*I'm not particularly happy with the results of the pitcher estimator,
but I'm not sure what to do about it. No matter what I input, I cannot
get a model to explain more that 55% of the variance of player salaries.
It's frustrating, but there's not much I can do. One thing that bothers me
is that the model seems to consistently underestimate the salaries. While
I am certain that the market may be overvaluing pitchers, I find it hard to
believe that it is skewed so much. It's interesting to note that
Studes at
The Hardball Times also noticed the pitchers seem to be earning more than
their contributions to marginal wins share above replacement level. But, even with the limitations of the estimator, I think it can be useful
for comparing pitchers. I welcome any suggestions you have.