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

BGonline.org Forums

eXtreme Gammon question

Posted By: Maik Stiebler
Date: Friday, 28 August 2009, at 6:08 p.m.

In Response To: eXtreme Gammon question (Timothy Chow)

I think you are right that what the bots do is equivalent to Bayesian inference with a uniform prior. I bet though that bot manuals will rather refer to classical statistics books when explaining what they are doing, which is where this talk about confidence comes from (Bayesians usually avoid the word "confidence").

I'll change my statement to "I'm also for more careful choices of priors", then.

However, if you roll the thing out enough, any reasonable choice of prior will converge to the same thing, so this shouldn't matter much in practice.

It is debatable if the thing is usually rolled out enough in practice for the choice of prior not to matter. I think Bob's example was a good practical counterexample (mine, not so much).

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.