Welcome to Regression Alert, your weekly guide to using regression to predict the future with uncanny accuracy.
Returning readers, you know how this works by now, but for new readers here's the deal. Every week I take a look at a specific statistic that is prone to regression and identify high and low outliers in that statistic, and then I wave my hands in the air and shout “regression!”
But since predictions aren't any fun without someone holding your feet to the fire afterward, I don't stop there. I lump all of the high outliers into Group A. I lump all of the low outliers into Group B. I verify that Group A is outperforming Group B. And then I predict that Group B will outperform Group A over the next four weeks.
I don't get to pick and choose my groups, beyond being free to pick and choose what statistics are especially prone to regression. If I'm tracking yards per target, and Antonio Brown is one of the high outliers in yards per target, then Antonio Brown goes into Group A and may the fantasy gods show mercy on my predictions.
And then, groups chosen and predictions made, I track my progress. That's this.
In Week 2, I outlined what regression was, what it wasn't, and how it worked. No prediction was made.
In Week 3, I listed running backs with exceptionally high and low yards per carry averages and predicted that the low-ypc cohort would outperform the high-ypc cohort over the next four weeks.
In Week 4, I looked at receivers who were overperforming and underperforming in yards per target and predicted that the underperformers would outperform the overperformers over the next four weeks.
In Week 5, I compared the predictive accuracy of in-season results to the predictive accuracy of preseason ADP. Outside of a general prediction that players would tend to regress in the direction of their preseason ADP, no specific prediction was made.
In Week 6, I looked at quarterbacks who were throwing too many or too few touchdowns given the amount of passing yards they were accumulating, then predicted that the underperformers would score more fantasy points than the overperformers going forward.
In Week 7, I looked at receivers who were catching too many or too few touchdowns based on their yardage total, then predicted that the underperformers would score more fantasy points than the overperformers going forward.
In Week 8, I revisited yards per carry, again predicting that the high-carry, low-ypc group would outrush the low-carry, high-ypc group going forward.
In Week 9, I went back to yard to touchdown ratios, predicting that the low-touchdown group would close the gap substantially with the high-touchdown group going forward.
|Statistic for regression||Performance before prediction||Performance since prediction||Weeks remaining|
|yards per carry||Group A had 60% more rushing yards per game||Group B has 16% more rushing yards per game||None (Win!)|
|yards per target||Group A had 16% more receiving yards per game||Group B has 11% more receiving yards per game||None (Win!)|
|passing yards per touchdown||Group A had 13% more fantasy points per game||Group A has 17% more fantasy points per game||None (Loss)|
|receiving yards per touchdown||Group A had 28% more fantasy points per game||Group A has 7% more fantasy points per game||1|
|yards per carry||Group A had 25% more fantasy points per game||Group B has 1% more fantasy points per game||2|
|rushing yards per touchdown||Group A had 21% more fantasy points per game||Group A has 147% more fantasy points per game||3|
Pay no attention to that last line; 147% sounds daunting, but the entire sample to this point is just three games per group, so it largely boils down to “Todd Gurley had a big week and Le'Veon Bell was on bye”.
The passing yard per touchdown prediction, however, has come due and handed regression its first loss of the season. I wish I could say that there was a simple explanation. There were certainly a lot of contributing factors— Jameis Winston dealt with an injury that had him leaving two games early and clearly impacted him in a third, for instance.
But there was no single factor that would have flipped the result. Alex Smith, Dak Prescott, Carson Wentz, Deshaun Watson, and Matthew Stafford all had hot starts to the season, but rather than cooling down they actually ramped their production up over ensuing weeks.
Again, the mantra of this column is these things wash out in the long run, but “in the long run” doesn't really lend itself well to accountability. So, in this case, there's really nothing to do but take the loss and move on.
Anyway, on to the prediction.
On Second Thought...
Actually, in lieu of a prediction this week, I'd like to drill down some more into the one that just failed.
Tom Brady is a pretty good quarterback. Early in his career, people called him a “game manager” and suggested that he was just a caretaker riding his defense and running game to victories.
In 2007, Brady took that narrative and smashed it to pieces. And he's continued smashing it ever since. In the ten seasons since, he's averaged 35 touchdown passes per 16 games. Over that span, 5.9% of all of his pass attempts have been touchdowns.
Peyton Manning holds pretty much every statistical record worth owning by a quarterback. No passer in history has made more pro bowls, earned more 1st Team All Pro nods, or been awarded more league MVPs. For his career, he averaged a touchdown on 5.7% of his passes, but that total is dragged down by his first two seasons and his last season; outside of those years, he threw a touchdown on 6.0% of his passes.
As I mentioned in the original yard-to-TD ratio piece, Aaron Rodgers is a touchdown-throwing machine. Adjusted for era, no quarterback has thrown touchdowns at a higher rate than he has. For his career, he has thrown a touchdown on 6.4% of his passes.
These players represent the limit of human performance over a long timeline. They are three of the best and most prolific quarterbacks to ever play, and these values represent their performance at their very peaks.
This season, Deshaun Watson's touchdown rate is 9.3%. Carson Wentz's is 7.9%. Dak Prescott's is 6.2%. Alex Smith's is 6.1%. I feel like it's not going out on too thin of a limb to suggest that all four of these quarterbacks are unlikely to end their career regarded as one of the five best players to ever play the position.
It's not, I feel, sour grapes to suggest that these rates are completely unsustainable. The fact that I said the same thing four weeks ago and they somehow managed to sustain them, (and in some cases improve them), doesn't alter this fact. Carson Wentz is probably not as good as Aaron Rodgers, so he's extremely unlikely going forward to average a touchdown rate higher than Rodgers has had in all but one of his seasons.
Again, the animating principle of this column is accountability. I make a prediction, I track the prediction, I report the results. And accountability demands smaller timelines, because nobody wants to wait three years to revisit these predictions.
But I do feel it needs to be said that just because regression didn't hit this time doesn't mean that regression isn't going to hit. Over a long enough timeline, it's inevitable.
More articles from Adam HarstadSee all
More articles on: AnalysisSee all
Beating the Odds: Week 19 - Zamichieli
Beating the Odds: Week 18 - Zamichieli
Monkey Knife Fight Player Props, Week 18 - Hindery