statistics, lies, and roger clemens

Roger Clemens’s agent released an 18,000 word report that presents and analyzes a number of statistics (OK, a LOT of statistics) based on Roger Clemens’s 24-year career. The purpose of the report is to “prove” that Roger Clemens did not use performance enhancing drugs. I didn’t have time to read the entire report, but the gist of the “proof” is that all of his abnormally good statistics are just random deviations that we would expect to see. Although feigning randomness is a legitimate defense, I don’t buy it, and neither does anyone else. Tim Keown of ESPN concurs, writing that

The bulk of the report is a skull-crushing dissection of nearly every start the man ever made. It is placed in the context of run support and other factors I think are supposed to make you believe Clemens is … not a steroid user… Comparisons with Curt Schilling, Randy Johnson and Nolan Ryan are central to the report. They all had abnormal strikeout seasons at ages when even the greatest pitchers are retired, which proves … what, exactly?

This is the most mathematical defense against using steroids that I have seen, but I’m not impressed. However, I’m not one of those people that analyzes baseball statistics, so I could be wrong.

Read better sports and statistics applications in The Journal of Quantitative Analysis in Sports.

One response to “statistics, lies, and roger clemens

  • Dharkko

    I have a problem with Roger Clemens and his lawyer coming out with a book of statistics to prove that he didn’t take performance enhancing drugs like HGH , steroids and the like. The Roger Clemens Report study looks at his performance in reference to the changing playing environment of the league, trying to prove that his erratic play over time proves that he was natural. Quite a stretch when there are so many factors that are always involved in what finally makes up sports statistics. The authors of the study compare Clemens’s ERA to the average of the league, looking at the difference. No surprise that his ERA difference fluctuated quite a bit over the course of his career, as it is inherently a volatile statistic. I’m not quite sure what he planned to gain from this and there is much to lose.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: