First- Versus Second-Order Latent Growth Curve Models: Some Insights From Latent State-Trait Theory

First-order latent growth curve models (FGMs) estimate change based on a single observed variable and are widely used in longitudinal research. Despite significant advantages, second-order latent growth curve models (SGMs), which use multiple indicators, are rarely used in practice, and not all aspects of these models are widely understood. In this article, our goal is to contribute to a better understanding of theoretical and practical differences between FGMs and SGMs. We define the latent variables in FGMs and SGMs explicitly on the basis of latent state–trait (LST) theory and discuss insights that arise from this approach. We show that FGMs imply a strict trait-like conception of the construct under study, whereas SGMs allow for both trait and state components. Based on a simulation study and empirical applications to the Center for Epidemiological Studies Depression Scale (Radloff, 1977) we illustrate that, as an important practical consequence, FGMs yield biased reliability estimates whenever constructs contain state components, whereas reliability estimates based on SGMs were found to be accurate. Implications of the state–trait distinction for the measurement of change via latent growth curve models are discussed.

[1]  R. Steyer,et al.  States and traits in psychological assessment. , 1992 .

[2]  Herbert W. Marsh,et al.  Longitudinal confirmatory factor analysis: Common, time‐specific, item‐specific, and residual‐error components of variance , 1994 .

[3]  E. Ferrer,et al.  Factorial Invariance and The Specification of Second-Order Latent Growth Models. , 2008, Methodology : European journal of research methods for the behavioral & social sciences.

[4]  A. Neubauer,et al.  Situational effects in trait assessment: The FPI, NEOFFI, and EPI questionnaires , 1995 .

[5]  M. Eid,et al.  Do you feel better or worse? The validity of perceived deviations of mood states from mood traits , 1999 .

[6]  T. Raykov.  A Method for Examining Stability in Reliability , 2000, Multivariate behavioral research.

[7]  J. Tisak,et al.  Longitudinal Models of Reliability and Validity: A Latent Curve Approach , 1996 .

[8]  William Meredith,et al.  Latent curve analysis , 1990 .

[9]  R. Steyer.  Analyzing Individual and Average Causal Effects via Structural Equation Models , 2005 .

[10]  J J McArdle,et al.  Latent growth curves within developmental structural equation models. , 1987, Child development.

[11]  C. Hertzog,et al.  Beyond autoregressive models: some implications of the trait-state distinction for the structural modeling of developmental change. , 1987, Child development.

[12]  Michael Eid,et al.  Latent state–trait theory and research in personality and individual differences , 1999 .

[13]  Donald B. Rubin,et al.  Reliability of measurement in psychology: From Spearman-Brown to maximal reliability. , 1996 .

[14]  J. Tisak,et al.  Permanency and ephemerality of psychological measures with application to organizational commitment. , 2000, Psychological methods.

[15]  Terry E. Duncan,et al.  A multivariate latent growth curve analysis of adolescent substance use , 1996 .

[16]  J. Mcardle.  Dynamic but Structural Equation Modeling of Repeated Measures Data , 1988 .

[17]  Michael Eid,et al.  Longitudinal Con rmatory Factor Analysis for Polytomous Item Responses: Model De nition and Model Selection on the Basis of Stochastic Measurement Theory , 1998 .

[18]  C. Geiser,et al.  Modelling and predicting complex patterns of change using growth component models: An application to depression trajectories in cancer patients , 2013 .

[19]  Michael Eid,et al.  Evaluating Interventions with Multimethod Data: A Structural Equation Modeling Approach , 2011 .

[20]  Ginger Lockhart,et al.  A comparison of four approaches to account for method effects in latent state-trait analyses. , 2012, Psychological methods.

[21]  L. Radloff.  The CES-D Scale , 1977 .

[22]  Daniel L. Murphy,et al.  The Effects of Autocorrelation on the Curve-of-Factors Growth Model , 2011 .

[23]  Michael Eid,et al.  On the meaning of the latent variables in the CT-C(M-1) model: a comment on Maydeu-Olivares and Coffman (2006). , 2008, Psychological methods.

[24]  Rolf Steyer,et al.  Models of classical psychometric test theory as stochastic measurement models: Representation, uniqueness, meaningfulness, identifiability, and testability. , 1989 .

[25]  J. Mcardle,et al.  Latent difference score structural models for linear dynamic analyses with incomplete longitudinal data. , 2001 .

[26]  Gregory R. Hancock,et al.  An Illustration of Second-Order Latent Growth Models , 2001 .

[27]  Delia S. Saenz,et al.  Sampling and recruitment in studies of cultural influences on adjustment: a case study with Mexican Americans. , 2008, Journal of family psychology : JFP : journal of the Division of Family Psychology of the American Psychological Association.

[28]  Manfred J. Schmitt,et al.  The effects of aggregation across and within occasions on consistency, specificity and reliability. , 1990 .

[29]  L. Dumenci,et al.  A Latent Trait-State Model of Adolescent Depression Using the Center for Epidemiologic Studies-Depression Scale. , 1996, Multivariate behavioral research.

[30]  Rolf Steyer,et al.  Latent state-trait models. , 2012 .

[31]  R. Steyer,et al.  A General Approach to Defining Latent Growth Components , 2012 .

[32]  M. Eid,et al.  Measuring Variability and Change With an Item Response Model for Polytomous Variables , 1998 .

[33]  Michael Eid,et al.  Analyzing true change in longitudinal multitrait-multimethod studies: application of a multimethod change model to depression and anxiety in children. , 2010, Developmental psychology.

[34]  Jacob Bishop,et al.  Modeling latent growth with multiple indicators: a comparison of three approaches. , 2015, Psychological methods.

[35]  Walter L. Leite.  A Comparison of Latent Growth Models for Constructs Measured by Multiple Items , 2007 .

[36]  Ulman Lindenberger,et al.  The effect of multiple indicators on the power to detect inter-individual differences in change. , 2010, The British journal of mathematical and statistical psychology.

[37]  M. Eid,et al.  Modeling true intraindividual change: True change as a latent variable. , 1997 .

[38]  R. Steyer,et al.  Modeling Latent Trait-Change , 2004 .

[39]  Steffi Pohl,et al.  Modelling method effects as individual causal effects , 2007 .

[40]  M. Schmitt,et al.  Vorschlag zur Vereinfachung des Beck-Depressions-Inventars (BDI) , 2000 .

[41]  David Chan,et al.  The Conceptualization and Analysis of Change Over Time: An Integrative Approach Incorporating Longitudinal Mean and Covariance Structures Analysis (LMACS) and Multiple Indicator Latent Growth Modeling (MLGM) , 1998 .

[42]  M. R. Novick.  The axioms and principal results of classical test theory , 1965 .

[43]  George W. Bohrnstedt,et al.  Common, Specific, and Error Variance Components of Factor Models , 1987 .

[44]  D. Bandalos.  The Effects of Item Parceling on Goodness-of-Fit and Parameter Estimate Bias in Structural Equation Modeling , 2002 .

[45]  Patricio Cumsille,et al.  Second-order latent growth models. , 2001 .