Monday, May 22, 2023
How bad will the A’s be?
Back in 2006, I developed a rather simple method to establish the true talent level of sports leagues (ANY sports league). For baseball specifically, and I'll use the A's as an example: you add 35 wins and 35 losses (a 35-35 record) to their current record, which you then convert to a win%. That's it.
So, for the A's, their 10-38 record (aka their OBSERVED record) gets a 35-35 record added (aka their PRIOR). Together that gives us 45-73, which as a percentage is .381 win%, their true talent record, their rest-of-season record (aka their POSTERIOR). With 114 games remaining, at a .381 win%, that gives us 43.5 rest-of-season wins. And so, our expectation is they will end the season with 53-54 wins.
Now, historically, how well has this method held up with such extreme teams? Well, thanks to Dan at Fangraphs, we can test our theory. I'm going to use only teams since 1950, which gives me 19 teams. Those teams averaged 11.8 wins in 48 games. Our expectation for their rest-of-season win% is .397, for a final Won-Loss record of 54-101. And what was their actual final Won-Loss record? Would you believe.... 54-101.
In other words, this method, developed 17 years ago to handle a broad set of teams perfectly works with the most extreme of extreme teams.