Author:

Keywords:

Science & Technology, Physical Sciences, Statistics & Probability, Mathematics, interval of ignorance, linear mixed model, missing at random, missing not at random, multivariate normal, sensitivity analysis, PATTERN-MIXTURE MODELS, LOCAL INFLUENCE APPROACH, SENSITIVITY-ANALYSIS, REGRESSION-MODELS, NONRANDOM DROPOUT, CATEGORICAL-DATA, MISSING DATA, INFERENCE, TRIAL, STATISTICS, stat.ME, 0104 Statistics, 4905 Statistics

Abstract:

Model selection and assessment with incomplete data pose challenges in addition to the ones encountered with complete data. There are two main reasons for this. First, many models describe characteristics of the complete data, in spite of the fact that only an incomplete subset is observed. Direct comparison between model and data is then less than straightforward. Second, many commonly used models are more sensitive to assumptions than in the complete-data situation and some of their properties vanish when they are fitted to incomplete, unbalanced data. These and other issues are brought forward using two key examples, one of a continuous and one of a categorical nature. We argue that model assessment ought to consist of two parts: (i) assessment of a model's fit to the observed data and (ii) assessment of the sensitivity of inferences to unverifiable assumptions, that is, to how a model described the unobserved data given the observed ones. © Institute of Mathematical Statistics, 2008.