|
|
#301
05-11-2005, 05:56 PM
|
|||
|
|||
Re: DERB
[ QUOTE ]
[ QUOTE ] [ QUOTE ] Even considering how high his BB/100 is? I just learned about confidence intervals in a class. I should be able to figure this out. Im gonna try anyways. edit-ok nm its already been done, i think this is what you are talking about anyways. [/ QUOTE ] Confidence intervals don't correctly predict the likelihood of this player being a winner, since this player was chosen because of the abnormality of his winrate. [/ QUOTE ] We are not talking confidence interval between a population of players, but confidence interval for a 100K sample of hands where each member is 100 hands!!!!!!!!!!!! [/ QUOTE ] What? This still doesn't get around the selection bias. 
|
|
#303
05-11-2005, 05:59 PM
|
|||
|
|||
|
Re: DERB
this isn't a math problem - i don't think anyone here would disagree that based on his WR stat alone, it is EXTREMELY unlikely that DERB is anything other than a winner in this game, and likely a significant one at that.
fortunately, we have more information than his WR stat - we have people who have played thousands of hands against him, and observed his play. these people have all agreed that he is very likely NOT a significant winner in the game, and there is a significant possiblity of his being a big loser. lastly, we have one poster claiming that there are other players like DERB in his DB (that he won't share the names of) who are also winners in the game. luckily, we can dispose of this easily: everyone in this thread who actually plays in those games immediately knew who DERB was, meaning that there cannot be many like him. to conclude, the most likely outcome is that DERB is one of few huge statistical outliers in the game who are very bad but ran really well for a really long time, though the possibility remains that he has found a style that is actually winning, but drastically different from that used by most who post here.
|
|
#304
05-11-2005, 06:18 PM
|
|||
|
|||
|
Re: DERB
[ QUOTE ]
this isn't a math problem - i don't think anyone here would disagree that based on his WR stat alone, it is EXTREMELY unlikely that DERB is anything other than a winner in this game, and likely a significant one at that. fortunately, we have more information than his WR stat - we have people who have played thousands of hands against him, and observed his play. these people have all agreed that he is very likely NOT a significant winner in the game, and there is a significant possiblity of his being a big loser. lastly, we have one poster claiming that there are other players like DERB in his DB (that he won't share the names of) who are also winners in the game. luckily, we can dispose of this easily: everyone in this thread who actually plays in those games immediately knew who DERB was, meaning that there cannot be many like him. to conclude, the most likely outcome is that DERB is one of few huge statistical outliers in the game who are very bad but ran really well for a really long time, though the possibility remains that he has found a style that is actually winning, but drastically different from that used by most who post here. [/ QUOTE ] Great post.
|
|
#305
05-11-2005, 06:19 PM
|
|||
|
|||
|
Re: DERB
I'm not sure if this question has been asked yet. How many of you have players with DERB's stats that aren't winning? And at what point do those numbers add up to where you've got more hands that say playing his style isn't +EV?
|
|
#306
05-11-2005, 06:20 PM
|
|||
|
|||
|
Re: DERB
[ QUOTE ]
[ QUOTE ] [ QUOTE ] [ QUOTE ] Even considering how high his BB/100 is? I just learned about confidence intervals in a class. I should be able to figure this out. Im gonna try anyways. edit-ok nm its already been done, i think this is what you are talking about anyways. [/ QUOTE ] Confidence intervals don't correctly predict the likelihood of this player being a winner, since this player was chosen because of the abnormality of his winrate. [/ QUOTE ] We are not talking confidence interval between a population of players, but confidence interval for a 100K sample of hands where each member is 100 hands!!!!!!!!!!!! [/ QUOTE ] What? This still doesn't get around the selection bias. [/ QUOTE ] Of course it does. It tells you with 95% confidence (or whatever level you choose to use) that based on the data in the avaliable sample (and the SD for it's 100 hand members) his true win rate is between some minumum and maximum. Edit to get the math in: With an SD of 30BB/100 hands (on the high side, but we'll roll with it) his confidence interval is 2.8BB/100 at a 99.7% confidence. This brings his true winrate to be between 0.2BB/100 and 5.8BB/100. Now 0.3% of the time he could still be outside this inteval, but this goes both to the winning and losing sides. But applying a little common sense we know that it is more likely to be to the loosing side. So the math tells us that he is likely a winner, but it's within the scope to say that he might just be a small winner running good and then of course there is the 0.3% lottery. Now if I was to give you even money on a bet that DERB is a winning player, would you take that bet! I'm not discounting the anecdotal evidence, but at the poker table we make bets all the time based on probabilities and in the face of statistic it'll take more than some bad beat stories and a few hand histories before I'll write DERB of as a fluke.
|
|
#307
05-11-2005, 06:28 PM
|
|||
|
|||
|
Re: DERB
[ QUOTE ]
[ QUOTE ] [ QUOTE ] [ QUOTE ] [ QUOTE ] Even considering how high his BB/100 is? I just learned about confidence intervals in a class. I should be able to figure this out. Im gonna try anyways. edit-ok nm its already been done, i think this is what you are talking about anyways. [/ QUOTE ] Confidence intervals don't correctly predict the likelihood of this player being a winner, since this player was chosen because of the abnormality of his winrate. [/ QUOTE ] We are not talking confidence interval between a population of players, but confidence interval for a 100K sample of hands where each member is 100 hands!!!!!!!!!!!! [/ QUOTE ] What? This still doesn't get around the selection bias. [/ QUOTE ] Of course it does. It tells you with 95% confidence (or whatever level you choose to use) that based on the data in the avaliable sample (and the SD for it's 100 hand members) his true win rate is between some minumum and maximum. [/ QUOTE ] which is almost completely irrelevant, because we have much more information about his play than a WR/std deviation over some number of hands.
|
|
#308
05-11-2005, 06:39 PM
|
|||
|
|||
|
Re: WHAT IS DERBS SCREENAME ON PP???
[ QUOTE ]
Thanks for telling me what DERB stands for. I'm still asking for his PP screename. [/ QUOTE ] the answer lies within this thread. its not my place to tell you, but i figured it out...
|
|
#309
05-11-2005, 06:48 PM
|
|||
|
|||
|
Re: WHAT IS DERBS SCREENAME ON PP???
[ QUOTE ]
[ QUOTE ] Thanks for telling me what DERB stands for. I'm still asking for his PP screename. [/ QUOTE ] the answer lies within this thread. its not my place to tell you, but i figured it out... [/ QUOTE ] It's not in this thread, but it is in another. It's best that it not get posted here. I sometimes wonder if he has found this thread and is getting a kick out of it.
|
 |
|
|
Linear Mode
