Hey Regression your jealousy is showing……
You can have regression up or down.
If your sample consists of below-MLB-mean winners (or loses), like the Cubbies the regression to the mean will make it appear that they move up in number of wins. But if your sample consists of high winners, like our World Champion Chicago White Sox, their mean will appear to move down relative to the number of wins. However, this all depends on the “r” or the correlation measuring how well one team plays baseball vs. another team or vs. the rest of MLB.
You can estimate exactly the percent of regression to the mean in any given situation. The formula is:
Prm = 100(1 - r)
where:
Prm = the percent of regression to the mean
r = the correlation measuring how well one team plays vs. another or to MLB
Given this formula the World Champion Chicago White Sox's “r” equals 1 (or maybe .9 because no one is perfect), and the Cubbies’ “r” equals 0 (or maybe .2 because no team can stink up the field that bad, maybe…except the Cubbies). Just do the math. This proves that the World Series Chicago White Sox have a small propensity to regress to the mean (r = 1 would be 0%) and that the Cubbies have a greater statistical correlation to regress to the mean (this is a good thing for Cubbie Blue fans, r = 0 would be 100%, it give you hope!!!).
Regression, thank for bring this up…. Don’t you just love numbers?
“Statistics are used like a drunk uses a lamppost…. For support, not illumination.” ~ Vin Scully
“Fans come to Comiskey Park to watch the game. They appreciate good baseball, and when you don’t play good baseball, they’ll let you know about that, too. But most people go to Wrigley Field to see how many bars they can hit before and after the game. Wrigley Field is more of a tourist attraction than anything else” ~ Paul Konerko, 2001