[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

SNOWIE ROLLOUTS

Posted By: Timothy Chow
Date: Thursday, 7 January 2010, at 3:49 p.m.

In Response To: SNOWIE ROLLOUTS (Daniel Murphy)

Daniel Murphy wrote:

But if I add that up (the sum is 880) and divide by 1296, I don't get 0.576, the cubeful equity; instead I get 0.679, the cubeless win %.

I need to get straightened out on this point before commenting further on anything else.

First of all, I don't understand why you're calling this the "cubeless win %" when the cube values are being factored in, but I think this is just a terminological point. I admit I haven't figured out a good, consistent terminology myself for all the different concepts floating around here.

Secondly, I wasn't aware of that feature of GNU. That's very nice to know; thanks for pointing it out.

Thirdly and most importantly, I don't think we can expect the 0.679 figure to match any equity number that GNU outputs, because you ran the rollout with variance reduction. Your calculation producing 0.679 does not apply any kind of variance reduction. If you turn variance reduction off, then I would expect GNU to report 0.679 as the cubeful equity. If this is not the case then I would be very curious as to how GNU gets its number.

Finally, the discussion started off as a discussion about Snowie rollouts. Does Snowie do these computations in the same way that GNU does?

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.