HIERARCHICAL STRUCTURE OF DENTAL DATA IN THE RANDOM EFFECTS INCLUSION APPROACH

Abstract

Data sets with complex structures is increasingly common in dental research. As consequences, statistical  methods to analyze and interpret these data must be efficient and robust. Hierarchical structures is one of  the most common kind of complex structures, and a proper approach is required. The multilevel modeling used to study hierarchical structures is a powerful tool which allows the collected data to be  analyzes in several levels. This study has as objective to make a literature review on multilevel linear models and to illustrate a three level model through a matrix procedure, without the use of specific software to estimate the parameters. With this model, we analyzed the vertical gingival retraction when using the substances: Naphazoline Chloridrate, Aluminium Chloride and without any substance. The intraclass correlation coefficient on dental level within patients showed that the hierarchical structure was important to accommodate the dependence within clusters.