thanks!hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-13248028454752220542020-02-11T16:14:11.613+00:002020-02-11T16:14:11.613+00:00Yes, but I don't use adjust=False
https://git...Yes, but I don't use adjust=False<br /><br />https://github.com/robcarver17/pysystemtrade/blob/master/systems/provided/futures_chapter15/rules.pyRob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-64639624184272782692020-02-11T16:06:18.368+00:002020-02-11T16:06:18.368+00:00thanks. is this correct then in python for the 64d...thanks. is this correct then in python for the 64day ewma? <br /> <br />ma_short = data.ewm(span=64, adjust=False).mean()<br />hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-76197534916251267642020-02-11T15:50:51.582+00:002020-02-11T15:50:51.582+00:00Yes go for EWMA. I use SMA to make it more underst...Yes go for EWMA. I use SMA to make it more understandableRob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-63819554472835122722020-02-11T15:49:42.461+00:002020-02-11T15:49:42.461+00:00thanks Rob. much appreciated. One more question.. ...thanks Rob. much appreciated. One more question.. in "Leveraged Trading" you use (simple) moving average whilst in "Systematic Trading" exponential weighted moving average. With me understanding and being able to calculate both, shall i go for ewma ? hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-60842205156947515162020-02-11T14:27:19.952+00:002020-02-11T14:27:19.952+00:00No 50% each is fine.
There is no statistically sig...No 50% each is fine.<br />There is no statistically significant difference in performance between the two systems.Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-32773673098270101462020-02-11T14:24:48.297+00:002020-02-11T14:24:48.297+00:00also, when I want to implement your system without...also, when I want to implement your system without carry. Would you place 50% or your risk on the MA system and 50% on the breakout. Or more on breakout as I can see from you chart that this has a slightly higher sharpe ratio?hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-84569108621193087722020-02-11T14:24:29.059+00:002020-02-11T14:24:29.059+00:00Equal weight is fine.Equal weight is fine.Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-63086225184671027432020-02-11T14:23:45.041+00:002020-02-11T14:23:45.041+00:00Hi Rob,
question on your book leveraged trading. ...Hi Rob,<br /><br />question on your book leveraged trading. In the book you got 6 different "strategies" for the breakout and 6 for the MA model with different lookback periods. Let's say trading costs are cheap enough for me to trade them all. Shall I equal weight then or what weights shall i put on each of the strategies when calculating the non-binary combined forecast. <br />hennerhttps://www.blogger.com/profile/15381506750678483901noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-54088085991282390932020-02-07T16:54:03.266+00:002020-02-07T16:54:03.266+00:00Personally I am not excited about this stuff. It&#...Personally I am not excited about this stuff. It's neccessary if you're writing option pricing models, but for normal trading risk management I find that assuming a joint normal distribution plus a little common sense and maybe some monte carlo risk modelling goes a long way. And by common sense, I mean not loading up a portfolio with obviously negative skew strategies, and limiting your weight to super fat tailed stuff like VIX. Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-74472505999997402262020-02-07T16:26:38.468+00:002020-02-07T16:26:38.468+00:00Thanks for the thoughtful response.
In general (i...Thanks for the thoughtful response.<br /><br />In general (i.e. w/o skew analysis), the increased correlations have definitely been noticeable across indexes, energy futs, etc since the virus scare started this year.<br /><br />On a separate note, have you looked at power-law distributions for modeling markets/returns much? TBH it's a new one to me, and a few sources (notably Gabaix et. al "A Theory of Power Law Distributions in Financial Market Fluctuations") *seem* to imply that "conventional" returns distribution modeling is insufficient w.r.t. the speed/size of bigger market participants moving big volumes. From that paper, one excerpt jumped out: "crashes do not appear to be outliers of the distribution."<br /><br />A few plots of power-law vs Gaussian/normal that I saw appeared to show a significant lead in power-law curvature vs. lag in the Gaussian.Chad Bhttps://www.blogger.com/profile/13026562498196984544noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-57437775845506756552020-02-07T16:13:15.236+00:002020-02-07T16:13:15.236+00:00It's a well known stylised fact that most nega...It's a well known stylised fact that most negative skew assets have high correlation in down markets (most vol selling short gamma like strategies got tanked in 2008). Therefore, without needing to look at the maths, it's obvious that a basket of -ve skew assets isn't really as diversified as you think it is.<br /><br />Personally I'm not too happy estimating parameters like co-skewness, because like skewness and kurtosis they are badly affected by a small number of outliers. A monte-carlo 'shuffle' type analysis will give more robust and insightful results, assuming that the data history is long enough to include at least one crisis period.<br /><br />(A shuffle analysis is basically sample from positions series, then sample from returns, then calculate a distribution of returns. This will give you a tail distribution that reflects the worst thing that could have happened to the worst kind of portfolio you had in the past)Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-111568209638925292020-02-07T15:31:20.659+00:002020-02-07T15:31:20.659+00:00Hi Rob,
I've been studying distribution model...Hi Rob,<br /> I've been studying distribution modeling & parameterization of the moments, and in a thread on nuclearphynance.com, some members (including N. Taleb) were discussing power-law distributions and how skewness & kurtosis might affect diversification. To wit:<br /><br />"One thing I would like to see you address is how skewness and kurtosis affect diversification. In the gaussian world, diversification is the great free lunch...<br />But in the non-gaussian world, life is not as good as in the gaussian fairy tale. And let's not even talk about correlation."<br /><br />"There is the start of an answer to that in "Bouchaud and Potters"<br />Theory of financial risk and derivative pricing.<br /><br />" for the sum of independant random variable, all the cumulant simply adds (..)<br />Normalized cumulant thus decay with N (number of asset) for n (order of the cumulant) >2. The higher the cumulant the faster the decay \lambda^N_n >N^{1-n/2}<br />Kurtosis, defined as the fourth order normalized cumulant thus decreases as 1/N"<br /><br />They note however further that for case of power law (instead of gaussian) the cumulant diverge and the sum of power law still behaves as a power law (page 22-23). They stress that the central limit theorem doesn't say anything about the tails of the portfolio, just about the "center".<br /><br />Further in the book they discuss portfolio theory using power law distribution while minimizing the VaR." (source: https://nuclearphynance.com/Show%20Post.aspx?PostIDKey=166742)<br /><br />I'm not promoting that site, I just frequent it when trying to get some street-wise perspective to all the math-heavy word-salad theory.<br /><br />Anyway, I'm curious as to whether you think any of the notions presented there have merit w.r.t. your experience. I didn't see discussion of finer details like frequency of their trades, and only some notes on types of strategies.Chad Bhttps://www.blogger.com/profile/13026562498196984544noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-84977042256028825672020-02-07T12:26:28.326+00:002020-02-07T12:26:28.326+00:00Yes and yesYes and yesRob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-54718937481950753892020-02-07T12:24:44.865+00:002020-02-07T12:24:44.865+00:00Rob, in an old Better System Trader podcast you st...Rob, in an old Better System Trader podcast you stated; “A very easy way to avoid fitting is to do no fitting at all.” May I ask a related statistical question?<br /><br />Fewer “degrees of freedom” means we can have a smaller sample size. Each new trading rule adds another degree of freedom.<br /><br />When we start optimizing, does each variation of a trading rule also add more degrees of freedom? In other words, does an optimized back test need a larger sample size than an un-optimized test?<br /><br />Anonymoushttps://www.blogger.com/profile/01655079732328145108noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-44006742359458791542020-02-06T16:32:28.512+00:002020-02-06T16:32:28.512+00:00Hi Rob, I think every trading approach should use ...Hi Rob, I think every trading approach should use different stop loss tactics. I remember the ATR (volatility) stop loss being use by the Turtles also as a position sizing technique. For example with overnight trading I use a fixed price based stop loss very large that triggers once in a while, like here: https://nightlypatterns.blog/2015/12/01/1-3-fixed-stop-loss-and-nightly-patterns-performance<br />Regards,<br />Marco Simioni<br />Nightly PatternsAnonymoushttps://www.blogger.com/profile/00987362260715821887noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-52317831130991626352020-02-03T15:35:54.075+00:002020-02-03T15:35:54.075+00:00I haven't read it, will do so thanks.I haven't read it, will do so thanks.Rob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-77740368656320451822020-02-03T14:54:58.536+00:002020-02-03T14:54:58.536+00:00I wonder what you think of this recent paper https...I wonder what you think of this recent paper https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3505422<br /><br />Cross-Asset Skewtraderhttps://www.blogger.com/profile/15568421130850633427noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-34397417020538233822020-02-02T09:55:40.504+00:002020-02-02T09:55:40.504+00:00No. For example
Returns-0.5, +0.5, -1.5, +1.5
Av...No. For example <br /><br />Returns-0.5, +0.5, -1.5, +1.5<br />Avg(abs(x)) = 1.0<br />Std dev = sqrt(.25+.25+2.25+2.25)= 2.24<br /><br />The exact ratio will depend on the distributionRob Carverhttps://www.blogger.com/profile/10175885372013572770noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-56779560980034569902020-02-01T22:49:34.250+00:002020-02-01T22:49:34.250+00:00Oh man, can you give a hint of how to get 1.255 ? ...Oh man, can you give a hint of how to get 1.255 ? Are you using a pure random walk with ATR=1 and no drift so with 0 average, then, Sigma should also be 1, no ? JDhttps://www.blogger.com/profile/09437309331219087298noreply@blogger.comtag:blogger.com,1999:blog-261139923818144971.post-42630678017781789922020-01-27T14:41:36.009+00:002020-01-27T14:41:36.009+00:00Hi
What is your opinion on the bond market and al...Hi<br /><br />What is your opinion on the bond market and allocation to bonds as of now? I just heard that some banks will invest more in infrastructure and property instead of bonds. <br /><br />RegardsAnonymoushttps://www.blogger.com/profile/15065803721557367683noreply@blogger.com