The use of items and item parcels in nonlinear structural equation models

Nonlinear structural equation models within the frequentist framework were developed to work with continuous items. Applied researchers who usually work with Likert-type items choose between two strategies to estimate such models: treat items as continuous variables or create item parcels. Two Monte Carlo studies were conducted to evaluate the effects of each strategy on estimates and Type I errors for models with interaction and quadratic effects estimated using LMS. The first study evaluated the effect of asymmetry type and item quantity. The second assessed the use of item parcels and parcel configuration under equivalent conditions. Results reveal that treating items as continuous variables is not problematic when item categories are symmetrical or have opposite-direction asymmetries; however, meaningful parameter bias and increased Type I errors are produced in the case of same-direction asymmetry. Use of parcels does not overcome these problems. The results are discussed to provide recommendations for applied researchers.

• Publication year

  2020

• Venue

  Unknown venue

• Publication date

  2020-04-06

• Fields of study

  Mathematics, Education, Psychology

• Identifiers
  DOI 10.5964/meth.2305
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Developing Multidimensional Likert Scales Using Item Factor Analysis

  2016influential reference
• Characteristics of academically-influential children: achievement motivation and social status

  2016cited by this paper
• Reexamining Nonlinear Structural Equation Modeling Procedures: The Effect of Parallel and Congeneric Measures

  2015influential reference
• Cognitive Closure and Risk Sensitivity in the Fear of Crime

  2015cited by this paper
• A Simulation Study Comparing Recent Approaches for the Estimation of Nonlinear Effects in SEM Under the Condition of Nonnormality

  2014influential reference
• The roles of identity formation and moral identity in college student mental health, health-risk behaviors, and psychological well-being.

  2013cited by this paper
• How transformational leadership and employee motivation combine to predict employee proenvironmental behaviors in China

  2013cited by this paper
• Why the items versus parcels controversy needn't be one.

  2013cited by this paper
• A Comparison of Strategies for Forming Product Indicators for Unequal Numbers of Items in Structural Equation Models of Latent Interactions

  2013influential reference
• Estimating Latent Variable Interactions With Nonnormal Observed Data: A Comparison of Four Approaches

  2012influential reference
• When can categorical variables be treated as continuous? A comparison of robust continuous and categorical SEM estimation methods under suboptimal conditions.

  2012influential reference
• False-Positive Psychology

  2011cited by this paper
• Advanced Nonlinear Latent Variable Modeling: Distribution Analytic LMS and QML Estimators of Interaction and Quadratic Effects

  2011influential reference
• Estimating Latent Variable Interactions with the Unconstrained Approach: A Comparison of Methods to Form Product Indicators for Large, Unequal Numbers of Items

  2011cited by this paper
• An Alternative Approach for Nonlinear Latent Variable Models

  2010cited by this paper
• A Bayesian Approach for Nonlinear Structural Equation Models With Dichotomous Variables Using Logit and Probit Links

  2010cited by this paper
• Likert scales, levels of measurement and the “laws” of statistics

  2010cited by this paper
• Estimation of nonlinear latent structural equation models using the extended unconstrained approach

  2009cited by this paper
• The psychometricians' fallacy: too clever by half?

  2009cited by this paper
• Estimation of IRT graded response models: limited versus full information methods.

  2009influential reference
• Research Methods: A Modular Approach

  2007cited by this paper
• Quasi-Maximum Likelihood Estimation of Structural Equation Models With Multiple Interaction and Quadratic Effects

  2007cited by this paper
• Bayesian Methods for Analyzing Structural Equation Models With Covariates, Interaction, and Quadratic Latent Variables

  2007cited by this paper
• Why Most Published Research Findings Are False

  2005cited by this paper
• Likert scales: how to (ab)use them

  2004cited by this paper
• Structural equation models of latent interactions: evaluation of alternative estimation strategies and indicator construction.

  2004influential reference
• The use of item parcels in structural equation modelling: non-normal data and small sample sizes.

  2004influential reference
• Parameter Recovery and Model Fit Using Multidimensional Composites: A Comparison of Four Empirical Parceling Algorithms

  2004cited by this paper
• A method of moments technique for fitting interaction effects in structural equation models.

  2003cited by this paper
• The Effects of Item Parceling on Goodness-of-Fit and Parameter Estimate Bias in Structural Equation Modeling

  2002influential reference
• The Impact of Categorization With Confirmatory Factor Analysis

  2002influential reference
• To Parcel or Not to Parcel: Exploring the Question, Weighing the Merits

  2002influential reference
• Maximum likelihood estimation of latent interaction effects with the LMS method

  2000influential reference
• Testing for robustness in Monte Carlo studies.

  2000influential reference
• Statistical analysis of nonlinear structural equation models with continuous and polytomous data.

  2000cited by this paper
• Item Parceling Strategies in SEM: Investigating the Subtle Effects of Unmodeled Secondary Constructs

  1999cited by this paper
• Robustness Studies in Covariance Structure Modeling

  1998influential reference
• Is More Ever Too Much? The Number of Indicators per Factor in Confirmatory Factor Analysis.

  1998influential reference
• Multiple Regression: Testing and Interpreting Interactions.

  1994cited by this paper
• Factoring items and factoring scales are different: Spurious evidence for multidimensionality due to item categorization.

  1989influential reference
• A comparison of some methodologies for the factor analysis of non‐normal Likert variables

  1985influential reference
• Estimating the nonlinear and interactive effects of latent variables.

  1984cited by this paper
• Pearson's R and Coarsely Categorized Measures

  1981cited by this paper
• Statistical Methods for the Social Sciences

  1979influential reference

• Latent Interaction Modeling with Ordinal Items: Evaluating Alternative Analytic Methods and Parceling Strategies

  2025cites this paper