I AM PUZZLED BY THE ARTICLE titled, “How Random Is That?” [September 2005 Observer]. The article appears to confuse (or at least not helpfully distinguish) random selection with several other “randoms” that populate our research vernacular. A similar confusion among several doctoral students taking comprehensive exams led me to fail several of them recently, and so I was dispirited to see the same confusion in our fine magazine. The discussion of permutation tests was particularly unclear on the different way that researchers use the term random.
“The key to a randomization test is that it does not require a sample to come from a large population — in fact, randomization thrives on taking one random sample, such as a set of convenient university students, and randomly dividing it into two experimental groups, which can then be analyzed and concluded upon as though they had both been drawn randomly from a vast pool of participants.”
The permutation method described concerns what Cook and Campbell (1979) called statistical conclusion validity, in essence, how well we believe the stats in a study. This issue is distinct from internal validity, a concern about inferring causality. The random assignment to experimental condition has little in common with statistical analysis of groups created after the fact. A third concept is also thrown into the mix: external validity. Random selection from a sample frame (that refers to a distinct population) allows one to infer generalizability. No amount of statistical legerdemain will increase our ability to infer causality or generalize to a population if research methods are inadequate.
— Noel Brewer
University of North Carolina at Chapel Hill
- Cook, T. D. & Campbell, D. T. (1979). Quasi-Experimentation: Design & Analysis Issues for Field Settings. Boston: Houghton Mifflin.
SUPC Support Missed
While I was heartened to read about Stanford’s fifth undergraduate psychology conference, [July 2005 Observer], I was disappointed to learn that the SUPC has veered from at least one of its original purposes-to provide assistance to an underserved Bay Area high school psychology program.
The proceeds from this year’s conference were donated to the California Psychology Internship Council.
During the conference’s first two year’s, my public high school psychology classes received monies which enabled me to take two students, whose work was exhibited at SUPC, to the Western Psychological Association Convention, where those students were recognized with plaques by Phil Zimbardo. In addition, another of my students received the Albert Bandura poster award at SUPC in 2002 as the outstanding poster in the high school division. That year, the conference’s organizer and Stanford’s Psi Chi president, Sarah Mascarenas, conducted trainings in the Bay Area for high school students before the conference to familiarize students with ways in which to prepare psychological research.
Although I no longer teach at a public high school, I know of many Bay Area high school classes that would surely benefit from participating at the SUPC and receiving conference proceeds. It’s a shame that Stanford has chosen to apparently close that avenue.
Leave a comment below and continue the conversation.