Well whenever agents and public relations types start constructing statistical analyses to defend their position, it's only a matter of time until the actual statisticians chime in.  After Roger Clemens' host of agents and handlers put together the Clemens Report to try and present his side of the story, a group of Penn business school professors broke down the report and identified some significant flaws in the methods used to construct it.  Both are interesting reads on their own, but unfortunately Clemens' agent, Randy Hendricks, just had to take shots at the professors yesterday, and he didn't come off sounding too knowledgeable.  Let's breakdown a few quotes from Mr. Hendricks:

"The purpose of the [Clemens] report is to provide the statistical background of Roger Clemens' career and to correct misconceptions about his career in the public forum."

Riiiiiiiiiiiiight.  This doesn't have anything to do with making the case that Clemens didn't use steroids or HGH, they just happened to have the URL rogerclemensreport.com on their hands and thought they'd get this info out there for the heck of it.  That's kind of like saying that Kermit Washington didn't really mean to hit Rudy Tomjanovich, his face just happened to be in the way of his swinging fist.

Then let's get to this gem.  The Clemens Report makes its case that his late-career success is very comparable to that of Nolan Ryan, Randy Johnson, and Curt Schilling.  The Penn group counters that in order to have a significant analysis, you need to include a representative sample of pitchers, not just the most successful ones - in their analysis, they looked at all pitchers since 1968 with more than 3,000 IP and at least 10 starts in 15 seasons.  Hendricks' response:

"Roger Clemens is not like every other pitcher in this group," the Hendricks statement read. "He is considered perhaps the best pitcher of his generation. The professors make the mistake of thinking that his career arc should look like the arc of every other pitcher in their selected group."

A sophomore high school geometry student could see through this one.  Hendricks is basically claiming that, since Clemens was great, he should only be compared to great pitchers.  Essentially, it should be automatically assumed that Clemens' greatness was legitimate.  Well, that's kind of what this whole thing is all about.  There is very valid questioning over whether his accomplishments are authentic or not.  In order to honestly analyze this whole situation, sorry Randy, but you have to compare him to a representative sample of pitchers.

"The professors make no adjustments for any of the changes that have taken place in baseball over the last forty years, treating every hit and walk exactly the same, despite the lowering of the pitching mound, the tightening of the strike zone, the changes in equipment, the addition of the designated hitter, the introduction of modern ballparks, and other factors that have affected the game over the years."

Again, another fallacy.  The professors are not looking at the absolute numbers, they're looking at statistical trends.  Clemens' performance improved significantly at a time when the great majority of other pitchers in his situation deteriorated.  It's not about a 2.00 vs. a 3.00 ERA over different eras, it's about career paths.

When the Congressional hearings take place on Wednesday, it's going to get ugly.  One thing is pretty clear from all of this; while you cannot definitively say that statistical analysis proves that Clemens did or did not use steroids or HGH, there is something very fishy going on.  Just my opinion, I'm siding with the professors.  Clemens' people's numbers just don't add up, and if I'm looking for statistical analysis to back up a claim on one side or the other, I'll go with the professors over the agents.