Xiao-Li Meng

Same Passion But Different Populations

Flowing in Rossman, Peck, Franklin, Hartlaub, and Scheaffer’s November, 2009 letter, (hereafter RPFHS) is passion and persuasion: passion for AP statistics and persuasion for its effectiveness. I greatly applaud their effort as passionate leaders and devoted promoters of statistical education, e.g., Professor Rossman is the current President of International Association for Statistical Education, Professor Scheaffer is a past President of ASA, and Professor Franklin’s textbook (with Professor Agresti) is actually the reference book for the Happy Course described in my op-ed (which is the piece that RPFHS commented on). The demand for statistics is such that we now need significantly more passionate and effective statistical educators, especially for introductory courses, for reasons discussed in Brown and Kass (2009) and Meng (2009).

The same passion for the future of statistics has led to recent efforts at Harvard Statistics; the Happy Course is just one of them (see Meng (2009) for others). Strong persuasion was also intended in my op-ed for The Harvard Undergraduate Research Journal (THURJ), persuading undergraduates to take at least one course in statistics, especially those who had been turned off by their AP statistics experiences. Coincidently, a colleague just forwarded an email from a Harvard undergraduate who read my op-ed and whose reaction is the type that prompted me to acknowledge their frustration (evidently this student made an effort to have himself “turned on” —Stat 104 is the course taught by the protagonist of the “Jesus” quotation in my op-ed):

I was therefore puzzled by the statement in RPFHS that my “criticism” of AP statistics is “mis-directed”. My op-ed was not assessing—much less criticizing—the overall quality of AP statistics, but rather addressing a situation on cases where it had a negative impact, as reported by students. In contrast, what RPFHS cited are cases where students have been turned on by their AP statistics experiences, also reported by students.

There were two sentences in my op-ed that mentioned AP statistics. One of them is (all emphases in the current article are added)

The other is a literal quotation from one of those students: “AP Statistics was the most boring course I took in high school!” I was therefore quoting from students who chose to stay away from statistics. Let’s denote that population as A. By contrast, RPFHS was quoting from students who are already in statistics major/minor/courses:

Putting aside the issue that different institutions are involved, the students quoted in RPFHS belong to the complementof A, A^C. We statisticians understand well that conditioning on A and conditioning on A^C are different matters, just as association (over time) and causation are not the same thing. Therefore, the intended or unintended uses of such mixed arguments in RPFHS puzzled me.

There is of course no puzzle whatsoever in the fact that an education program can have both significant positive and negative impact, depending on how it is actually implemented. When an AP statistics course or any other introductory course is done well, such as those described in RPFHS, it does a great service to our profession. When it is done poorly, as experienced by some Harvard undergraduates, it has a strong effect but in the opposite direction. Therefore, the evidence from these different observations actually reinforce the same point: the first courses in statistics, regardless whether at the high school level or the college level, are absolutely critical and we need substantially more passionate and skilled educators in order to maximize their positive impact. In other words, the worry discussed below is not about the AP program per se, which of course has increased awareness of statistics at the high school level by putting statistics on an equal footing with many other subjects. The worry is simply due to the severe shortage of qualified statistical teachers who can teach introductory courses in such a way to arouse students’ interests in statistics, or at least not to turn them away from statistics.