Gilbert Saporta – författare

Data science unifies statistics, data analysis and machine learning to achieve a better understanding of the masses of data which are produced today, and to improve prediction. Special kinds of data (symbolic, network, complex, compositional) are increasingly frequent in data science. These data require specific methodologies, but there is a lack of reference work in this field. Advances in Data Science fills this gap. It presents a collection of up-to-date contributions by eminent scholars following two international workshops held in Beijing and Paris. The 10 chapters are organized into four parts: Symbolic Data, Complex Data, Network Data and Clustering. They include fundamental contributions, as well as applications to several domains, including business and the social sciences.

This volume presents state of the art theories, new developments, and important applications of Partial Least Square (PLS) methods.

This volume presents state of the art theories, new developments, and important applications of Partial Least Square (PLS) methods.

The major focus of the book is on using the methods suitable for an on-line and off-line process control both in the univariate and multivariate case. The authors not only concentrate on the standard situation when the errors accompanying the observed process are normally distributed, but also describe in detail the more general situations that call for the use of the robust and non-parametric approaches. Within these approaches, the use of recent methods of the multivariate analysis in the total quality control is enhanced with particular reference to the customer satisfaction area, the monitoring of interval data and the comparison of patterns generated from multioccasion observations. The authors cover both practical computational aspects of the problem and the necessary mathematical background, taking into account requirements of total quality control.