1. Introduction 1. Data augmentation and parameter expansion in likelihood and Bayesian inference 2. Model expansion for substantive or computational reasons 2. Truncated and censored data 1. truncated and censored data models 2. modeling truncated data as censored but with an unknown number of censored data points 3. Latent variables 1. latent discrete variables in mixture models 2. latent continuous variables in logistic regression 4. multivariate missing-data imputation 1. iterative univartiate imputations 2. inconsistent conditional distributions 3. example from survey imputation 4. potential consequences of incompatibility 5. multilevle regression models 1. rescaling regression predictors 2. parameter expansion 1. hierarchical model with potentially slow convergence 2.