Sunday, November 15, 2026

Salaries and wins, 2006-2026

Salary and win data came from The Baseball Cube. For the years 2006-2026 (except for 2020), I calculated each team's average number of wins per year. For salary I calculated how much above or below the league average in total salary each team paid in percentage terms for each year. Then I took the average of that for each team over the years 2006-2026. Suppose a team was 10% above average one year and 30% above average another year, they would get 20 (if were just over two years).

Then I ran a regression with average wins per year as the dependent variable and the average salary (SAL, the % above or below the league average) as the independent variable.

Here is the regression equation

Wins = 0.112*SAL + 80.985

The r-squared was .437 and the standard error was 4.11 wins. The T-value for SAL was 4.66 (p-value 0.000070). The .112 means that if you spent 10% more on salaries than the average team, you win 1.12 more games than the average team. Also, if your average% was zero, then your team would win just about 81 games (80.985).

The graph below shows the relationship. The vertical axis is wins and the horizontal axis is SAL.

Image 

Back in 2008 I did a similar analysis that covered the years 1986-2005. See Another look at salaries and wins. 

Here is the regression equation from that earlier study:

Wins = 0.157*SAL + 80.22

The r-squared was .489 and the standard error was 3.89 wins. The T-value for SAL was 5.17. The .157 means that if you spent 10% more on salaries than the average team, you win 1.57 more games than the average team. 

No comments: