A REJOINDER TO ALBANESE, "THE CORRECTION FOR GUESSING: A FURTHER ANALYSIS OF ANGOFF AND SCHRADER"

Albanese is critical of the Angoff-Schrader (1984) study for several reasons, mainly, the fact that it draws some of its data from volunteer student-subjects. If this criticism is valid, and if we therefore decide to exclude all studies based on volunteer subjects, we necessarily discontinue virtually all experimentation. Albanese recognizes this, but offers no workable substitute for experimental studies. We find, on the other hand, no evidence that the use of volunteer subjects impaired the soundness of our conclusions. Albanese offers an index of his own construction for use in evaluating the Angoff-Schrader data, and in applying it, comes to a different interpretation from that given by the authors. However, we find serious statistical flaws in his index when applied to our data. For example, we observe that when it is applied to small samples it yields uninterpretable results. After careful consideration of Albanese's reanalyses and interpretations, we stand firm in our original conclusion that formula scores are essentially invariant under different testing directions.