The proxy of Dorian Gray: scientific realism, construct validation and the way forward

Abstract

Purpose This paper aims to clarify some of the representations regarding philosophy of science and statistical methods, which are contained in Cadogan and Lee (this issue). Design/methodology/approach This paper uses logical argument and a review of literature. Findings Rigdon’s (2012) approach to construct validation is entirely consistent with scientific realism, while the “realist variable framework” revives the empiricist reification of common factors found in Bagozzi’s (1984) Holistic Construal and throughout the early literature of structural equation modeling. Factor indeterminacy is a phenomenon that makes it impossible to equate common factors with conceptual variables. The future of marketing measurement is not in the historical error-centric framework but in a measurement framework centered around uncertainty. Research limitations/implications Researchers should avoid reification of common factors and recognize the validity gap between conceptual variables and empirical proxies, consistent with Rigdon (2012) and should move toward an uncertainty-centric approach to measurement. Practical implications Decision-makers need to acknowledge the difference between data and the underlying reality. Success or failure will be shaped by the reality, not by the data. Originality/value To the best of the author’s knowledge, this is the first paper seeking to clarify representations in Cadogan and Lee (this issue). This paper aims to save journal readers from being misled.