Testing ignorable missingness in estimating equation approaches for longitudinal data

• Published in: Biometrika 2002-12, Vol.89 (4), p.841-850
• Main Authors: Qu, Annie, Song, Peter X.‐K.
• Format: Article
• Language: English
• Subjects: Applications; Consistent estimators; Estimation bias; Estimators; Exact sciences and technology; Generalised estimating equation; Goodness‐of‐fit test; Hypotheses; Hypothesis testing; Ignorable missingness; Inference; Linear inference, regression; Longitudinal data; Longitudinal studies; Mathematics; Maximum likelihood estimation; Medical sciences; Missing data; Numerical analysis; Numerical analysis. Scientific computation; Numerical methods in probability and statistics; Parametric inference; Probability and statistics; Quadratic inference function; Sample size; Schizophrenia; Schizophrenia trial; Sciences and techniques of general use; Statistics
• ISSN: 0006-3444; 1464-3510
• DOI: 10.1093/biomet/89.4.841

We address the matter of determining whether or not missing data in longitudinal studies are ignorable with regard to quasilikelihood or estimating equations approaches. This involves testing for whether or not the zero‐mean property of estimating equations holds true. Chen & Little (1999) proposed testing for significant differences among parameter estimators calculated from sample subsets with different patterns of missing data, whereas we propose a more unified generalised score‐type test. This avoids exhaustive estimation of parameters for each missing‐data pattern, testing instead with a single quadratic score test statistic whether or not there is a common parameter under which the means of all the pattern‐specific estimating equations are zero. Comparisons are made for the two approaches with both simulations and real data examples.