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

BGonline.org Forums

eXtreme Gammon question

Posted By: Timothy Chow
Date: Wednesday, 26 August 2009, at 11:59 p.m.

In Response To: eXtreme Gammon question (Bob Koca)

So after some additional thought, I think I understand the confusion here...we don't really disagree.

I wrote: The confidence level answers the question, "If I declare the higher-scoring play to be the better play, what percentage of the time will I be correct?"

You replied: Not correct. It depends on the distribution of problems fed into it. For example supose you are only giving it problems in which you are pretty sure that play A is much better than play B. The higher scoring play will be correct more than what the confidence level says.

Your point is that it would have been more precise for me to say, "If I declare the higher-scoring play to be the better play, what percentage of the time will I be correct, assuming that the DMP winning probabilities of the two plays are picked uniformly at random?" I agree that I was making that implicit assumption. With that assumption, though, what I said was correct.

You also wrote: As the rollout progresses the two individual deviations get smaller but the JSD gets larger and larger.

As you clarified later, one must distinguish between the j.s.d. itself and the number of j.s.d.'s the two estimates are separated by, which is the number gnubg reports. When I said "j.s.d. value" I meant the j.s.d. itself, not the number reported by gnubg. Again with that clarification, what I said was correct.

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.