The Journal of Quantitative Analysis in Sports
has recently published a paper entitled "Did Steroid Use Enhance the Performance of the Mitchell Batters? The Effect of Alleged Performance Enhancing Drug Use on Offensive Performance from 1995 to 2007
). The authors are three professors of Public Health at Emory University.
If I'm understanding their methodology correctly from the abstract, they did not in fact use any control group for the study, but instead looked only at players named in the Mitchell Report, comparing their "tainted" seasons with their "clean" seasons in an ANOVA-like framework.
I'll withhold full judgment until I can read the article, but this doesn't seem like a sound methodology to me at first glance.