tde: trimmed density estimation and its application in outlierdetection; an approach based on forward search

The presence of an outlier in data influences the accuracy and reliabilityof statistical inference. density estimation is affected by an outlier too. we proposetrimmed density estimation (tde) approach which by forward search in density of observations,ranks the data based on their outlyingness. this technique is able to detecta local outlier as good as a global outlier in multivariate mixture data. the introducedalgorithm, after trimming the outliers, estimates the density of all observations usingthe remaining clean data to achieve robust density estimation. tde overcomes thelimitations of existing methods, such as the low accuracy and high sensitivity to initialsetting of the parameters. to implement the forward search, we present a techniqueto select an initial free outlier subset in complex data. using the estimated densityof ordered data by forward search, we figure out a cut-off point to trim the outliers.experiments demonstrate that tde’s average accuracy is better than the existing approachesand is free of tuning the parameters.