I have written before about survivorship bias. Frank over at Engineering Returns has developed a survivor-free S&P500 database and further demonstrates the impact of survivorship on a simple RSI2 trading system.
Plainly speaking, anyone backtesting and not using de-listed data is going to have results that are not accurate.
While I have not tested this idea sufficiently enough for it to be more than a theory, I theorize that a short-term system which holds stocks for a few days to a week or so may indeed show improvement when using a survivor-free database. (However, Frank’s recent testing shows my theory may be incorrect.) Conversely, systems that are of the trend-following variety (and usually hold stocks for longer periods of time) seem to suffer worse when de-listed data is used. For a good example of this, see my started, but not-yet-finished-series on building a momentum rotational system. I was shocked at how much performance was degraded when adding de-listed data, to the extent that it stopped the series in its tracks.
While it should be obvious how survivorship bias will affect trading systems that trade a portfolio of stocks, what may not be as obvious is that it will also affect indicators. Specifically, an indicator like a breadth indicator, which uses the data from hundreds or thousands of stocks, is going to be affected by survivorship bias. If such an indicator is applied to a trading system which was developed with de-listed data, the impact of survivorship bias is compounded.
Inevitably, this type of post leads people to ask where I get my data. I use Norgate’s Premium Data, which offers a de-listed data base for a very low one-time fee.
An early “happy one year anniversary” for the Power Dip system Wood! I hope I am able to focus on it more this year. Appreciate your 11/8 post and analysis of the various risk models and year to date results. Keep up the great work.
Thanks Lindsay!
Power dip killing it today! I exited all 12 positions with a profit.
The only boring part now is putting them all on my Excel sheet.
Lol at spreadsheet entries. Don’t you just hate that? Sucks more though when they are losers!
Hawaii, are you getting better exits not waiting for the close?
I’ll check and get back.. don’t really know..I just like to get out safely with a nice profit. Today, I kinda think I did because I got out when the market was at its peak.
Wood,
Of the 12, I got out of yesterday your system only got us out of 3. Here are the three:
System: CYD 3.28%, CVI 3.70%, TC 4.65%
Hawaii: CYD 2.01%, CVI 3.74%, TC 5.06%
Not much of a study, but I’ll follow up when the system closes the others. I would do the all of my trading since I started, but it wouldn’t be meaningful as I’m not consistent with regard to when I exit. I think yesterday though I did exit at the high point of the day or close to it.
On a humorous note you might be interested to know that when I went back to check this out for you, my Excel sheet didn’t show any entrees for yesterday. I suppose in the turmoil of trading other stocks yesterday, I neglected to save my entries. So I had to go into the garbage and retrieve my paper copies and re-enter them into the spread sheet again.
I guess it a good thing that I’m not in charge of the more complex stuff that you’re handling!
Wood,
The system got us out of 3 more of my 12 yesterday today. Result comparison:
Closes 11/19/2010
System: DNN 8.44, PWAV .47, GG .07
Hawaii: DNN 7.39, Pwav .93, GG .97
Wood- that email tonight on the huge list of all the stocks the system sold today, along with the percentage gains— wow. Would make an interesting post if you get a chance.