No abstract

No abstract

The purpose of this paper was to provide an empirical test of the hypothesis that elimination scores are more reliable and valid than classical corrected for‐guessing scores or weighted‐choice scores. The evidence presented supports the hypothesized superiority of elimination scoring.

Three intact groups of graduate education students enrolled in a required two course sequence in research design and data anlaysis were assigned to three levels of experience with a computer simulated program evaluation project: control (no experience), restricted (2 semester hours), and intensive (6 semester hours). At the end of term I performance was compared on four variables: the course final; attitudes toward research; self assessment of research competency; and an objective rating of the students' research products (proposal and final report). The general hypothesis was that scores on each variable would increase monotonically with the amount of experience. Analysis of co-variance confirmed this hypothesis for achievement and product scores, but no significant differences were found for attitudes. Additional experience and tests during the second term confirmed both these findings.

No abstract