Premium
On building better construct measures: Implications of a general hierarchical model
Author(s) -
Mowen John C.,
Voss Kevin E.
Publication year - 2008
Publication title -
psychology and marketing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.035
H-Index - 116
eISSN - 1520-6793
pISSN - 0742-6046
DOI - 10.1002/mar.20221
Subject(s) - nomological network , construct (python library) , curse of dimensionality , scale (ratio) , hierarchical database model , construct validity , psychology , reliability (semiconductor) , test (biology) , process (computing) , computer science , structural equation modeling , artificial intelligence , data mining , psychometrics , machine learning , paleontology , power (physics) , physics , operating system , quantum mechanics , biology , programming language , clinical psychology
Four problems occur in the scale development process: (a) defining the construct, (b) drawing items from multiple domains, (c) identifying dimensions, and (d) showing nomological validity. In order to minimize these problems, the authors propose a general hierarchical model (GHM) that provides an organizational structure for placing many of the individual difference constructs used in marketing and consumer behavior. Three principles, which were derived from the GHM, add to the current scale development paradigm: (a) Define and test the construct within a hierarchical network that includes antecedents and consequences, (b) define and test the construct's dimensionality, and (c) match the construct's items to its level in the hierarchical system. By using these steps in scale development, researchers can build more precise measures possessing higher levels of validity and reliability. © 2008 Wiley Periodicals, Inc.