Donald Campbell's Advice Applied to Lord's Paradox (Growth Study Paper #30) ANCOVA
Linn, Robert L.;
Werts, Charles E.
- Publication Year:
- Report Number:
ETS Research Bulletin
- Document Type:
- Page Count:
- Subject/Key Words:
Analysis of Covariance (ANCOVA),
A Study of Academic Prediction and Growth
As Lord has demonstrated, the use of analysis of covariance on nonexperimental data cannot be counted on to make proper allowances for uncontrolled pre-existing differences between groups. In this paper it is suggested that the interpretational problem that Lord raised is not limited to nonexperimental research but is generic to the research process.