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

BGonline.org Forums

Thanks

Posted By: Tom Keith
Date: Wednesday, 23 June 2010, at 3:56 p.m.

In Response To: Thanks (Chuck Bower)

There are so many problems with anocdotal reports:

(1) It is difficult to count rolls accurately while playing. People miss rolls even if they are writing them down.

(2) Without a prestated hyposthesis, it is hard to know how unusual something is. Any set of random numbers will have some kind of pattern if you look hard enough.

(3) Hundreds of thousands (millions?) of people play computer backgammon every day. Results that are more than 3 SD's from the mean should happen all the time.

(4) Similar reports are common for all backgammon games, including games where the dice are known to be random. In that sense, you could argue this report is consistent with the hypothesis that the dice are random.

That's not to say you shouldn't look further if you want to. Bot developers and users would certainly gain from a properly done scientific study. But to me this looks more like steam than smoke.

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.