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

BGonline.org Forums

Confidence

Posted By: Timothy Chow
Date: Monday, 13 June 2011, at 3:00 p.m.

In Response To: Confidence (leobueno)

Technically, the statement is that we can reject the hypothesis that the plays are equal at the X% confidence level.

However, informally you can think of it as a "confidence" that the top play is better than the other play.

As for equity differences, the standard deviations of the plays themselves (as opposed to the JSD) gives you some indication of how accurate an estimate of the equity you're getting. Roughly speaking, if you were to do a second rollout with the same number of trials, the new estimate of the equity would fall within 2 standard deviations of your first estimate about 95% of the time.

Since most of the time we're interested in the actual estimates of the equity and not just which play is better, the standard deviations are often more relevant than the JSD's. That may be why GNU focuses on the standard deviations and not the JSD's.

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.