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.
In Week 12, I went into the difference between regression to the mean, (the idea that production will probably improve or decline going forward), and the gambler's fallacy, (the idea that production is "due" to improve or decline going forward). No specific prediction was made.
In Week 13, I badmouthed interception rate for a bit and then predicted that the most interception-prone quarterbacks to that point would throw fewer picks than the least interception-prone quarterbacks going forward.
In Week 14, I delved into the various biases that permeate this column and how regression to the mean works even in less spectacular ways than the ones I choose to highlight here. No specific prediction was made.
In Week 15, I explained why regression was especially cruel in the fantasy playoffs. No specific prediction was made.
Statistic For Regression
|
Performance Before Prediction
|
Performance Since Prediction
|
Weeks Remaining
|
Yards per Carry
|
Group A had 24% more rushing yards per game
|
Group B has 4% more rushing yards per game
|
SUCCESS!
|
Yards:Touchdown Ratio
|
Group A had 28% more fantasy points per game
|
Group B has 23% more fantasy points per game
|
SUCCESS!
|
Yards per Target
|
Group A had 16% more receiving yards per game
|
Group A has 13% more receiving yards per game
|
Failure
|
Yards:Touchdown Ratio
|
Group A had 26% more fantasy points per game
|
Group B has 4% more fantasy points per game
|
SUCCESS!
|
Yards per Carry
|
Group A had 9% more rushing yards per game
|
Group B has 23% more rushing yards per game
|
SUCCESS!
|
Total Interceptions
|
Group A had 83% as many total interceptions
|
Group B has 46% as many total interceptions
|
1
|
At the time I made my interception prediction, Group A had thrown 78 interceptions and Group B had thrown 94. In the three weeks since, Group A has thrown 35 interceptions and Group B has thrown just 16. Group B has dominated Group A every single week, throwing 5, 6, and 5 interceptions compared to 12, 11, and 12. And that Group A total doesn't even include the interception that Drew Brees threw on a 2-point conversion attempt that the Panthers returned for two points of their own.
In the last three weeks, Aaron Rodgers has doubled his interception total (from 1 to 2); Drew Brees (2 to 5) and Jared Goff (6 to 13) have more than doubled their totals. The only starting quarterbacks in our sample who haven't thrown an interception are Deshaun Watson from Group B and Derek Carr... who was the most interception-prone quarterback in Group A. Interceptions aren't completely random... but over the size samples we're dealing with, they're not very far from it.
There's one week left to go on the prediction, but Group B could throw as many interceptions this week as they have in the last three weeks combined, and Group A could collectively not throw a single pick, and Group B would still pull this out.
Everything is Awful and Everyone is Hurt
I mentioned last week that I was planning on ending the season with a special one-week-only regression prediction. The idea was to predict the regular-season stars who had been up-and-down in the fantasy playoffs to show up big in week 16. When I said that, I was counting on the short-term injury trend regression, too. So far, it... hasn't.
Cam Newton has been shut down for the season. James Conner has gone from likely to unlikely to appear this weekend. Todd Gurley's status is suddenly up in the air. Aaron Jones has been placed on injured reserve. Odell Beckham Jr and Julio Jones are both major question marks, as are T.Y. Hilton and Keenan Allen. This adds to several weeks worth of bad news for top performers, removing Melvin Gordon, Kareem Hunt, A.J. Green, Cooper Kupp, Rob Gronkowski, O.J. Howard, and a raft of other top contributors. 2018 will be uniquely remembered for how much the playoff picture shifted in the final few weeks.
I often stress that the key to regression is allowing larger samples. The more players I can include, the more weeks I can run, the more games in the sample, the more regression to the mean is going to show its impact. Obviously, I can't allow four weeks for a final prediction, but I figured if I could get enough players in my sample I could help offset that. But with so many of the players I wanted to talk about questionable or worse, I don't feel comfortable making and scoring a specific prediction. The samples involved will just be too small and the expected success rate would be too low.
I will say this: larger samples are always more predictive than smaller ones. This means that playoff heroes like Derrick Henry should be expected to produce more in line with his full-season ranking (RB13 in standard scoring) than his recent-weeks production (RB1 by a country mile since the fantasy playoffs started). Similarly, ice-cold Drew Brees should be expected to score in week 16 more in line with his QB5 ranking over the full season than his QB24 ranking over the last two weeks.
If you're a top seed who survived to your championship game despite duds from your biggest stars, take heart in the fact that help is probably on the way this week. If you've reached the title game on the back of out-of-nowhere offensive explosions by bit players, understand that week 16 likely presents an uphill battle for the title.
But to anyone still alive: no matter what, don't despair. Regression to the mean dominates over large samples, but a title game is the smallest sample around, which means anything and everything is still in play.