How should I account for the strategies I tested and threw away? #31
Verified answer
by
martex-dev
martex-dev
asked this question in
Q&A
|
How should I account for the strategies I tested and threw away? Notes and answer below. |
Admin verified this answer by
martex-dev
Aug 27, 2026
Replies: 1 comment
|
They count. If you test two hundred strategies, the best Sharpe you observe is largely the maximum of a noise distribution. The deflated Sharpe ratio corrects the observed value for the number of trials and for non-normal returns, but it needs an honest trial count. Keep a log of every hypothesis tested including abandoned ones, or the correction cannot be computed and the reported number is not meaningful. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
They count. If you test two hundred strategies, the best Sharpe you observe is largely the maximum of a noise distribution. The deflated Sharpe ratio corrects the observed value for the number of trials and for non-normal returns, but it needs an honest trial count. Keep a log of every hypothesis tested including abandoned ones, or the correction cannot be computed and the reported number is not meaningful.