05-25-2010, 02:22 PM
<!--quoteo(post=98250:date=May 25 2010, 12:58 PM:name=jstraw)-->QUOTE (jstraw @ May 25 2010, 12:58 PM) <{POST_SNAPBACK}><!--quotec--><!--quoteo(post=98247:date=May 25 2010, 12:49 PM:name=leonardsipes)--><div class='quotetop'>QUOTE (leonardsipes @ May 25 2010, 12:49 PM) <{POST_SNAPBACK}><!--quotec--><!--quoteo(post=98129:date=May 24 2010, 06:39 PM:name=KBwsb)--><div class='quotetop'>QUOTE (KBwsb @ May 24 2010, 06:39 PM) <{POST_SNAPBACK}><!--quotec--><!--quoteo(post=98128:date=May 24 2010, 06:34 PM:name=leonardsipes)--><div class='quotetop'>QUOTE (leonardsipes @ May 24 2010, 06:34 PM) <{POST_SNAPBACK}><!--quotec--><!--quoteo--><div class='quotetop'>QUOTE <!--quotec-->I read about a couple of psychologists who studied the so-called "hot hand" in basketball—the idea that players who are hot keep hitting baskets and players who are cold keep missing them. No matter how they crunched the stats, it turned out that the phenomenon didn't exist<!--QuoteEnd--><!--QuoteEEnd-->
This is a great example, to show how the stat heads are misguided. It is common sense, that some days, guys are going to be sick or injured, and have a bad day. They play against different defenders and coaches use different schemes. Hotness and coldness are not random, but they happen within a normal distribution. You take a guy with a 50% FG% (a coin) and flip it 16 times, for 82 games. It is not going to be 8 heads all 82 times. There are going to be a normal distribution of results - random hotness occurs. Basketball is a game of skill. We know actual hotness happens, but because it never happens to the extent that it could not be random, it does not statistically happen.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I think we need to define what we're talking about here. You guys are saying, after the fact, that some guys are clutch, or get the hot hand, and it was obvious to all who saw it. Obviously, I agree with that, because it's an inarguable point.
What I'm talking about is: is it something you can <b>predict?</b> Is it something inherent in that player?
<!--QuoteEnd--></div><!--QuoteEEnd-->
First of all, the quote is saying not only that hot/cold can't be predicted, but that it does not exist. My post was not about clutch, except to make the point that the stat heads are so clearly wrong about hot and cold, that maybe they are wrong about clutch as well.
Making a basket is skill not luck. When a player makes few 3 pointers early in a game, the opposing coach does not say "don't guard that guy, I want him to keep putting up 3s, he is due to miss." They change their defensive scheme, so he doesn't get any more open 3s.
Hotness can't be predicted, in that the Suns can't say in game 1 we guard Kobe because he is going to be hot, in game 2 we are going to let him shoot away, but hotness/coldness can be identified when it occurs.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I have never before heard this idea that stat heads don't think hot and cold exist. Anecdotally, Posnanski mentions statisticians crunching numbers and not finding evidence of, well...essentially, streaks...hitting or missing a number of times in a row that represents a statistical outlier, in terms of distribution. I don't believe it. I think this casual mention is bullshit and is either made up or a complete misinterpretation or misrepresentation of some statistical analysis.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I'm not convinced that Posnanski understands stats much, because if he did he would understand that outside of the hard sciences, they have serious flaws.
This is a great example, to show how the stat heads are misguided. It is common sense, that some days, guys are going to be sick or injured, and have a bad day. They play against different defenders and coaches use different schemes. Hotness and coldness are not random, but they happen within a normal distribution. You take a guy with a 50% FG% (a coin) and flip it 16 times, for 82 games. It is not going to be 8 heads all 82 times. There are going to be a normal distribution of results - random hotness occurs. Basketball is a game of skill. We know actual hotness happens, but because it never happens to the extent that it could not be random, it does not statistically happen.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I think we need to define what we're talking about here. You guys are saying, after the fact, that some guys are clutch, or get the hot hand, and it was obvious to all who saw it. Obviously, I agree with that, because it's an inarguable point.
What I'm talking about is: is it something you can <b>predict?</b> Is it something inherent in that player?
<!--QuoteEnd--></div><!--QuoteEEnd-->
First of all, the quote is saying not only that hot/cold can't be predicted, but that it does not exist. My post was not about clutch, except to make the point that the stat heads are so clearly wrong about hot and cold, that maybe they are wrong about clutch as well.
Making a basket is skill not luck. When a player makes few 3 pointers early in a game, the opposing coach does not say "don't guard that guy, I want him to keep putting up 3s, he is due to miss." They change their defensive scheme, so he doesn't get any more open 3s.
Hotness can't be predicted, in that the Suns can't say in game 1 we guard Kobe because he is going to be hot, in game 2 we are going to let him shoot away, but hotness/coldness can be identified when it occurs.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I have never before heard this idea that stat heads don't think hot and cold exist. Anecdotally, Posnanski mentions statisticians crunching numbers and not finding evidence of, well...essentially, streaks...hitting or missing a number of times in a row that represents a statistical outlier, in terms of distribution. I don't believe it. I think this casual mention is bullshit and is either made up or a complete misinterpretation or misrepresentation of some statistical analysis.
<!--QuoteEnd--></div><!--QuoteEEnd-->
I'm not convinced that Posnanski understands stats much, because if he did he would understand that outside of the hard sciences, they have serious flaws.