Estimated read time: 2-3 minutes
This archived news story is available only for your personal, non-commercial use. Information in the story may be outdated or superseded by additional information. Reading or replaying the story in its archived form does not constitute a republication of the story.
PROVO — A Brigham Young University statistics professor and an alum have developed a statistical model that they believe can predict how many home runs major league baseball players will hit in upcoming seasons.
Using data from 1871-2008, professor Gil Fellingham and alum Jared Fisher's model takes into account the players' ERA, season of play, and ballparks to predict a player's “pure performance” curve.
The Bayesian semiparametric model was tested out on 22 players, using data from 2009-2016. Compared to other models, Fellingham and Fisher's Bayesian model proved to be accurate with 11 cases were superior to the simple hierarchical Bayesian model. Nine were equivalent and for two other cases, the old model predicted right.
To increase their ability to accurately predict home runs, Fellingham and Fisher added in control factors that might impact home run frequency such as mound heights, ERAs and elevation of the different ballparks.
“If you know where something’s going, you’ve got a leg up to get there and beat the competition,” Fellingham said in a statement. “And in sports, these players make a lot of money, so if you’re able to predict their performance better, general managers are better able to calibrate a contract.”
When asked to put his study in action and make a prediction on how many homers New York Yankee Aaron Judge will hit in the 2018 season, he compared Judge to Angels’ Albert Pujols’ pure performance curve. The Yankees rookie had a record-breaking 2017 season by hitting 52 homers.
To predict his home runs for the next season, Fillingham has to assume Judge’s record-breaking rookie year reflects his true ability and that he will have about the same amount of at-bats this upcoming season.
If all those things occur within the 2018 season, Fellingham expects Judge to hit at the same rate as he did last year, predicting around 53 homers from the Yankees star.
The research could change the game of baseball forever, particularly if managers have the tools to accurately predict players' performance, which can help them better negotiate contracts and select players for their teams.
“If you have a methodology that does a little better at predicting, then that’s worth pursuing,” Fellingham said. “What we’re trying to do is anticipate what is going to happen years down the road, and by being able to anticipate it, be better prepared.” Lexi Lewis is studying public relations at Utah Valley University. You can follow her on twitter @lex_lew1018.
