Data in health research are frequently structured hierarchically. For example, data may consist of patients nested within physicians, who in turn may be nested in hospitals or geographic regions. Fitting regression models that ignore the hierarchical structure of the data can lead to false inferences being drawn from the data. Implementing a statistical analysis that takes into account the hierarchical structure of the data requires special methodologies. In this paper, the concept of hierarchically structured data is introduced, and an introduction to hierarchical regression models is presented. The performance of a traditional regression model with that of a hierarchical regression model is compared on a dataset relating test utilization at the annual health exam with patient and physician characteristics. In comparing the resultant models, it is evident that false inferences can be drawn by ignoring the structure of the data.
View full text
Research and statistical methods