The Impact of Misspecified Item Parceling on Representing Latent Variables in Covariance Structure Modeling: A Simulation Study

By Sooyeon Kim, K. Hagtvet. 2003

85 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Nature and Landscape Conservation, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/23ed3c79cc9b5c42da5cc6361954f8cdc887b8f9

How researchers see this paper

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

In Management Science and Operations Research

In Nature and Landscape Conservation

In Statistics and Probability

Citations in the corpus

How Well Do Item Parcels Represent Conceptually Defined Latent Constructs? A Two-Facet Approach (2004, methodology): “For this purpose a two-facet measurement model is suggested (Hagtvet, 1998, 1999; Kim & Hagtvet, 2003) to examine the unidimensionality of item parcels where items and parcels represent two different facets of empirical indicator information of the same latent construct (see Figure 1).”
Problems With Item Parceling for Confirmatory Factor Analytic Tests of Measurement Invariance (2006, methodology): “Several authors have noted that when parcels are formed from multidimensional items, the true nature of the measurement model can be masked by the parcels (Bandalos, 2002; Bandalos & Finney, 2001; Hall, Snell, & Foust, 1999; Kim & Hagtvet, 2003; Little et al., 2002).”
An Empirical Comparison of the Efficacy of Covariance-Based and Variance-Based SEM (2009, result): “In general, however, our approach is substantially more complex than those applied by other researchers in similar situations, specifically due to the use of Mattson's (1997) method of data generation, which gives us confidence in the external validity of our results.”
Is Parceling Really Necessary? A Comparison of Results From Item Parceling and Categorical Variable Methodology (2008, unknown): “However, Kim and Hagtvet (2003) found that unequal loading patterns resulted in much greater levels of parameter estimate bias than did equal loading patterns in their study of item parceling, so the results reported here most likely represent the best rather than the worst case scenario.”
Why the Items versus Parcels Controversy Needn’t Be One (2013, background): “Similarly, Hagtvet and Nasser (2004; Kim & Hagtvet, 2003) have suggested beginning with a “two-facet” model, where to-be-parceled items are modeled as indicators of latent subfactors of the construct of interest.”
The Effects of Parceling Unidimensional Scales on Structural Parameter Estimates in Structural Equation Modeling (2006, background): “…literature, with focus on both the item parceling techniques and the effects of parceling on model fit and convergence (see Bandalos, 2002; Bandalos & Finney, 2001; Hagtvet & Nasser, 2004; Hall, Snell, & Foust, 1999; Kim & Hagtvet, 2003; Little, Cunningham, Shahar, & Widaman, 2002; Schallow, 2000).”
Ethical Leadership and Team Ethical Voice and Citizenship Behavior in the Military: The Roles of Team Moral Efficacy and Ethical Climate (2020, background): “Some scholars argue that the estimation of a measurement model can be biased when a parceling approach is applied to multidimensional constructs (e.g., Bandalos, 2002; Hagtvet & Nasser, 2004; Hall et al., 1999; S. Kim & Hagtvet, 2003; Schallow, 2000).”
The Influence of Childhood (2012, methodology): “Parcels serving as indicators of their respective constructs were then entered into SEM tests (Kim & Hagtvet, 2003).”
The Use of Structural Equation Modeling in Counseling Psychology Research (2005, background): “In fact, recent Monte Carlo simulations have found that item parcels often mask misspecified models by yielding acceptable factor loadings and fit indices (Bandalos, 2002; Kim & Hagtvet, 2003).”