Convergent validity requires same-trait correlations across methods to exceed other correlations

Evidence

According to Campbell and Fiske (1959), the validation process requires significant and positive correlations between different methods of the same trait (i.e., validity values, convergent validity), validity values should be larger in magnitude than values that neither have a trait nor method in common (discriminant validity), and should be larger in magnitude than different traits measures by the same method (discriminant validity), and the correlation patterns found using one method should be similar to the correlation patterns using another method (discriminant validity). — Sherman A. Lee, Chelsea A. Reid, Stephen D. Short, Jeffrey A. Gibbons, Ruth Yeh, and Matthew L. Campbell, Fear of Muslims, 89

Categorization

• DEFINE: States the four Campbell and Fiske criteria for a valid multitrait-multimethod matrix in one compressed list.
• XREF: Connects to psychometrics and measurement-validity literature, e.g. Cronbach and Meehl’s construct validity framework.