Planning an Experiment in the Company of Measurement Error

Abstract

"Textbook" calculations of statistical power and/or sample size follow from formulas that as sume that the variables under consideration are measured without error. However, in the "real world" of behavioral research, errors of measure ment cannot be neglected. A recent sample-size determination approach is easily adapted to incor porate unreliability information for both com pletely randomized and randomized block anal ysis-of-variance designs. A worked example pre sents an instance wherein a blocking strategy is clearly advantageous assuming infallible measur ing instruments, but not when the same instru ments are granted fallibility.

Locations

• University of Minnesota Digital Conservancy (University of Minnesota) - View - PDF
• Applied Psychological Measurement - View