Openly accessible

Investigating directionality for a media consumption construct : establishing the utility of confirmatory vanishing tetrad analysis

Wilson, Bradley, Vocino, Andrea, Adam, Stewart and Stella, Jason 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, no. 1, pp. 23-38.

Attached Files
Name Description MIMEType Size Downloads
vocino-investigatingdirectionality-post-2011.pdf Author post print application/pdf 287.75KB 350

Title Investigating directionality for a media consumption construct : establishing the utility of confirmatory vanishing tetrad analysis
Author(s) Wilson, Bradley
Vocino, Andrea
Adam, Stewart
Stella, Jason
Journal name Asia Pacific journal of marketing and logistics
Volume number 23
Issue number 1
Start page 23
End page 38
Total pages 16
Publisher Emerald Group Publishing
Place of publication Bingley, England
Publication date 2011
ISSN 1355-5855
1758-4248
Keyword(s) Mass media
Multivariate analysis
Modelling
Summary 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 post hoc test called confirmatory vanishing tetrad analysis (CTA hereafter) to a single construct called mass media consumption information exposure, which antecedent studies conceptually posited to be a formative (causative) representation.
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 Mplus 5 through the estimation of a single-factor congeneric model. The CTA test calculates a test statistic similar to an asymptotic x2 distribution with degrees of freedom equal to the number of nonredundant tetrads tested.
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 pre and post hoc tests as a key component of standard research practice.
Language eng
Field of Research 150504 Marketing Measurement
Socio Economic Objective 910403 Marketing
HERDC Research category C1 Refereed article in a scholarly journal
HERDC collection year 2011
Copyright notice ©2011, Emerald Group Publishing
Persistent URL http://hdl.handle.net/10536/DRO/DU:30034596

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Access Statistics: 174 Abstract Views, 354 File Downloads  -  Detailed Statistics
Created: Tue, 17 May 2011, 11:49:57 EST by Katrina Fleming

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.