Modeling Change in the Presence of Nonrandomly Missing Data: Evaluating a Shared Parameter Mixture Model

In longitudinal research, interest often centers on individual trajectories of change over time. When there is missing data, a concern is whether data are systematically missing as a function of the individual trajectories. Such a missing data process, termed random coefficient-dependent missingness, is statistically nonignorable and can bias parameter estimates obtained from conventional growth models that assume missing data are missing at random. This article describes a shared parameter mixture model (SPMM) for testing the sensitivity of growth model parameter estimates to a random coefficient-dependent missingness mechanism. Simulations show that the SPMM recovers trajectory estimates as well as or better than a standard growth model across a range of missing data conditions. The article concludes with practical advice for longitudinal data analysts.

[1]  Daniel J. Bauer,et al.  Factors Affecting the Adequacy and Preferability of Semiparametric Groups-Based Approximations of Continuous Growth Trajectories , 2012, Multivariate behavioral research.

[2]  G. A. Marcoulides,et al.  Using the Delta Method for Approximate Interval Estimation of Parameter Functions in SEM , 2004 .

[3]  J. Laub,et al.  On the Robustness and Validity of Groups , 2004 .

[4]  Jason Roy,et al.  Latent class models and their application to missing-data patterns in longitudinal studies , 2007, Statistical methods in medical research.

[5]  Christopher Winship,et al.  Models for Sample Selection Bias , 1992 .

[6]  Jeroen K. Vermunt,et al.  A nonparametric random-coefficients approach : The latest class regression model , 2001 .

[7]  G. Verbeke,et al.  A Linear Mixed-Effects Model with Heterogeneity in the Random-Effects Population , 1996 .

[8]  Joseph L Schafer,et al.  Analysis of Incomplete Multivariate Data , 1997 .

[9]  David C. Atkins,et al.  Rates of change in naturalistic psychotherapy: contrasting dose-effect and good-enough level models of change. , 2009, Journal of consulting and clinical psychology.

[10]  Roger A. Sugden,et al.  Multiple Imputation for Nonresponse in Surveys , 1988 .

[11]  M. Davier,et al.  Modeling Nonignorable Missing Data with Item Response Theory (IRT). Research Report. ETS RR-10-11. , 2010 .

[12]  M. Kenward,et al.  Informative Drop‐Out in Longitudinal Data Analysis , 1994 .

[13]  Craig K Enders,et al.  Missing not at random models for latent growth curve analyses. , 2011, Psychological methods.

[14]  Antonio A Morgan-Lopez,et al.  Analytic methods for modeling longitudinal data from rolling therapy groups with membership turnover. , 2007, Journal of consulting and clinical psychology.

[15]  G Molenberghs,et al.  Sensitivity Analysis for Nonrandom Dropout: A Local Influence Approach , 2001, Biometrics.

[16]  Daniel S. Nagin,et al.  Analyzing developmental trajectories: A semiparametric, group-based approach , 1999 .

[17]  Yiu-Fai Yung,et al.  Finite mixtures in confirmatory factor-analysis models , 1997 .

[18]  Geert Molenberghs,et al.  EVERY MISSING NOT AT RANDOM MODEL HAS GOT A MISSING AT RANDOM COUNTERPART WITH EQUAL FIT , 2008 .

[19]  G. A. Marcoulides,et al.  Advanced structural equation modeling : issues and techniques , 1996 .

[20]  W. Wothke.  Longitudinal and multigroup modeling with missing data. , 2000 .

[21]  B. Muthén,et al.  Finite Mixture Modeling with Mixture Outcomes Using the EM Algorithm , 1999, Biometrics.

[22]  Geert Verbeke,et al.  A Semi‐Parametric Shared Parameter Model to Handle Nonmonotone Nonignorable Missingness , 2009, Biometrics.

[23]  R. Little,et al.  Selection and pattern-mixture models , 2008 .

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

[25]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data: Little/Statistical Analysis with Missing Data , 2002 .

[26]  Daniel J Bauer,et al.  Local solutions in the estimation of growth mixture models. , 2006, Psychological methods.

[27]  Roderick J. A. Little,et al.  A Class of Pattern-Mixture Models for Normal Incomplete Data , 1994 .

[28]  B. Muthén,et al.  Growth modeling with nonignorable dropout: alternative analyses of the STAR*D antidepressant trial. , 2011, Psychological methods.

[29]  W. Fals-Stewart,et al.  Consequences of misspecifying the number of latent treatment attendance classes in modeling group membership turnover within ecologically valid behavioral treatment trials. , 2008, Journal of substance abuse treatment.

[30]  Nisha C. Gottfredson,et al.  Evaluating shared parameter mixture models for analyzing change in the presence of non-randomly missing data , 2011 .

[31]  Jason Roy,et al.  Modeling Longitudinal Data with Nonignorable Dropouts Using a Latent Dropout Class Model , 2003, Biometrics.

[32]  J. Heckman,et al.  A Method for Minimizing the Impact of Distributional Assumptions in Econometric Models for Duration Data , 1984 .

[33]  Russell V. Lenth,et al.  Statistical Analysis With Missing Data (2nd ed.) (Book) , 2004 .

[34]  J. Schafer,et al.  A comparison of inclusive and restrictive strategies in modern missing data procedures. , 2001, Psychological methods.

[35]  Gerhard Arminger,et al.  Mixtures of conditional mean- and covariance-structure models , 1999 .

[36]  A. McNeil,et al.  Latent Curve Models: A Structural Equation Approach , 2007 .

[37]  Manshu Yang,et al.  Abstract: Treatment Effects in Randomized Longitudinal Experiments with Different Types of Non-Ignorable Dropout , 2009, Multivariate behavioral research.

[38]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

[39]  Daniel J Bauer,et al.  Distributional assumptions of growth mixture models: implications for overextraction of latent trajectory classes. , 2003, Psychological methods.

[40]  Craig K. Enders,et al.  A Primer on Maximum Likelihood Algorithms Available for Use With Missing Data , 2001 .

[41]  Joseph L Schafer,et al.  On the performance of random‐coefficient pattern‐mixture models for non‐ignorable drop‐out , 2003, Statistics in medicine.

[42]  Roderick J. A. Little,et al.  Modeling the Drop-Out Mechanism in Repeated-Measures Studies , 1995 .

[43]  Charles E McCulloch,et al.  Latent Pattern Mixture Models for Informative Intermittent Missing Data in Longitudinal Studies , 2004, Biometrics.

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

[45]  M. Kenward.  Selection models for repeated measurements with non-random dropout: an illustration of sensitivity. , 1998, Statistics in medicine.

[46]  R. Little.  Pattern-Mixture Models for Multivariate Incomplete Data , 1993 .

[47]  Raymond J. Carroll,et al.  Estimation and comparison of changes in the presence of informative right censoring by modeling the censoring process , 1988 .

[48]  Daniel J. Bauer.  Observations on the Use of Growth Mixture Models in Psychological Research , 2007 .

[49]  B. Muthén,et al.  Performance of Factor Mixture Models as a Function of Model Size, Covariate Effects, and Class-Specific Parameters. , 2007 .

[50]  Han L. J. van der Maas,et al.  Fitting multivariage normal finite mixtures subject to structural equation modeling , 1998 .

[51]  James L. Arbuckle,et al.  Full Information Estimation in the Presence of Incomplete Data , 1996 .

[52]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[53]  W. DeSarbo,et al.  Finite-Mixture Structural Equation Models for Response-Based Segmentation and Unobserved Heterogeneity , 1997 .

[54]  J. Schafer.  Multiple imputation: a primer , 1999, Statistical methods in medical research.

[55]  Cécile Proust-Lima,et al.  The International Journal of Biostatistics Pattern Mixture Models and Latent Class Models for the Analysis of Multivariate Longitudinal Data with Informative Dropouts , 2011 .

[56]  J. Heckman.  The Common Structure of Statistical Models of Truncation, Sample Selection and Limited Dependent Variables and a Simple Estimator for Such Models , 1976 .

[57]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data , 1988 .

[58]  H. Akaike.  A new look at the statistical model identification , 1974 .

[59]  M. Kenward,et al.  Every missingness not at random model has a missingness at random counterpart with equal fit , 2008 .