tag:blogger.com,1999:blog-35364652.post5826902374878450176..comments2022-01-18T09:16:21.942-05:00Comments on Quantitative Trading: What are we to do with Sharpe ratio?Ernie Chanhttp://www.blogger.com/profile/02747099358519893177noreply@blogger.comBlogger18125tag:blogger.com,1999:blog-35364652.post-44819183896111463462011-03-08T02:43:11.281-05:002011-03-08T02:43:11.281-05:00This is very nice article and providing very impor...This is very nice article and providing very important information about trading and also focused on strategies for trading, i think which is very helpful.RAJEEV SINGHhttps://www.blogger.com/profile/06802852728611175248noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-40112398254511444962010-09-30T05:45:46.351-04:002010-09-30T05:45:46.351-04:00Alexandre,
Some people think that upside volatili...Alexandre,<br /><br />Some people think that upside volatility in the observed sample suggests there will be downside volatility in the future data you haven't seen yet. If you believe this then this feature of the sharpe ratio is sensible gives a conservative approach.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-8977180132752057002010-09-11T07:53:34.344-04:002010-09-11T07:53:34.344-04:00Hi Jesse,
pnl=sum(lag1(positions).*dailyret,2) is ...Hi Jesse,<br />pnl=sum(lag1(positions).*dailyret,2) is a calculation of daily P&L, it is not a calculation of daily return. The daily ret is pnl divided by total capital, which in this case is 2.<br />And yes, the strategy I backtested assumed holding position overnight.<br />Best,<br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-68974022907402836472010-09-10T14:02:14.949-04:002010-09-10T14:02:14.949-04:00Hello Ernie,
On the subject of calculating retur...Hello Ernie, <br />On the subject of calculating returns for a market neutral strategy, in your book, in the section regarding the calculation of Sharpe ratios for a market neutral strategy, there is the following formula: <br /> netRet = (dailyret – dailyretSPY) / 2 it says we should divide by 2 because twice as much capital is used. (long position and short position)<br />A couple pages later on the subject of Pair Trading of GLD and GDX the pnl=sum(lag1(positions).*dailyret,2) ,So these returns are added but they are not divided by 2. I see this will not change the Sharpe ratio calculation, but it does change the cumulative return by a factor of 2. This pairs trading code is calculating these returns with only 1 price per day (the closing price), so the program must be assuming we are holding these positions overnight. I want to know if there is some reason we don’t need to divide these pnl’s returns by 2?<br /><br />Thanks againJessenoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-60040230022515362842010-09-02T20:25:32.302-04:002010-09-02T20:25:32.302-04:00Jesse,
We should indeed include zero position and ...Jesse,<br />We should indeed include zero position and zero return days in calculating Sharpe ratio. After all, the average annualized returns will most definitely include zero-position day, otherwise it would not be representative of the total return of the year. As average returns go, so go Sharpe ratios.<br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-37717071065357463862010-09-02T19:24:06.107-04:002010-09-02T19:24:06.107-04:00Thanks for answering our questions?
I have noticed...Thanks for answering our questions?<br />I have noticed that when calculating the Sharpe ratio you include every data point of the pnl vector, even though at times pnl(t) might be zero because there is no trade open. I am wondering if under any circumstances, is it legitimate when calculating the Sharpe ratio to only average in days where we have a return. After all, the reason for not having a return in this case is because a position is not actually open, we are on the sidelines waiting for a signal to enter.Jessenoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-36391288681715829322010-08-23T21:11:54.923-04:002010-08-23T21:11:54.923-04:00Alexandre,
You can read the book The Quants about ...Alexandre,<br />You can read the book The Quants about the meltdown of many quant funds in 2007.<br /><br />I believe there is no cure to this illness if one holds multiple days, except diversification of strategies and assets.<br /><br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-87191981389397916602010-08-23T10:18:31.512-04:002010-08-23T10:18:31.512-04:00Ernie, do you have any references related to your ...Ernie, do you have any references related to your comment?<br /><br />I run some pairs strategies with horizons of several days and I have noticed that kind of behaviour from time to time, especially when there is a big rally. I've tried many ways of heding this risk but to no avail. Do you have any ideas from your experience? Thanks, great blog!Alexandre Rubesamhttps://www.blogger.com/profile/06959364973104336889noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-62131687241862260592010-08-21T08:15:14.068-04:002010-08-21T08:15:14.068-04:00Hi anon,
Cumulative compounded returns should be u...Hi anon,<br />Cumulative compounded returns should be used when one is holding a position without rebalancing over multiple periods (e.g. days). It should also be used if one is determining the order size (or market value) based on Kelly's formula, i.e. increasing market value when equity increases and vice versa.<br /><br />Cumulative simple returns should be used if you exit your position at the end of every period, or if you rebalance your position to keep the capital the same at the end of every period, or when you keep the order size/market value the same at the beginning of every period irrespective of equity (i.e. not using Kelly formula to size the order/market value).<br /><br />I use the cumulative simple returns for a lot of backtests because it relieves me from explaining whether I follow Kelly sizing, and if so, at what leverage.<br /><br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-25720835434379142822010-08-21T08:09:14.058-04:002010-08-21T08:09:14.058-04:00Edouard,
Thanks for the reference to the paper on ...Edouard,<br />Thanks for the reference to the paper on trend following strategies. However, I would like to make 2 points:<br />1) The paper does not refer specifically to a high frequency strategy. In fact, their simulation is done on daily FX data. <br />2) Even assuming that per period returns on HF trend following strategy also follows such skewed distribution, it is unclear that the daily return (accumulated over many intraday period returns), will show the same skewness. For investors, it is the distribution of daily returns that matter, not that of the intraday returns.<br /><br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-31411089025506102122010-08-21T00:07:52.687-04:002010-08-21T00:07:52.687-04:00Hello Ernie,
In your book you used cumprod(1+retve...Hello Ernie,<br />In your book you used cumprod(1+retvect)-1; in calculating the max drawdown. I believe this would be known as the cumulative return. You also used cumsum(pnl(testset)) to just simply add the returns in your pairs trading code. I was not familiar with just summing returns, especially daily returns. I notice these different methods can give very different results when compared with each other, and also they are very different from the basic profit loss return calculation. Why do you use sum of daily returns? and when is it proper to use these different methods. Thank you.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-2187653719789317602010-08-20T10:10:36.916-04:002010-08-20T10:10:36.916-04:00Sharpe ratio isn't useful for measuring every ...Sharpe ratio isn't useful for measuring every high frequency strategy performance. A condition is having a symmetric gain distribution.<br /><br />It wouldn't make sense to use a sharpe ratio with a high frequency trend follower because trend followers usually have a strongly asymmetrical gain distribution (take a look at <a href="http://www.cfm.fr/papers/0508104.pdf" rel="nofollow">Bouchaud's paper</a>).Edouard d'Archimbaudhttp://www.darchimbaud.comnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-19808539577073647992010-08-16T16:11:23.544-04:002010-08-16T16:11:23.544-04:00Jonathan,
Yes, if everyone can agree to switch to ...Jonathan,<br />Yes, if everyone can agree to switch to reporting Sortino ratio instead of Sharpe ratio, it would be a great thing. Unfortunately, as long as most people are talking about Sharpe ratio, we still have to report Sharpe ratio for benchmarking purposes.<br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-67127869325336832242010-08-16T15:59:15.399-04:002010-08-16T15:59:15.399-04:00Jez,
Thanks for telling us about this measure!
Ern...Jez,<br />Thanks for telling us about this measure!<br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-36457305028975887192010-08-16T15:58:38.810-04:002010-08-16T15:58:38.810-04:00Hi Alexandre,
I am wary of strategies that hold p...Hi Alexandre, <br />I am wary of strategies that hold position for multiple days because it has been shown in recent years that they are highly vulnerable to tail risks as well as the non-stationarity of fundamental factors.<br />ErnieErnie Chanhttps://www.blogger.com/profile/02747099358519893177noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-76034278360896657112010-08-16T09:10:17.125-04:002010-08-16T09:10:17.125-04:00Penalizing deviation in the upside (as the sharpe ...Penalizing deviation in the upside (as the sharpe ratio does) is ridiculous. I have a strategy that takes advantage of extreme situations, so the return has periodic jumps (upward) and little downside risk.<br /><br />Sortino does a much better job of providing a useful picture of the upside of the strategy than Sharpe. <br /><br />Unfortunately, like the Sharpe ratio, it makes no allowance for possible risks, only those that have been observed. Still, I would like to see Sortino used in place of Sharpe as a metric.Jonathan Shorehttps://www.blogger.com/profile/08858453641392256663noreply@blogger.comtag:blogger.com,1999:blog-35364652.post-65788527645169854772010-08-15T14:28:18.106-04:002010-08-15T14:28:18.106-04:00completely agree, the Sharpe ratio has many flaws....completely agree, the Sharpe ratio has many flaws.<br /><br />One of them is the use of arithmetic returns, which can give false view of multi-period profitability.<br /><br />Same thing applies to the Information Ratio (which is an improve version of the Sharpe ratio - choice of benchmark).<br /><br />Here is an improved version using geometric return: the <a href="http://www.automated-trading-system.com/geometric-information-ratio/" rel="nofollow">Geometric Information Ratio</a>, which gives a better performance measure for trading strategies and managers (<a href="http://www.automated-trading-system.com/cta-alpha-calculate/" rel="nofollow">as seen here</a>)Jez Libertyhttp://www.automated-trading-system.comnoreply@blogger.comtag:blogger.com,1999:blog-35364652.post-55097021720689903722010-08-15T11:23:43.292-04:002010-08-15T11:23:43.292-04:00Hey Ernie, how do you mean you're losing your ...Hey Ernie, how do you mean you're losing your enthusiasm about stat-arb strategies with horizons of several days?Alexandre Rubesamhttps://www.blogger.com/profile/06959364973104336889noreply@blogger.com