What Response Rates Are Needed to Make Reliable Inferences from Student Evaluations of Teaching?

Autor/inn/en	Zumrawi, Abdel Azim; Bates, Simon P.; Schroeder, Marianne
Titel	What Response Rates Are Needed to Make Reliable Inferences from Student Evaluations of Teaching?
Quelle	In: Educational Research and Evaluation, 20 (2014) 7-8, S.557-563 (7 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1380-3611
DOI	10.1080/13803611.2014.997915
Schlagwörter	Inferences; Test Reliability; Response Rates (Questionnaires); Student Evaluation of Teacher Performance; Evaluation Problems; Online Surveys; Likert Scales; Learning Modules; Simulation; Vignettes; Methods Research; Test Items; Robustness (Statistics); Goodness of Fit; Error of Measurement; College Students; Foreign Countries; Canada + Suchen Sie Ihr Suchwort? Inference; Inferenz; Testreliabilität; Antwortkontrolle; Likert-Skala; Learning module; Lernmodul; Simulation program; Simulationsprogramm; Methodenforschung; Test content; Testaufgabe; Widerstandsfähigkeit; Messfehler; Collegestudent; Ausland; Kanada
Abstract	This paper addresses the determination of statistically desirable response rates in students' surveys, with emphasis on assessing the effect of underlying variability in the student evaluation of teaching (SET). We discuss factors affecting the determination of adequate response rates and highlight challenges caused by non-response and lack of randomization. Estimates of underlying variability were obtained for a period of 4 years, from online evaluations at the University of British Columbia (UBC). Simulations were used to examine the effect of underlying variability on desirable response rates. The UBC response rates were compared to those reported in the literature. Results indicate that small differences in underlying variability may not impact desired rates. We present acceptable response rates for a range of variability scenarios, class sizes, confidence level, and margin of error. The stability of estimates observed at UBC, over a 4-year period, indicates that valid model-based inferences of SET could be made. (As Provided).
Anmerkungen	Routledge. Available from: Taylor & Francis, Ltd. 325 Chestnut Street Suite 800, Philadelphia, PA 19106. Tel: 800-354-1420; Fax: 215-625-2940; Web site: http://www.tandf.co.uk/journals
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01