A New Technique for Identification of Outliers using various extreme value distributions

An outlier is an observation that appears to deviate markedly from other observations in the sample as to arouse suspicions that it was generated by a different mechanism. Outlier detection is known as one of the most important tasks in data analysis. The outliers describe the abnormal data behavior, i.e., data which are deviating from the natural data variability. Some other terminologies e.g., abnormalities, discordants, deviants, or anomalies are also commonly used in the data mining and statistics literature. Outliers are categorized in two sectors: some of them are unusual data and should be omitted by one of the outlier detection methods; however there are points which do not belong to bad data category clearly. These data points are due to random variation in measurements or may be scientifically interesting due to something informative inside them. The present book “A New Technique for Identification of Outliers using various extreme value distributions” comprises of total five chapters viz., Introduction, Effect of presence of outliers in the estimation of parameters of Extreme Value Distributions, Detection of a single outlier in a sample from a Gumbel Distribution with known scale parameter, Detection of outliers in a sample from a Frechet Distribution and Detection of outliers in a sample from a Weibull Distribution.