PDA

View Full Version : On Streakiness



RedsManRick
01-21-2011, 12:47 PM
Fangraphs has done a great analysis on streaks and streakiness.

http://www.fangraphs.com/blogs/index.php/were-going-streaking-again/

As with clutch, there has long been analysts, professional and amateur, who assign streakiness as a characteristic of a player -- usually in the form of its converse consistency.

But there's an important distinction between the historical artifact of a streak and the idea that players possess an inherent ability related to consistency. Any stat geek such as myself will assert that streaks are bound to occur even when no such skill underlies it. But that doesn't really prove either way if the skill exists -- just that observing streaks is insufficient proof (particularly in light of the human instinct to see pattens everywhere, even where they don't exist, and the fundamental attribution error -- inappropriately ascribing outcomes to human characteristics).

That all said, I highly recommend people read the article.

And for the lazy among us, the conclusion:

So what, ultimately, can we take away from all of this? Although the analysis is complicated, the lessons it teaches us are straightforward. Streaky seasons undoubtedly exist. However, it appears that there is no such thing as a streaky or unstreaky player. Rather, the truth seems to be that all players are streaky players. Being human, they have their ups and downs, and they are inherently streakier than random chance would dictate.

http://www.fangraphs.com/blogs/index.php/were-going-streaking-again/

RANDY IN INDY
01-21-2011, 03:21 PM
Fangraphs has done a great analysis on streaks and streakiness.

http://www.fangraphs.com/blogs/index.php/were-going-streaking-again/

As with clutch, there has long been analysts, professional and amateur, who assign streakiness as a characteristic of a player -- usually in the form of its converse consistency.

But there's an important distinction between the historical artifact of a streak and the idea that players possess an inherent ability related to consistency. Any stat geek such as myself will assert that streaks are bound to occur even when no such skill underlies it. But that doesn't really prove either way if the skill exists -- just that observing streaks is insufficient proof (particularly in light of the human instinct to see pattens everywhere, even where they don't exist, and the fundamental attribution error -- inappropriately ascribing outcomes to human characteristics).

That all said, I highly recommend people read the article.

And for the lazy among us, the conclusion:


http://www.fangraphs.com/blogs/index.php/were-going-streaking-again/

Good article, Rick. Would agree that all players are streaky. Some just have longer or more consistent streaks than others.

RedsManRick
01-21-2011, 06:20 PM
Good article, Rick. Would agree that all players are streaky. Some just have longer or more consistent streaks than others.

As a historical reality, of course they do. Over time, some players will have greater streakiness than others. But that would be expected even in a world where there was no such thing as a streakiness skill. Just like if you had a bunch of people flip coins 100 times. Everybody will experience streaks. Some people will experience more streaks than others. But the question is whether or not those streaks have predictive value regarding future streakiness. If you stop after 50 flips and take the streakiest flippers and compare their next 50 flips to the rest of the group, they'll look the same.

Did those guys have longer or more consistent streaks because they are higher on the scale of a skill called streakiness? Or is it just that those guys just happened to be the guys who ended up being the ones who flipped 10 heads in a row twice over this stretch of time? The ones who drew the short straw.

This analysis suggests it it's latter. So most every player experiences runs of success or failure above and beyond what random chance would predict. But if you take a group of guys who have been particularly streaky and watch them in subsequent years, they tend to end up looking like the rest of the population rather than continuing to be extra streaky. That is, everybody is streaky and players will experience varying levels of streakiness. But you can't accurately say that some people are inherently more streaky than others. Experience does not equal characteristic.

Here's the key paragraph from the article:

Knowing a player’s streakiness in one season effectively gives us no ability at all to predict his streakiness in the next. In fact, even knowing a player’s streakiness in three consecutive seasons gives us no ability to say anything about the fourth. Streakiness also appears random within a given season: correlation between streakiness from one month to the next (minimum 100 PA) is r = 0.013, which is, again, not statistically different from zero (N = 3,844, p = 0.413). In short, if we believe our methodology—which I personally have no reason to doubt, although I’m open to suggestions—streakiness among hitters appears to be completely random.

To be clear, I don't have a position based on my own personal experience -- I'm just trying to provide clarity on what the study concluded.

BCubb2003
01-21-2011, 08:08 PM
I think that by definition, streakiness is not a skill. If it were, players were never stop their streak, and therefore it wouldn't be a streak.

Also, the longer and more consistent a streak is, the less streaky it is.

But I could buy the claim that streakiness is probably random, like clutch.