ERIC Number: ED046892
Record Type: Non-Journal
Publication Date: 1970-Dec
Reference Count: N/A
A Case Study in Statistical Inference: Reconsideration of the Rosenthal-Jacobson Data on Teacher Expectancy.
Elashoff, Janet Dixon; Snow, Richard E.
This paper presents a critical evaluation of the research study Pygmalion in the Classroom by R. Rosenthal and L. Jacobson (New York: Holt, Rinehard and Winston, 1968) and reports an extensive reanalysis of the Rosenthal-Jacobson data. The Pygmalion study purported to show that children whose teachers expected them to "bloom" intellectually would do so. The critique suggests that the Rosenthal-Jacobson report as a whole is inadequate. Descriptions of design, basic data, and analysis are incomplete. Inconsistencies between text and tables, overly dramatic conclusions, oversimplified, inaccurate, or incorrect statistical discussions and analyses all contribute to a generally misleading impression of the study's results. In their reanalyses of the Rosenthal-Jacobson data, the present authors demonstrate a wide variation in apparent results which can be obtained from slightly different statistical approaches if serious imbalance in design and major measurement problems exist in a research study. They conclude that the reanalysis reveals no treatment effect of "expectancy advantage" in grades 3 through 6. The first and second graders may or may not exhibit some expectancy effect, but a conclusive analysis of first- and second-grade IQ scores is not possible. (Author/RT)
Publication Type: N/A
Education Level: N/A
Sponsor: Office of Education (DHEW), Washington, DC. Bureau of Research.
Authoring Institution: Stanford Univ., CA. Stanford Center for Research and Development in Teaching.