ABSTRACT
Not long ago, a researcher, program evaluator or other professional involved in measuring, assessing, and evaluating would reference their work by pointing to the “models” of House (1980), Madaus, Scriven, and Stufflebeam (1983), and almost certainly to Bloom, Hastings, and Madaus (1974). (Many other figures prominent in measurement, evaluation, and assessment could be named, too.) The basic thrust of influence for these leaders was to encourage systematic approaches to applied research in higher education, which in such contexts is nearly always quantitative. Typically, there was heavy reliance upon descriptive statistics as well as inferential, classical statistics with null hypothesis significance testing (NHST). Sir Ronald Fisher’s ANOVA (analysis of variance) tests, and Student’s t-tests along with confidence intervals, were the near-universal reporting genre.
