Test-Retest Coefficients and the National Faculty Surveys

This paper analyzes the statistical reliability of items in the "Faculty at Work" survey, identifies several constructs that are wrongly assumed to be stable, and discusses the consequences for other faculty surveys, future research, and policy. While most survey items achieve statisticall...

Full description

Saved in:
Bibliographic Details
Published in:Review of higher education 1992-10, Vol.16 (1), p.19-39
Main Authors: Blackburn, Robert T, Mackie, Christopher J
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper analyzes the statistical reliability of items in the "Faculty at Work" survey, identifies several constructs that are wrongly assumed to be stable, and discusses the consequences for other faculty surveys, future research, and policy. While most survey items achieve statistically significant retest correlation coefficients, the range of correlation is large. Patterns of higher and lower reliability exist, but anomalous results complicate the picture.
ISSN:0162-5748
1090-7009
1090-7009
DOI:10.1353/rhe.1992.0001