Evidence on the Dimensionality and Reliability of Professional References’ Ratings of Teacher Applicants |
| |
| Institution: | 1. American Institutes for Research/CALDER, 3876 Bridge Way N, Suite 201, Seattle, WA 98103, United States;2. Center for Education Data and Research, University of Washington, 3876 Bridge Way N, Suite 201, Seattle, WA 98103, United States;3. Faculty of Education, Charles University, Magdalény Rettigové 4, Prague 116 39, Czech Republic;4. Department of Statistical Modelling, Institute of Computer Science of the Czech Academy of Sciences, Pod Vodárenskou vě?í 2, Prague 182 07, Czech Republic;1. University of California, Irvine;2. Purdue University;3. Boston University;4. University of Denver;1. Department of Economics, University of Illinois at Chicago;2. Urban Institute Health Policy Center;1. University of Mannheim, Department of Economics, Office 326, L7, 3-5, Mannheim, 68161, Germany;2. University of Essex, Department of Economics, Wivenhoe Park, Colchester, CO4 3SQ, United Kingdom;1. U. of Missouri, Dept. of Economics, 909 University Avenue, 327 Professional Building, Columbia, MO 65211-6040, USA;2. Mississippi State U., Dept. of Finance and Economics, 114 McCool Hall, 40 Old Main, P.O. Box 5288, Mississippi State, MS 39762, USA;3. Georgia State U., Dept. of Economics, P.O. Box 3992, Atlanta, GA 30302-3992, USA |
| |
| Abstract: | There is growing interest in using measures of teacher applicant quality to improve hiring decisions, but the statistical properties of such measures are not well understood. We use unique data on structured ratings solicited from the references of teacher applicants to explore the dimensionality of measures of teacher applicant quality and the inter-rater reliability of the reference ratings. Despite questions about applicants designed to capture multiple dimensions of quality, factor analysis suggests that the reference ratings only capture one underlying dimension. Point estimates of inter-rater reliability range between 0.23 and 0.31 and are significantly lower for novice applicants. It is difficult to judge whether these levels of reliability are high or low in the current context given so little evidence on applicant assessment tools. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
