Is there a absolute dollar form of the Kelly equation $f=\frac{m}{s^2}$? (i.e. one that does not use percent returns).
$\begingroup$
$\endgroup$
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
2
Well, the first formula on the wiki page gives you a straight forward answer in absolute terms (you do know your bankroll so its pretty much absolute):
http://en.wikipedia.org/wiki/Kelly_criterion
Simple as that, sometimes it does not pay but only causes headaches to overcomplicate things :-)
Happy Thanksgiving!!!
Update as requested by OP:
http://www.math.washington.edu/~morrow/336_10/papers/jane.pdf
and here an application using R
http://braverock.com/brian/R/PerformanceAnalytics/html/KellyRatio.html
-
$\begingroup$ That formula seems to be a specific case for binary outcomes, quote: "For simple bets with two outcomes, one involving losing the entire amount bet, and the other involving winning the bet amount multiplied by the pay-off odds". I was more specifically wondering if there was an absolute dollar form in the continuous case. $\endgroup$– CraigCommented Nov 23, 2012 at 19:23
-
$\begingroup$ Added more references for the continuous case and specifically applied to financial assets. $\endgroup$ Commented Nov 25, 2012 at 10:05
$\begingroup$
$\endgroup$
1
See Ralph Vince's excellentbook: Handbook of Portfolio Mathematics where he goes through explicit, worked examples of using an appropriate modified-Kelly system in dollar / contract terms (Optimal F). He even gives Excel examples for the programmatically uninitiated.
-
$\begingroup$ Cheers! That book looks like it's worth a read. $\endgroup$– CraigCommented Dec 1, 2012 at 17:11