Minimizing Sample Size When Using Exploratory Factor Analysis for Measurement

Both hypothetical and real research examples illustrate the usefulness of sub-sample analysis in determining that a sample size of at least 50 and not more than 100 subjects is adequate to represent and evaluate the psychometric properties of measures of social constructs.

Abstract

Traditional protocol for the determination of an adequate sample size is power analysis. Such a protocol is not useful when the primary hypothesis focuses on psychometric measurement properties. Traditional psychometrics advises that there should be 10 respondents per item. Both hypothetical and real research examples illustrate the usefulness of sub-sample analysis in determining that a sample size of at least 50 and not more than 100 subjects is adequate to represent and evaluate the psychometric properties of measures of social constructs. The “10 respondents per item” advice builds a sample size disincentive into the research design; it also represents “sample size overkill.” Sample-size overkill occurs when the research design specifies a number of cases needed, which is in excess of the number actually needed for a desired inference.