Outlier detection to hierarchical and mixedeffects models

Antonella Plaia, Miriam Daniele

Research output: Contribution to conferenceOtherpeer-review

Abstract

Hierarchical and mixed effects modelsare models where a varying number of coefficients may be random atdifferent levels of the hierarchy.The purpose of outlier analysis for these models is to determine whetheran outlying unit at higher level is entirely outlying, or outlying due to effectof one or a few aberrant lower level units.Most works on diagnostics for these complex models have focusedon the mixed model rather than on the hierarchical models, obscuring somerelevant aspects of the hierarchical model.In this paper we will present an approach toinfluence analysis and outlier detection for mixed and hierarchicalmodel, focusing on the special structure of nested data thatthese models describe.
Original languageEnglish
Number of pages0
Publication statusPublished - 2008

Fingerprint

Dive into the research topics of 'Outlier detection to hierarchical and mixedeffects models'. Together they form a unique fingerprint.

Cite this