Using Parcels to Convert Path Analysis Models Into Latent Variable Models

By D. Coffman, R. Maccallum. Multivariate Behavioral Research, 2005

691 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b03fa2c309f118e507b2ebeed1d9e9cdab103135

How researchers see this paper

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

In Computer Networks and Communications

1. Robert J. Vandenberg
2. Gordon W. Cheung
3. Rebecca S. Lau
4. J. Edwards
5. Lawrence J. Williams
6. Klaus Oberauer
7. Stephan Lewandowsky
8. Gilles E. Gignac

In Statistics and Probability

1. Gordon W. Cheung
2. Robert J. Vandenberg
3. Rebecca S. Lau
4. Stephan Lewandowsky
5. J. Edwards
6. T. Little
7. Zhonglin Wen
8. Lawrence J. Williams

Citations in the corpus

• Understanding the Interplay Among Regulatory Self-Efficacy, Moral Disengagement, and Academic Cheating Behaviour During Vocational Education: A Three-Wave Study (2018, methodology): “…by many items and the construct was confirmed to be one-dimensional, we implemented a partially disaggregated approach in which its latent factor was defined at each time point using parcels (i.e. the sum or the average of several items measuring the construct) (Coffman and MacCallum 2005).”
• Hope and emotional well-being: A six-year study to distinguish antecedents, correlates, and consequences (2015, background): “…of using item parcels since they are more normally distributed, reliable, less influenced by unique characteristics of individual items and require the estimation of fewer parameters (Bagozzi & Heatherton, 1994; Coffman & MacCallum, 2005; Kishton & Widaman, 1994; West, Finch, & Curran, 1995).”
• Driven to Work and Enjoyment of Work (2012, positive): “…for testing causal sequences such as those proposed in the present study; the biasing effects of measurement error are reduced, measurement and structural models are tested, and indices of overall fit are obtained (Coffman & MacCallum, 2005; Kenny, Kashy, & Bolger, 1998; Mathieu & Taylor, 2006).”
• Stress, resilience and leisure coping among university students: applying the broaden-and-build theory (2017, methodology): “Based on factor loadings, items were assigned to corresponding parcels in descending order (Coffman & MacCallum, 2005).”
• Tourism Entrepreneurship Performance (2015, methodology): “Because place identity and entrepreneurial self-efficacy are presented in the literature as higher-order, multidimensional constructs, we used the parceling method to transform them into latent factor constructs (Bagozzi and Edwards 1998; Coffman and MacCallum 2005).”
• Speed or quality? How the order of market entry influences the relationship between market orientation and new product performance (2011, neutral): “Finally, as shown by Coffman and MacCallum (2005), summing or averaging the scale items prior to estimating the structural parameters of the model can lead to biased parameter estimates.”
• Insecure attachment and depressive symptoms: The mediating role of rumination, empathy, and forgiveness (2009, background): “…using parcels has advantages, including higher reliability (Kishton & Widaman, 1994), a reduction in the number of measured variables in the model (Coffman & MacCallum, 2005) and a greater likelihood of meeting the assumptions of maximum likelihood, including normality (West, Finch, & Curran,…”
• Gameful Experience in Gamification: Construction and Validation of a Gameful Experience Scale [GAMEX] (2018, background): “Even though more items improve the representation of a construct, it also increases the risk that a good model that closely approximates the construct will not fit well, given the high number of parameter estimates (Coffman and MacCallum 2005).”
• An Examination of the Role of Attachment and Efficacy in Life Satisfaction (2010, background): “…it is not uncommon for researchers to use subscales as multiple indicators of a latent variable (e.g., Tokar et al., 2003) or to parcel items on a scale or subscale to create multiple indicators that measure a latent variable (Coffman & MacCallum, 2005; Mallinckrodt & Wei, 2005; Wei et al., 2006).”
• The role of basic psychological needs satisfaction in the relationship between transformational leadership and innovative work behavior (2021, methodology): “Thus, the unique variance of latent variables may be underestimated (Coffman & MacCallum, 2005; Williams & O'Boyle Jr., 2008).”
• A structural equation model analyzing the relationship of student achievement motivations and personality factors in a range of academic subject-matter areas (2007, neutral): “(1995), Dauphinee et al. (1997), and Hilton et al.”