How does Hollinger still have a job?

[BballTim]

If you don't care about "stats" enough to understand them, its best not to mock them.

I understand stats quite well actually.  Which is why I dismiss them.

Subjective observation always will trump stats because there just aren't any stats that can account for the intangibles nessecary to be successful in sports.  Until someone can develope a way to measure a man's heart, determinantion, poise under pressure, etc., it will always be this way.

If you understood stats you'd know that statistical prediction consistently beats subjective prediction, in basketball and elsewhere.

  They seem to be discussing the understanding of specific basketball stats, not the theory of stats in general. You don't need to know about statistical prediction accuracy to understand PER or the like. Statistical prediction consistently beating subjective prediction would obviously be dependent on the accuracy of the prediction model and consistency of the data. I might be able to come up with a prediction model for the nba based on the height or age of the players but it wouldn't necessarily be more accurate than informed subjective prediction.

True though in this case if we're talking about score differential, how this thread started, I think it has been proven to be more accurate than subjective predictions on the aggregate.

Not really looking to argue the point anymore, just want to throw this out there.

Did not our very own beloved Celtics prove the scoring margin theory to be wrong last season?

Statistics deal with probabilities not certainties, what the Celtics did was unexpected by the majority of NBA observers. (including me!)

That doesn't mean you throw away 30+ years of data.

  What the Celtics did last year wasn't randomly outperform their expectations. There were specific reasons that the predictions were wrong and there were many people that would have had no problem pointing this out at any point before or during the playoffs. In other words, the "post mortems" of the many matched the predictions of a number of people (myself included).

The models are inherently going to fail when the team being studies isn't really *trying* their hardest to win.  We all know that the C's basically coasted into the playoffs, with the goal being to be healthy rather than to have the best possible record/playoff seeding.  That's going to skew every single statistic of theirs, and I'm not sure how any model is going to adjust for that.

  The problem wasn't a lack of effort, it was having two of our best players in and out of the lineup and, just as importantly, playing well below their typical level because they were playing through nagging injuries. Remember, they started out just fine until the injuries struck. But you're right, his model can't adjust to that. My (original) point was that, even though what was happening was outside his model he didn't make the obvious choice to ignore the data. Instead he searched the annals of the nba for teams that performed similarly to the Celts even though the reasons for the similar performances were obviously unrelated to what was happening.

[Boris Badenov]

His system looks at scoring differential not wins and losses. The Heat have beaten up the bad teams they've played by a large margin.

Does anyone else actually agree with this system?  In my opinion scoring differential doesn't mean too much in basketball.

  I think in general scoring differential is more important than records in predictions, but obviously there are more factors involved.

I agree.  But I think about all the times that a game is much different than the score says it was.  Garbage time has got to skew the results.

What's curious, to me, is not that Hollinger uses point differential rather than W/L. It's that he chooses between the two rather than incorporating both.

From a statistical standpoint, the goal of his system should be "goodness of fit," meaning its ability to explain as much variation in championship success as possible.

And from that same standpoint, it HAS to be true that a model incorporating both W/L and differential will outperform a model using only one of those. It's very simple: the more information you use, the better your model. This will be true even if point differential is a much better predictor of who wins championships, as long as W/L contains some information that differential does not contain.

Too many variables often reduces the predictive power and goodness of fit of a model.

Adding variables cannot reduce how well the model fits the data.

Goodness of fit is, in the situation faced by Hollinger, probably best measured by R-squared (I suspect that he's using linear regression).

http://en.wikipedia.org/wiki/Coefficient_of_determination

"R2 is a statistic that will give some information about the goodness of fit of a model."

"In this case R-squared increases as we increase the number of variables in the model (R2 will not decrease)."

There is something called adjusted R-squared that may fall as you include more variables - but Hollinger should care about the unadjusted R-squared.

[Fafnir]

His system looks at scoring differential not wins and losses. The Heat have beaten up the bad teams they've played by a large margin.

Does anyone else actually agree with this system?  In my opinion scoring differential doesn't mean too much in basketball.

  I think in general scoring differential is more important than records in predictions, but obviously there are more factors involved.

I agree.  But I think about all the times that a game is much different than the score says it was.  Garbage time has got to skew the results.

What's curious, to me, is not that Hollinger uses point differential rather than W/L. It's that he chooses between the two rather than incorporating both.

From a statistical standpoint, the goal of his system should be "goodness of fit," meaning its ability to explain as much variation in championship success as possible.

And from that same standpoint, it HAS to be true that a model incorporating both W/L and differential will outperform a model using only one of those. It's very simple: the more information you use, the better your model. This will be true even if point differential is a much better predictor of who wins championships, as long as W/L contains some information that differential does not contain.

Too many variables often reduces the predictive power and goodness of fit of a model.

Adding variables cannot reduce how well the model fits the data.

Goodness of fit is, in the situation faced by Hollinger, probably best measured by R-squared (I suspect that he's using linear regression).

http://en.wikipedia.org/wiki/Coefficient_of_determination

"R2 is a statistic that will give some information about the goodness of fit of a model."

"In this case R-squared increases as we increase the number of variables in the model (R2 will not decrease)."

There is something called adjusted R-squared that may fall as you include more variables - but Hollinger should care about the unadjusted R-squared.

Its been a while since I delved into the detailed terminology. I was thinking of over fitting.

Also since there is a heavy correlation between score differential and wins and losses, they aren't independent. I don't think its all that surprising that he doesn't use raw wins/losses due to this.

[guava_wrench]

If you don't care about "stats" enough to understand them, its best not to mock them.

I understand stats quite well actually.  Which is why I dismiss them.

Subjective observation always will trump stats because there just aren't any stats that can account for the intangibles nessecary to be successful in sports.  Until someone can develope a way to measure a man's heart, determinantion, poise under pressure, etc., it will always be this way.

If you understood stats you'd know that statistical prediction consistently beats subjective prediction, in basketball and elsewhere.

  They seem to be discussing the understanding of specific basketball stats, not the theory of stats in general. You don't need to know about statistical prediction accuracy to understand PER or the like. Statistical prediction consistently beating subjective prediction would obviously be dependent on the accuracy of the prediction model and consistency of the data. I might be able to come up with a prediction model for the nba based on the height or age of the players but it wouldn't necessarily be more accurate than informed subjective prediction.

True though in this case if we're talking about score differential, how this thread started, I think it has been proven to be more accurate than subjective predictions on the aggregate.

Not really looking to argue the point anymore, just want to throw this out there.

Did not our very own beloved Celtics prove the scoring margin theory to be wrong last season?

Statistics deal with probabilities not certainties, what the Celtics did was unexpected by the majority of NBA observers. (including me!)

That doesn't mean you throw away 30+ years of data.

  What the Celtics did last year wasn't randomly outperform their expectations. There were specific reasons that the predictions were wrong and there were many people that would have had no problem pointing this out at any point before or during the playoffs. In other words, the "post mortems" of the many matched the predictions of a number of people (myself included).

There are some major problems with objections I regularly hear of Hollinger's work.

Look at his playoff odds. Nowhere did it say that the Celtics can't win. The odds of the Celtics making the finals in his playoff odds were probably much higher than the % of basketball savvy individuals who picked the Celtics (since almost no one did apart from Celtics fans who are obviously not disinterested).

The alleged ability to point out the reasons why the Celtics would succeed in last year's playoffs is nonsense. That is typical armchair quarterbacking where the lay fan ignores all the times they are horribly wrong while focusing on when they end up correct, even though they felt just as sure about their wrong predictions as their correct ones.

I suppose some could argue that Lakers fans are smarter than the rest of us because a much higher percentage of Lakers fans predicted the last 2 NBA champions. Lebron fans are also more intelligent about basketball because a higher percentage of them were able to predict the last 2 MVPs.

I in fact knew the Celtics would make it to the finals. I knew that if I wore my lucky hat, no team in the East could beat them. My prediction was correct (let's ignore those other times I wore the hat).

More significantly, in most seasons, even the best, most informed prediction before the playoffs has a greater than 50% chance of being wrong.

If we were to do a study of the correctness of subjective predictions, we would find that they are horrible. Predictions are bad in general. Evaluations of teams are so steeped in sentimental mumbo-jumbo.

Hollinger regularly points out that no statistical analysis can really account for the impact of injuries or effort. This is one of many places where he counts on readers not being idiots and being able to fill in the blanks.

The problem is that when some fill in those blanks, they act as if he is an ignoramus, ignoring that he regularly talks about the flaws of his metric.

[BballTim]

If you don't care about "stats" enough to understand them, its best not to mock them.

I understand stats quite well actually.  Which is why I dismiss them.

Subjective observation always will trump stats because there just aren't any stats that can account for the intangibles nessecary to be successful in sports.  Until someone can develope a way to measure a man's heart, determinantion, poise under pressure, etc., it will always be this way.

If you understood stats you'd know that statistical prediction consistently beats subjective prediction, in basketball and elsewhere.

  They seem to be discussing the understanding of specific basketball stats, not the theory of stats in general. You don't need to know about statistical prediction accuracy to understand PER or the like. Statistical prediction consistently beating subjective prediction would obviously be dependent on the accuracy of the prediction model and consistency of the data. I might be able to come up with a prediction model for the nba based on the height or age of the players but it wouldn't necessarily be more accurate than informed subjective prediction.

True though in this case if we're talking about score differential, how this thread started, I think it has been proven to be more accurate than subjective predictions on the aggregate.

Not really looking to argue the point anymore, just want to throw this out there.

Did not our very own beloved Celtics prove the scoring margin theory to be wrong last season?

Statistics deal with probabilities not certainties, what the Celtics did was unexpected by the majority of NBA observers. (including me!)

That doesn't mean you throw away 30+ years of data.

  What the Celtics did last year wasn't randomly outperform their expectations. There were specific reasons that the predictions were wrong and there were many people that would have had no problem pointing this out at any point before or during the playoffs. In other words, the "post mortems" of the many matched the predictions of a number of people (myself included).

There are some major problems with objections I regularly hear of Hollinger's work.

Look at his playoff odds. Nowhere did it say that the Celtics can't win. The odds of the Celtics making the finals in his playoff odds were probably much higher than the % of basketball savvy individuals who picked the Celtics (since almost no one did apart from Celtics fans who are obviously not disinterested).

  Who said that Hollinger claimed the Celts can't win? And what % of the basketball savvy individuals agreed with him? Specifics, please.

The alleged ability to point out the reasons why the Celtics would succeed in last year's playoffs is nonsense. That is typical armchair quarterbacking where the lay fan ignores all the times they are horribly wrong while focusing on when they end up correct, even though they felt just as sure about their wrong predictions as their correct ones.

  Yes, that's obviously it. People *have* to be wrong most of the time if they don't use stats, your mommy/daddy/favorite teacher at school said so.

I suppose some could argue that Lakers fans are smarter than the rest of us because a much higher percentage of Lakers fans predicted the last 2 NBA champions. Lebron fans are also more intelligent about basketball because a higher percentage of them were able to predict the last 2 MVPs.

  Because no non-Laker fans thought they had a chance to win the title? Because nobody outside of Cleveland thought LeBron could win the MVP? Please.

I in fact knew the Celtics would make it to the finals. I knew that if I wore my lucky hat, no team in the East could beat them. My prediction was correct (let's ignore those other times I wore the hat).

  The hat's always lucky, just not always lucky for the owner. Anyone who knows anything knows this.

More significantly, in most seasons, even the best, most informed prediction before the playoffs has a greater than 50% chance of being wrong.

If we were to do a study of the correctness of subjective predictions, we would find that they are horrible. Predictions are bad in general. Evaluations of teams are so steeped in sentimental mumbo-jumbo.

  Yes, everyone who makes any kind of basketball prediction does so horribly. Everyone who gambles on sports loses money hand over fist. They gamble not in hopes of winning but because they'd like to see their favorite bookie/casino do well, not because they have any hopes of winning.

  It's a well known fact, at least to you, that people's predictions are always less accurate than statistcal predictions. It doesn't really matter how accurate the statistical prediction is, just being based on statistics makes it inherently superior.

Hollinger regularly points out that no statistical analysis can really account for the impact of injuries or effort. This is one of many places where he counts on readers not being idiots and being able to fill in the blanks.

The problem is that when some fill in those blanks, they act as if he is an ignoramus, ignoring that he regularly talks about the flaws of his metric.

  Haha. Finally, you and your lucky hat arrive at the point. Maybe the hat's lucky after all, at least for you, at least for the last line or two of your post. When the Celts were outperforming expectations last year he didn't just chalk it up to not being able to account for things like injury and effort. He tried to determine how well the Celts would do by comparing them to other teams that had similar seasons vs playoff runs, albeit for completely different reasons. Apparently he was one of the idiots that was unable to fill in the blanks that you're referring to.