A Comparison of Statistical Methods for Analyzing Discrete Hierarchical Data: A Case Study of Family Data on Alcohol Abuse

摘要

Although hierarchical correlated data are increasingly available and are being used in evidence-based medical practices and health policy decision making, there is a lack of information about the strengths and weaknesses of the methods of analysis with such data. In this paper, we describe the use of hierarchical data in a family study of alcohol abuse conducted in Edmonton, Canada, that attempted to determine whether alcohol abuse in probands is associated with abuse in their first-degree relatives. We review three methods of analyzing discrete hierarchical data to account for correlations among the relatives. We conclude that the best analytic choice for typical correlated discrete hierarchical data is by nonlinear mixed effects modeling using a likelihood-based approach or multilevel (hierarchical) modeling using a quasilikelihood approach, especially when dealing with heterogeneous patient data.