Can I read HubertRousseeuwVerboven RobustPCAhighdim DIRS 2003 on EtoBox?

HubertRousseeuwVerboven RobustPCAhighdim DIRS 2003 by jinxingwang0223 is a document available to read on EtoBox.

What is HubertRousseeuwVerboven RobustPCAhighdim DIRS 2003 about?

The document discusses robust Principal Component Analysis (PCA) methods for high-dimensional data, which are necessary due to the limitations of classical PCA that is sensitive to outliers. It compares two robust methods: one based on projection pursuit and another combining outlyingness with the FAST-MCD algorithm, evaluating their performance through simulation studies. The paper provides detailed algorithms for both methods and illustrates their application on chemometrical data sets.

Author

jinxingwang0223

Language

EN