An empirical comparison of some outlier detection methods with longitudinal data

TL;DR

This paper compares traditional statistical outlier detection methods with modern machine learning approaches on longitudinal data, highlighting their differences in assumptions, flexibility, and effectiveness through empirical analysis.

Contribution

It provides an empirical comparison of classical and modern outlier detection methods applied to longitudinal data, illustrating their relative strengths and limitations.

Findings

Recent methods are more flexible and sometimes more effective.

Traditional methods are simple but require specific assumptions.

Modern methods can handle multidimensional data.

Abstract

This note investigates the problem of detecting outliers in longitudinal data. It compares well-known methods used in official statistics with proposals from the fields of data mining and machine learning that are based on the distance between observations or binary partitioning trees. This is achieved by applying the methods to panel survey data related to different types of statistical units. Traditional methods are quite simple, enabling the direct identification of potential outliers, but they require specific assumptions. In contrast, recent methods provide only a score whose magnitude is directly related to the likelihood of an outlier being present. All the methods require the user to set a number of tuning parameters. However, the most recent methods are more flexible and sometimes more effective than traditional methods. In addition, these methods can be applied to multidimensional data.