Photo: Imagn Images

Welcome to Regression Alert, your weekly guide to using regression to predict the future with uncanny accuracy.

For those who are new to the feature, here's the deal: every week, I dive into the topic of regression to the mean. Sometimes I'll explain what it really is, why you hear so much about it, and how you can harness its power for yourself. Sometimes I'll give some practical examples of regression at work.

In weeks where I'm giving practical examples, I will select a metric to focus on. I'll rank all players in the league according to that metric, and separate the top players into Group A and the bottom players into Group B. I will verify that the players in Group A have outscored the players in Group B to that point in the season. And then I will predict that, by the magic of regression, Group B will outscore Group A going forward.

Crucially, I don't get to pick my samples, (other than choosing which metric to focus on). If the metric I'm focusing on is 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.

Most importantly, because predictions mean nothing without accountability, I track the results of my predictions over the course of the season and highlight when they prove correct and also when they prove incorrect. Here's a list of all my predictions from last year and how they fared.

THE SCORECARD

In Week 2, I laid out our guiding principles for Regression Alert. No specific prediction was made.

In Week 3, I discussed why yards per carry is the least useful statistic and predicted that the rushers with the lowest yard-per-carry average to that point would outrush the rushers with the highest yard-per-carry average going forward.

In Week 4, I explained why touchdowns follow yards, (but yards don't follow back), and predicted that the players with the fewest touchdowns per yard gained would outscore the players with the most touchdowns per yard gained going forward.

In Week 5, I talked about how preseason expectations still held as much predictive power as performance through four weeks. No specific prediction was made.

In Week 6, I looked at how much yards per target is influenced by a receiver's role, how some receivers' per-target averages deviated from what we'd expect according to their role, and predicted that the receivers with the fewest yards per target would gain more receiving yards than the receivers with the most yards per target going forward.

In Week 7, I demonstrated how randomness could reign over smaller samples, but regression dominates over larger ones. No specific prediction was made.

In Week 8, I discussed how even something like average career length could be largely determined by regression-prone fluctuations in incoming talent. No specific prediction was made.

In Week 9, I looked at running backs scoring touchdowns at an unsustainable rate and posited that even Todd Gurley must return to earth.

In Week 10, I delved into the purpose of regression alert and the proper takeaways. No specific prediction was made.

In Week 11, I explained an easy way to find statistics that were more prone to regression and picked on yards per carry one more time.

Our "low-touchdown" running backs had a phenomenal week, marking the second straight time they outscored the "high-touchdown" running backs straight up and putting themselves in fantastic position to flip the results with a strong final week. Before that prediction closes, a thought. The impetus behind the prediction was asking whether even sublime talents in perfect situations like Todd Gurley regress to the mean. And while there's officially one week left on the prediction, Gurley is off next week with a bye, which means his sample is done.

As of right now, he ranks 5th out of the 8 Group A backs in points per game. Including him reduced Group A's average! And the Group B backs are actually outscoring him straight up with 15.3 points per game to Gurley's 15.1. No one is immune to the forces of regression.

Finally, what more can I say about yards per carry, other than "it's not a thing". A lot of people think it's a thing, but that doesn't make it a thing. Heading into last week, Group A backs averaged 5.7 yards per carry and Group B backs averaged 4.1 yards per carry. Last week, Group A backs averaged 4.7 yards per carry and Group B backs averaged 4.6 yards per carry. I really cannot stress enough that yards per carry absolutely, positively, 100% is not a thing. It's 90% noise and 10% signal. Whenever I have a rough run of predictions it's nice to return to yards per carry for an easy win.

(Now watch Group A have a fantastic three weeks to close us out and leave me looking foolish.)

Julio Jones and Receiving Touchdowns

You may have heard that, after very nearly becoming the first player in history to gain 1,000 receiving yards without scoring a touchdown, Julio Jones has now scored in three straight games. I spend a lot of time on Twitter, which is obviously a biased news ecosystem, but I feel like every touchdown he scores at this point might as well be accompanied by a klaxon. I half expected the New York Times to run a full-page spread in the sports section that merely said "Julio Jones scores touchdown" in 180-point font.

Jones is one of the patron saints of Regression Alert. The entire idea for the column sprung from an article I wrote in 2015 that looked back at a pair of posts I'd made in 2014 about Jones and Le'Veon Bell when they were piling up the yards but failing to reach the end zone. I predicted based on history that they would start reaching the end zone again soon, they did exactly that, and the rest is history.

Heading into 2018, Julio Jones scored one touchdown for every 210 yards during his career, but this figure is a little bit misleading. Jones' career raises interesting questions, such as "can a player's 'true mean' change over time?" The answer: yes, it certainly can! For instance, it's hard to believe it now, but early on in his career, Jones was actually quite the touchdown threat.

Did you know: there once was a time when Julio Jones caught touchdowns and Antonio Brown did not?

Here's the top receivers from 2011-2012 sorted by yards gained per touchdown scored. pic.twitter.com/Y0Z4wHJ9xW

— Adam Harstad (@AdamHarstad) November 9, 2018

Same thing, but 2014-2018. pic.twitter.com/ps2W9VWpeo

— Adam Harstad (@AdamHarstad) November 9, 2018

Thanks to his mini scoring explosion, Julio is now averaging 386 yards per touchdown for 2018, which is below his 2014-2018 average, but within striking distance. Another touchdown or two and his 2018 average is right in line with his recent career average again.

Does this mean that Julio Jones is "due" for another touchdown or two? No, that's the old gambler's fallacy rearing its ugly head. Just because a player has underperformed their true mean does not mean they're more likely to overperform their true mean to offset. That's not how regression works.

Just as the scoring drought to begin the season was not actually a new normal, neither is the recent scoring onslaught a new normal. Jones has six games left to play this year. If history is any indication, (and it is), he'll probably get around 600 receiving yards, barring injury. And based on his long-term averages, those 600 yards will probably bring 2 or 3 touchdowns— not enough to please his harshest critics, but maybe enough to silence the klaxons until 2019.