Outliers in Multilevel Data Export

@article{citeulike:234836, abstract = {This paper offers the data analyst a range of practical procedures for dealing with outliers in multilevel data. It first develops several techniques for data exploration for outliers and outlier analysis and then applies these to the detailed analysis of outliers in two large scale multilevel data sets from educational contexts. The techniques include the use of deviance reduction, measures based on residuals, leverage values, hierarchical cluster analysis and a measure called DFITS. Outlier analysis is more complex in a multilevel data set than in, say, a univariate sample or a set of regression data, where the concept of an outlying value is straightforward. In the multilevel situation one has to consider, for example, at what level or levels a particular response is outlying, and in respect of which explanatory variables; furthermore, the treatment of a particular response at one level may affect its status or the status of other units at other levels in the model.}, author = {Langford, Ian H. and Lewis, Toby}, citeulike-article-id = {234836}, citeulike-linkout-0 = {http://www.jstor.org/stable/2983246}, journal = {Journal of the Royal Statistical Society A}, keywords = {diagnostics, multilevel, statistics}, pages = {121--160}, posted-at = {2005-06-22 14:34:13}, priority = {2}, title = {Outliers in Multilevel Data}, url = {http://www.jstor.org/stable/2983246}, volume = {161}, year = {1998} }

TY - JOUR ID - citeulike:234836 L3 - citeulike-article-id:234836 N2 - This paper offers the data analyst a range of practical procedures for dealing with outliers in multilevel data. It first develops several techniques for data exploration for outliers and outlier analysis and then applies these to the detailed analysis of outliers in two large scale multilevel data sets from educational contexts. The techniques include the use of deviance reduction, measures based on residuals, leverage values, hierarchical cluster analysis and a measure called DFITS. Outlier analysis is more complex in a multilevel data set than in, say, a univariate sample or a set of regression data, where the concept of an outlying value is straightforward. In the multilevel situation one has to consider, for example, at what level or levels a particular response is outlying, and in respect of which explanatory variables; furthermore, the treatment of a particular response at one level may affect its status or the status of other units at other levels in the model. JF - Journal of the Royal Statistical Society A EP - 160 TI - Outliers in Multilevel Data VL - 161 SP - 121 KW - diagnostics KW - multilevel KW - statistics AU - Langford, Ian AU - Lewis, Toby PY - 1998/// UR - http://www.jstor.org/stable/2983246 ER -