When doing a rubustness check using a 12 week hold, should I do a robustness check using all 12 different start dates or just 4?


Attach file (image (.gif, or .jpg), screen (.und) or report (.rpd))
KMatras
at 05/03/11 11:31 PM : RE: how many periods


When doing a robustness test using a 12 week rebalance over a long backtest time span, I'll often use a 12 week robustness test. But if you think about it, 4 weeks is likely fine enough for a quick validation or not because week 5 in the first period of the 12 week robustness test and week 1 of the second period of the 4 week robustness test will essentially recreate the same thing. The difference however will resde in the average return of all runs. For example, if you're averaging 12 runs vs. 4, the results will vary. Not so much because the runs will be different. But if the test was a year long, the last run in a 12 week robustness test will only have 3 quarters of a year of results (and run 11 will be 3 quarters and 1 week's worth of results, and etc.), whereas the 4 weeks will go thru the full year, give or take an extra week or two, thus making the runs within your average of all runs calculation more similar time-wise.


Attach file (image (.gif, or .jpg), screen (.und) or report (.rpd))

For questions or more information or to Order Today, call 1-800-767-3771, ext. 9392 or 1-312-630-9890, ext. 9392
You can also e-mail our Sales Support at: kevinm@zacks.com
Copyright 2012
Zacks Investment Research
111 N. Canal St., Suite 1101, Chicago, IL 60606
(800) 767-3771 ext. 9392