Calibration experiments: An alternative to multi-method approaches for measurement validation in consumer research
提出实验校准作为多特质多方法矩阵的替代方案，用于消费者研究中可外部操纵的潜变量测量验证，能区分相近方法、无需无关潜变量并优化评估流程。
Measurement validation in consumer research is ideally performed within the context of a multi-trait multi-method matrix (MTMM). While statistically well developed, this approach has several shortcomings that limit its domain of application: (1) the requirement for sufficiently unrelated latent variables that can be measured with the same methods, (2) the requirement for conceptually different methods to disambiguate trait from methods, and most seriously (3) the difficulty in identifying a more valid over a less valid method. We compare the MTMM approach to experiment-based calibration, an alternative framework for validating those latent variables that can be externally manipulated. We show how calibration lets researchers make distinctions between even closely related measurement methods, dispenses with the need for unrelated latent variables, and enables optimization of the measurement evaluation procedure itself. Calibration can be an important part of an integrative validity argument in consumer research and, more broadly, across the social sciences.