Genetic algorithms for outlier detection and variable selection in linear regression models

Abstract

This article addresses some problems in outlier detection and variable selection in linear regression models. First, in outlier detection there are problems known as smearing and masking. Smearing means that one outlier makes another, non-outlier observation appear as an outlier, and masking that one outlier prevents another one from being detected. Detecting outliers one by one may therefore give misleading results. In this article a genetic algorithm is presented which considers different possible groupings of the data into outlier and non-outlier observations. In this way all outliers are detected at the same time. Second, it is known that outlier detection and variable selection can influence each other, and that different results may be obtained, depending on the order in which these two tasks are performed. It may therefore be useful to consider these tasks simultaneously, and a genetic algorithm for a simultaneous outlier detection and variable selection is suggested. Two real data sets are used to illustrate the algorithms, which are shown to work well. In addition, the scalability of the algorithms is considered with an experiment using generated data.

Stimuli-Magnitude-Adaptive Sample Selection for Data-Driven Haptic Modeling

“…Afterwards, the authors in [32] used genetic algorithms for detection of outliers and sample selection in linear regression models in the context of cross-section data. In [33], sample selection was carried out in the framework of Multi Objective Evolutionary Learning (MOEL) of Fuzzy Rule-Based Systems (FRBSs) by using a co-evolutionary method.…”

Reducing noise impact on MLP training

“…On the other hand, there only very few approaches to instance selection for regression tasks can be found in the literature and in the the publications we were able to find the experiments were conducted only on artificial datasets, which were generated especially for the purpose of the experiments. Tolvi (2004) presented a genetic algorithm to perform feature and instance selection for linear regression models. In their works Guillen (2009) discussed the concept of mutual information used for selection of prototypes in regression problems.…”

Modelling and Understanding of Speech and Speaker Recognition

“…This has to be carried out by estimating, the mapping-function between inputs and outputs of the model. Such functions are usually highly non-linear and have to be computed using adaptive vector quantization (AVQ) (Tolvi (2004); Hongwei et al (2005)) based unidirectional temporary associative memory (UTAM) of neural-network, as depicted in figure 18.…”