Double serial correlation for multilevel growth curve models

Multilevel growth curve models for repeated measures data have become increasingly popular and stand as a flexible tool for investigating longitudinal change in students’ outcome variables. In addition, these models allow the estimation of school effects on students’ outcomes though making strong assumptions about the serial independence of level-1 residuals. This paper introduces a method which takes into account the serial correlation of level-1 residuals and also introduces such serial correlation at level-2 in a complex double serial correlation (DSC) multilevel growth curve model. The results of this study from both real and simulated data show a great improvement in school effects estimates compared to those that have previously been found using multilevel growth curve models without correcting for DSC for both the students’ status and growth criteria.

[1]  Geert Verbeke,et al.  Assessing the goodness-of-fit of the laird and ware model : An example : The jimma infant survival differential longitudinal study , 1999 .

[2]  H Goldstein,et al.  Multilevel time series models with applications to repeated measures data. , 1994, Statistics in medicine.

[3]  Jeffrey R. Harring.  A Nonlinear Mixed Effects Model for Latent Variables , 2009 .

[4]  Christopher H. Morrell,et al.  Estimating Unknown Transition Times Using a Piecewise Nonlinear Mixed-Effects Model in Men with Prostate Cancer , 1995 .

[5]  G. Molenberghs,et al.  Linear Mixed Models for Longitudinal Data , 2001 .

[6]  Li Cai,et al.  Consequences of Unmodeled Nonlinear Effects in Multilevel Models , 2009 .

[7]  P. Diggle,et al.  Analysis of Longitudinal Data , 2003 .

[8]  Judith D. Singer,et al.  Using SAS PROC MIXED to Fit Multilevel Models, Hierarchical Models, and Individual Growth Models , 1998 .

[9]  E Lesaffre,et al.  The detection of residual serial correlation in linear mixed models. , 1998, Statistics in medicine.

[10]  G. Verbeke,et al.  The effect of misspecifying the random-effects distribution in linear mixed models for longitudinal data , 1997 .

[11]  Gregory Camilli,et al.  Application of a Method of Estimating DIF for Polytomous Test Items , 1999 .

[12]  M. Opdenakker,et al.  Educational Effectiveness : an introduction to international and Flemish research on schools, teachers and classes , 2006 .

[13]  P. Onghena,et al.  The impact of coding time on the estimation of school effects , 2013 .

[14]  C. Teddlie,et al.  The International Handbook of School Effectiveness Research , 1999 .

[15]  Stephen W. Raudenbush,et al.  The Estimation of School Effects , 1995 .

[16]  P. Diggle.  An approach to the analysis of repeated measurements. , 1988, Biometrics.

[17]  Stephen Raudenbush,et al.  A longitudinal hierarchical linear models for estimating school e?ects and their stability , 1989 .

[18]  P. Diggle.  Time Series: A Biostatistical Introduction , 1990 .

[19]  Ian H. Langford,et al.  A User’s Guide to MLwiN, Version 2.10 , 2000 .

[20]  J. Ware,et al.  Applied Longitudinal Analysis , 2004 .

[21]  Jaap Scheerens,et al.  The Foundations of Educational Effectiveness , 1997 .

[22]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[23]  John Ferron,et al.  Effects of Misspecifying the First-Level Error Structure in Two-Level Models of Change , 2002, Multivariate behavioral research.