Series editor(s): Professor Shaoming Zou
Subject Area: Marketing
|Title:||Using Formative Measures in International Marketing Models: A Cautionary Tale Using Consumer Animosity as an Example|
|Author(s):||Adamantios Diamantopoulos, Petra Riefler|
|Volume:||22 Editor(s): Marko Sarstedt, Manfred Schwaiger, Charles R. Taylor ISBN: 978-1-78052-094-0 eISBN: 978-1-78052-095-7|
|Citation:||Adamantios Diamantopoulos, Petra Riefler (2011), Using Formative Measures in International Marketing Models: A Cautionary Tale Using Consumer Animosity as an Example, in Marko Sarstedt, Manfred Schwaiger, Charles R. Taylor (ed.) Measurement and Research Methods in International Marketing (Advances in International Marketing, Volume 22), Emerald Group Publishing Limited, pp.11-30|
|DOI:||10.1108/S1474-7979(2011)0000022004 (Permanent URL)|
|Publisher:||Emerald Group Publishing Limited|
|Article type:||Chapter Item|
Purpose – Despite the increasing use of formative measurement models in literature, little is known about potential consequences for substantive theory testing. Against this background, the aims of this chapter are (1) to highlight some problems that may arise when formative instead of reflective measures are used to test even simple theoretical models with covarianced-based methodologies, (2) to illustrate some approaches that might help overcome these problems, (3) to pinpoint potential interpretation difficulties of the results involving re-specified measurement models, and (4) to stimulate discussion on the implications for theory development when models are tested with formative measures.
Methodology/approach – Potential consequences of formative measurement models for theory testing are highlighted using an empirical study on consumer animosity as an illustrative example and applying covarianced-based structural equations modeling procedures for estimation purposes.
Findings – The empirical study shows (a) that some scaling options for the (composite) latent variable result in non-convergence problems, (b) that, assuming convergence, parameter estimates, standard errors, and significance levels vary depending on the scaling method used, and (c) that goodness-of-fit statistics cannot be used as diagnostic measures for the appropriateness of divergent results.
Originality/value of paper – The contribution of this chapter is two-fold: First, it shows that to enable estimation, it is often necessary to modify (i.e., expand) the original theoretical model in a conceptually reasonable manner and to do so before data collection. Second, it demonstrates that alternative scaling options for composite latent variables may result in inconsistent substantive conclusions. Consequently, the impact of formative measurement on theory testing is a critical topic and needs to receive further attention in future literature.
Downloadable; Printable; Owned
HTML, PDF (387kb)
Due to our platform migration, pay-per-view is temporarily unavailable.
To purchase this item please login or register.
Complete and print this form to request this document from your librarian