The problem of measurement model misspecification in behavioral and organizational research and some recommended solutions.

By Scott B. MacKenzie, Philip M. Podsakoff, Cheryl Burke Jarvis. Journal of Applied Psychology, 2005

1,782 citations recorded by the source corpus.

Subfields: Applied Psychology, Management Science and Operations Research, Organizational Behavior and Human Resource Management

View Paper: https://www.semanticscholar.org/paper/5b26603c2407f6447988f1f4e32e6f65ab24f231

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Psychology

1. James Avey
2. Osman M. Karatepe
3. Russell E. Johnson
4. Adamantios Diamantopoulos
5. Arun Rai
6. Richard P. Bagozzi
7. D. L. Ferris
8. J. Cadogan

In Management Science and Operations Research

1. J. Edwards
2. Adamantios Diamantopoulos
3. Richard P. Bagozzi
4. James Avey
5. Arun Rai
6. Jason Bennett Thatcher
7. Nicholas H. Roberts
8. J. Cadogan

In Organizational Behavior and Human Resource Management

1. D. van Knippenberg
2. Arnold B. Bakker
3. Russell E. Johnson
4. Deanne N. den Hartog
5. Shahriar Akter
6. James Avey
7. Sharon K. Parker
8. Thomas W. H. Ng

Citations in the corpus

• Reconceptualizing entrepreneurial orientation (2015, methodology): “Hence, measurement model misspecification resulted in a Type II error in the case of the unidimensional model, as would be expected (MacKenzie et al., 2005).”
• Construct Measurement and Validation Procedures in MIS and Behavioral Research: Integrating New and Existing Techniques (2011, background): “Second, recent Monte Carlo simulations reported by Jarvis et al. (2003), MacKenzie et al. (2005), and Petter et al. (2007) suggest that structural parameter estimates can be biased when indicators that should be modeled as having formative relationships with a construct are modeled as having…”
• 12 Structural Equation Modeling in Management Research: A Guide for Improved Analysis (2009, methodology): “This model is based on an example of formative measurement offered by MacKenzie et al. (2005), in which the latent variable η is contextual job performance (CJP) and x 1 , x 2 , and x 3 are measures of task performance, job dedication, and interpersonal facilitation.”
• Specifying Formative Constructs in Information Systems Research (2007, background): “…error (a false positive by declaring a path significant when it is really nonsignificant) and Type II error (a false negative by declaring a path nonsignificant when it is really significant) in conclusions related to the structural model (Jarvis et al. 2003; MacKenzie 2001; MacKenzie et al. 2005).”
• The Development and Validation of a New Machiavellianism Scale (2009, neutral): “Moreover, consistent with the criteria established by MacKenzie, Podsakoff, and Jarvis (2005), we have treated this dimensional structure as a latent variable model with effects indicators (i.e., with arrows flowing from the construct to the indicators) rather than an aggregate or manifest variable…”
• INTERNAL AUDIT QUALITY AND EARNINGS MANAGEMENT (2009, background): “For a discussion of the difference between formative and reflective indicators, see Jarvis et al. (2003) and Mackenzie et al. (2005).”