Robust estimation of dropout models using hierarchical likelihood

Noh, M; Lee, Y; Kenward, MG; (2011) Robust estimation of dropout models using hierarchical likelihood. Journal of statistical computation and simulation, 81 (6). pp. 693-706. ISSN 0094-9655 DOI:

Full text not available from this repository. (Request a copy)


It is very well known that analyses for missing data depend on untestable assumptions. As a consequence, in such settings, sensitivity analyses are often sensible. One such class of analyses assesses the dependence of conclusions on an explicit missing value mechanism. Inevitably, there is an association between such dependence and the actual (but unknown) distribution of the missing data. In a particular parametric framework for dropout in this paper, an approach is presented that reduces (but never removes) the impact of incorrect assumptions on the form of the association. It is shown how these models can be formulated and fitted relatively simply using hierarchical likelihood. These are applied directly to an example involving mastitis in dairy cattle, and an extensive simulation study is described to show the properties of the methods.

Item Type: Article
Keywords: adjusted profile likelihood, hierarchical likelihood, marginal, likelihood, missing data, restricted likelihood, sensitivity analysis, GENERALIZED LINEAR-MODELS, MISSING DATA, T-DISTRIBUTION, SENSITIVITY, INFERENCE
Faculty and Department: Faculty of Epidemiology and Population Health > Dept of Medical Statistics
Research Centre: Centre for Statistical Methodology
Web of Science ID: 290680600003


Download activity - last 12 months
Downloads since deposit
Accesses by country - last 12 months
Accesses by referrer - last 12 months
Impact and interest
Additional statistics for this record are available via IRStats2

Actions (login required)

Edit Item Edit Item