CB> Since 1990, a voucher experiment in Milwaukee has allowed more than 
CB> 2,000
CB> low-income students to go to private, nonreligious schools at public
CB> expense. Jay Greene, Paul Peterson, and Jiangto Du (GPD) recently 
CB> released
CB> a study arguing that Milwaukee private school voucher students do 
CB> better,
CB> 2. The GPD study has serious methodological flaws. GPD's main 
CB> analysis--the
CB> one they base their conclusions on--violates rules that even a 
CB> Statistics
CB> 101 student would be held accountable for observing. For example:
CB>      + The two student groups being compared are not the same. Yet in
CB>      their main analysis, GPD do not control for such differences as
CB>      parent education level, even though they acknowledge that such
CB>      differences could bias their results.
CB>      GPD claim that the Milwaukee voucher program provided a natural
CB>      experiment by "randomly assigning" students to two groups: those
CB>      selected to participate in the choice program (the experimental
CB>      group) and those not selected (the control group). Because the
CB>      process was "random," the authors argue that these two groups
CB>      share similar characteristics. However, the student selection
CB>      process was not random; the private schools retained the right 
CB> to
CB>      choose their students. Moreover, GPD's own back-of-report 
CB> numbers
CB>      show that the two groups were not similar, especially on parent
CB>      education level, one of the most significant out-of-school
CB>      influences on achievement research has ever found. The students
CB>      selected into the private schools had mothers (only mothers'
CB>      education level is presented) who had some college, while the
CB>      students who ended up in public school had high school dropout
CB>      mothers. 
    If the education level of the kid's mother was a major factor skewing the 
Milwaukee study, it may have a meaning voucher opponents would prefer to 
ignore: that vouchers can indeed deliver a real benefit to the kid of the 
mother who is relatively educated but lacks the money to send her kid to 
private school.
    This is far from saying that vouchers don't help kids.  Instead, it may 
mean that for some kids, they make all the difference.
--- Simplex BBS (v1.07.00Beta [DOS])
---------------