A new parameterization for pattern mixture models oflongitudinal data with informative dropoutMichael

Pattern mixture models are frequently used to analyze longitudinal data where missingness is induced by dropout. For measured responses, it is typical to model the complete data as a mixture of multivariate normal distributions, where mixing is done over the dropout distribution. Fully parameterized pattern mixture models are not identiied by incomplete data; Little (1993) has characterized several identifying restrictions which can be used for model tting. We propose a re-parameterization of the pattern mixture model which allows investigation of sensitivity to assumptions about non-identiied parameters in both the mean and variance, and allows consideration of a wide range of non-ignorable missing data mechanisms. The parameterization makes clear an advantage of pattern mixture models over parametric selection models, namely that the missing data mechanism can be varied without aaecting the marginal distribution of the observed data. To illustrate the utility of the new parameterization, we analyze data from a recent clinical trial of growth hormone for maintaining muscle strength in the elderly. Dropout occurs at a high rate and is potentially informative. We undertake a detailed sensitivity analysis to understand the impact of missing data assumptions on the inference about the eeects of growth hormone on muscle strength.