Item parceling issues in structural equation modeling

By D. Bandalos, S. Finney. 2001

977 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d08940b49f8faffec47d067d232adb2a733df6ba

How researchers see this paper

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

Citations in the corpus

Estimating Latent Variable Interactions with the Unconstrained Approach: A Comparison of Methods to Form Product Indicators for Large, Unequal Numbers of Items (2011, methodology): “These approaches include parceling together items with similar content, random assignment of items to parcels (Kishton & Widaman, 1994), forming parcels within a factor by grouping adjacent items on a scale (Bandalos & Finney, 2001), and item-to-construct balance parcels (Yang et al., 2010).”
Online communication, compulsive Internet use, and psychosocial well-being among adolescents: a longitudinal study. (2008, background): “Bandalos and Finney (2001) stated that in applications where the focus is on structural relationships and the latent variables are one dimensional, the use of item parcels is defensible.”
Navigating uneven terrain : the roles of political skill and LMX differentiation in prediction of work relationship quality and work outcomes. (2016, background): “Parceling has been an issue of debate among methodologists (e.g., Bandalos & Finney, 2001; Little, Cunningham, Shahar & Widaman, 2002).”
The Effects of Item Parceling on Goodness-of-Fit and Parameter Estimate Bias in Structural Equation Modeling (2002, background): “In the Bandalos and Finney (2001) review, only 32.3% of published studies made any reference to the unidimensionality of the items being parceled.”
Why the Items versus Parcels Controversy Needn’t Be One (2013, methodology): “We also review evidence that supports their use as well as evidence that suggests caution under particular circumstances (see also Bandalos & Finney, 2001).”
Active on the Job—Proactive in Change (2007, background): “…them are reduction of non-normality in the distribution of data, higher reliability of parcels than of individual items, improvement of the ratio of estimated parameters to sample size, greater likelihood of achieving a proper model solution, and better model fit (e.g., Bandalos & Finney, 2001).”