Validity and Reliability Consequences of Confidence Weighting

each item (or, in some cases, the incorrectness of the distractors). Early and apparently independent attempts to apply such procedures were those of Hevner (1932), Soderquist (1936), and Dressel and Schmid (1953). No sustained interest in the topic was evidenced until Ebel (1961, 1965a) presented promising preliminary findings showing meaningful increases in reliability resulting from confidence weighting. Great enthusiasm was expressed for the technique by Shuford, Albert, and Massengill (1966) who presented a strong theoretical case for its efficacy when certain assumptions were met. Shuford and Massengill (1967) later commercially marketed a Valid Confidence Testing Demonstration Kit designed for classroom and other use. As Ebel (1968) pointed out, in an appraisal of