I think you also need to reconsider how you go about assessing SEM model fit after this new 'in press' publication ... CFA-SEM modeling has now become far more tricky than just reporting a few fit indices and a couple of 'famous-name' references to justify ad-hoc thresholds.
McNeish, D., An, J., & Hancock, G.R. (2017). The thorny relation between measurement quality and fit index cutoffs in latent variable models. Journal of Personality Assessment (http://www.tandfonline.com/doi/abs/10.1080/00223891.2017.1281286), In Press, , 1-11.
Abstract
Latent variable modeling is a popular and flexible statistical framework. Concomitant with fitting latent variable models is assessment of how well the theoretical model fits the observed data. Although firm cutoffs for these fit indexes are often cited, recent statistical proofs and simulations have shown that these fit indexes are highly susceptible to measurement quality. For instance, a root mean square error of approximation (RMSEA) value of 0.06 (conventionally thought to indicate good fit) can actually indicate poor fit with poor measurement quality (e.g., standardized factors loadings of around 0.40). Conversely, an RMSEA value of 0.20 (conventionally thought to indicate very poor fit) can indicate acceptable fit with very high measurement quality (standardized factor loadings around 0.90). Despite the wide-ranging effect on applications of latent variable models, the high level of technical detail involved with this phenomenon has curtailed the exposure of these important findings to empirical researchers who are employing these methods. This article briefly reviews these methodological studies in minimal technical detail and provides a demonstration to easily quantify the large influence measurement quality has on fit index values and how greatly the cutoffs would change if they were derived under an alternative level of measurement quality. Recommendations for best practice are also discussed.
Regards .. Paul Barrett
From: Organizational Behavior Division Listserv [mailto:OB@AOMLISTS.AOM.ORG] On Behalf Of Michael Frone
Sent: Thursday, June 15, 2017 11:19 AM
To: OB@AOMLISTS.AOM.ORG
Subject: Re: [OB-LIST] Scale Development
Scott,
In terms of model papers, the literature is full of measurement development and/or validation papers that can be found searching a bit on Google Scholar. There is no complete one-size-fit-all approach. There will be similarities across papers, such as using CFA to assess the proposed factor structure after the measure has been developed, pilot tested, and revised. And there will be differences. When estimating a CFA, most researchers use ML estimation, treating ordinal indicators as continuous. Yet other researchers may use WLS estimation and treat the ordinal indicators as ordinal. When exploring associations between the central construct and other variables comprising its nomological network, most researchers report zero-order correlations. However, multiple regression analysis can be a better approach. It would be useful to take a broad look, see the various options, and determine what might be the best approach for your particular project. The following paper might be useful to you as one example:
https://www.researchgate.net/publication/269410946_The_Meaning_and_Measurement_of_Work_Fatigue_Development_and_Evaluation_of_the_Three-Dimensional_Work_Fatigue_Inventory_3D-WFI
Good Luck,
Mike Frone
**************************************************************************
Michael R. Frone, Ph.D.
Senior Research Scientist
Research Institute on Addictions
State University of New York at Buffalo
1021 Main Street
Buffalo, New York 14203
Office: 716-887-2519
Fax: 716-887-2477
E-mail: frone@ria.buffalo.edu
Alcohol and Illicit Drug Use in the Workforce and Workplace
RIA Website Google Scholar ResearchGate LinkedIn
***************************************************************************
From: Kurt Kraiger <Kurt.Kraiger@COLOSTATE.EDU>
To: OB@AOMLISTS.AOM.ORG
Date: 06/14/2017 06:40 PM
Subject: Re: [OB-LIST] Scale Development
Sent by: Organizational Behavior Division Listserv <OB@AOMLISTS.AOM.ORG>
Scott,
The outlet really depends on the content of the scale.
A really good model paper is: http://psycnet.apa.org/index.cfm?fa=buy.optionToBuy&id=2016-48470-001
Note that this is the Journal of Applied Psychology, meaning that if it's a really good scale development project, you can publish it even in a top-tier journal!
Good luck with the paper,
Kurt
--
*******************************************************
Kurt Kraiger, Ph.D.
Professor of Psychology
Department of Psychology
Campus Delivery 1876
Colorado State University
Fort Collins, CO 80523-1876
(970) 491-6821
.
Skype: kurt.kraiger
Facetime: Kurt.Kraiger@gmail.com
http://www.linkedin.com/in/kraiger
Kurt.Kraiger@colostate.edu
*****************************************************
On Tue, Jun 13, 2017 at 4:00 PM, Jeffrey, Scott <0000005c764d771e-dmarc-request@aomlists.aom.org> wrote:
Hi All,
A while back I asked for some good articles on scale development. The ones you recommended were all very good.
Anyway, I have now developed my two scales. The fit is good (not excellent) and the loadings while they could be better are all above 0.6.
So – now, I need two more things.
1. A good "model" paper that I can use to base my paper off of.
2. A good outlet.
Thanks in advance for any advice.
Scott Jeffrey
Associate Professor
Leon Hess Business School
Monmouth University