A baseball team would be considered “streaky” if its record exhibits an unusually high number of consecutive wins or losses, compared to what might be expected if the team’s performance does not really depend on whether or not they won their previous game. If an average team in Major League Baseball (i.e., with a record of 81-81) is not streaky, we assume its win probability would be stable at around 50% for most games, outside of peculiar details of day-to-day outcomes, such as whether the game is home or away, who is the starting pitcher, and so on.
In this paper, we investigate win outcomes for every major league team between 1962 and present (the year both leagues expanded to play 162 games per season) in order to find out if teams exhibit any significant streakiness. We use a statistical “runs test” based on the observed sequences of winning streaks and losing streaks accumulated during the season. Overall, our findings are consistent with what we would expect if no teams exhibited a nonrandom streakiness that belied their overall record. That is, major league baseball teams, as a whole, are not streaky.
Copyright © 2017 SABR.
The definitive version is available at: https://sabr.org/research/comprehensive-analysis-team-streakiness-major-league-baseball-1962-2016
Kvam, Paul H., and Zezhong Chen. "A Comprehensive Analysis of Team Streakiness in Major League Baseball: 1962-2016." Baseball Research Journal 46, no. 2 (2017): 112-115.
Kvam, Paul H. and Chen, Zezhong, "A Comprehensive Analysis of Team Streakiness in Major League Baseball: 1962-2016" (2017). Math and Computer Science Faculty Publications. 203.