Singer & Willett, 2003 October 13, 2003 © Harvard University 1 Doing Data Analysis in the Multilevel Model for Change Doing Data Analysis in the Multilevel Model for Change Judy Singer & John Willett Harvard University Graduate School of Education What we will cover? What we will cover? p.116 §4.6 Comparing models  Using deviance statistics  Using information criteria (AIC and BIC) p.132 §4.9 Model-based (Empirical Bayes) estimates of the individual growth trajectories p.104 §4.5 Practical model building strategies  Developing and fitting a taxonomy of models  Displaying prototypical change trajectories  Recentering to improve interpretation p.92 §4.4 First steps: unconditional means model and unconditional growth model  Intraclass correlation  Quantifying proportion of explained outcome variation p.80 §4.2 Composite specification of the multilevel model for change