The Motley Fool Discussion Boards
Investing/Strategies / Mechanical Investing
|Subject: Re: The Best Measure for the Best Blend||Date: 11/20/2007 2:45 PM|
|Author: emintz||Number: 204117 of 254113|
No comment on the results I posted? I'd like to hear what you think about how this test turned out. Is it what you expected? What conclusions would you draw from it, if any?
I'm on the road and haven't commented because of that.
My initial comment is to ask what is meant by the comment that is labeled "Look-back period". In the paragraph above the table you refer to the granularity of the data by that's not what I normally think "look-back period" means. Does this mean that you are using only single-start dates per period, or that you are only looking back a limited time for some calculation?
My own results, using a much more limited data set, find that as the MAR was increased, you get higher CAGR, higher GSD, and lower Sharpe, but the changes were much more dramatic than what you saw... probably because of my inclusion of simulated bond returns - with low MAR, a high percentage of the port is in bonds.
I guess I need a better understanding of what that look-back period column really means. If I had to guess, I'd think it just meant granularity of the data used and that the results (other than daily) are averages of the rolling periodic returns?
|Copyright 1996-2014 trademark and the "Fool" logo is a trademark of The Motley Fool, Inc. Contact Us|