Probabilistic and Statistical Models for Outlier Detection
The oldest methods for outlier detection are rooted in probabilistic and statistical models, and date back to the nineteenth century . The earliest methods were proposed well before the advent and popularization of computer technology. Therefore, these methods were designed without much focus on practical issues such as data representation or computational efficiency. Nevertheless, the underlying mathematical models are extremely useful, and have eventually been adapted to a variety of computational scenarios.
KeywordsConvex Hull Central Limit Theorem Gaussian Mixture Model Mahalanobis Distance Outlier Detection
Unable to display preview. Download preview PDF.