Online from: 1989
Subject Area: Marketing
Options: To add Favourites and Table of Contents Alerts please take a Emerald profile
|Title:||Investigating directionality for a media consumption construct: Establishing the utility of confirmatory vanishing tetrad analysis|
|Author(s):||Bradley Wilson, (Design and Social Context College, School of Media and Communication, RMIT University, Melbourne, Australia), Andrea Vocino, (School of Management and Marketing, Deakin University, Burwood, Australia), Stewart Adam, (School of Management and Marketing, Deakin University, Burwood, Australia), Jason Stella, (Sensis, Melbourne, Australia)|
|Citation:||Bradley Wilson, Andrea Vocino, Stewart Adam, Jason Stella, (2011) "Investigating directionality for a media consumption construct: Establishing the utility of confirmatory vanishing tetrad analysis", Asia Pacific Journal of Marketing and Logistics, Vol. 23 Iss: 1, pp.23 - 38|
|Keywords:||Mass media, Modelling, Multivariate analysis|
|Article type:||Research paper|
|DOI:||10.1108/13555851111099970 (Permanent URL)|
|Publisher:||Emerald Group Publishing Limited|
Purpose – When assessing the psychometric properties of measures and estimate relations among latent variables, many studies in the social sciences (including management and marketing) often fail to comprehensively appraise the directionality of indicants. Such failures can lead to model misspecification and inaccurate parameter estimates. The purpose of this paper is to apply a
Design/methodology/approach – This paper analyses a consumer sample of 585 US respondents and applies the CTA test to a single construct by its inclusion in various matrices within a statistical analysis system-macro that takes into account nonnormal data characteristics. The matrices are derived from M
Findings – The preliminary data analyses reveal that the data characteristics are nonnormal which is not uncommon in social research. The CTA results reveal that the reflective (emergent) item orientation cannot be fully ruled out as being the correct model representation. This is in contrast to prior theoretical conceptual work which would strongly support this construct being a formative representation.
Originality/value – Insofar as the authors are aware, there is no paper with a particular focus on how the CTA might not provide sound results with a demonstrated example. The paper makes a valuable contribution by discussing modelling philosophy and a procedure for directionality testing. The authors advocate the implementation of
To purchase this item please login or register.
Complete and print this form to request this document from your librarian