Bootstrapping again

[Jrinne]

Hi Yuval,

Expanding on this:

Has anyone considered why the Sharpe Ratio has a positive correlation while the information ratio is negative in the paper?

Has anyone read the paper? I cannot download it.

The most likely explanation (without reading the paper) for why this would be is that some of the algorithms use hedging to reduce the volatility (standard deviation in the Sharpe ration and the IR). If the same benchmark is used, they are fully invested and it is all equities (no bonds) for all of the algorithms then I think this is very likely the reason.

James, if this is the case your comments about pairs trading and leverage are important.

I will not go further as I have not read the paper and there could be another reason.

But you should read the complete paper before changing too much. If you have read it I would be interested in whether the paper explains this.

-Jim

From what I gleaned, the correlations were both so close to zero that whether one had a negative or positive correlation was pretty irrelevant. I have an extremely low opinion of the Sharpe ratio for the same reasons as Andreas does. The lesson I gleaned from the paper is never to expect correlation between in-sample and out-of-sample performance over very short periods. If I remember the 2016 paper correctly, it looked at in-sample and out-of-sample performance over periods that were less than two years long (maybe even less than one). I also think that the regression lines in the illustrations are comical at best. One shouldn’t try to draw linear regression lines using OLS methods through data that looks like a hornet’s nest. This is all just my opinion, of course, and I may be misremembering the paper, and maybe someone will convince me that I’m mistaken here.

-Yuval

Probably the best, universally accepted, way to get around using Standard Deviation and finding confidence intervals is with Bootstrapping.

I have read texts just about this subject and programmed using this (mostly with R at this point). I cannot summarize all of it in one post. You may have to download a text or 2 if you are not already familiar with this…

BUT THIS IS THE ORIGINAL PURPOSE FOR BOOTSTRAPPING OR AT LEAST ONE OF ITS FIRST MAINSTREAM USES.

Just to let you know that you may already have the best method for getting around the use of standard deviation in your toolbox as you are already using bootstrapping: the principle at least.

You really do write some great stuff about machine learning elsewhere: like how the Netflix completion is like picking stocks.

Please keep up the good work in your writings and please bring as much of that as you can to the P123 platform.

I will say that done (more-or-less) right all the methods lead to pretty much the same result. I, for one, should not get overly concerned about convincing others to use a particular method.

Marco’s, idea of using DataRobot—which would allow for a range of methods–seems like something worth checking out: I know this is Marco’s idea and is already being considered. Probably with a bunch of other good ideas.

Thank you.

-Jim

[yuvaltaylor]

Thank you, Jim. One of the reasons I pushed hard for exposing stock ID numbers was to make bootstrapping easier to do.