Extremes in random fields. A theory and its applications (Q2851118)

A large bulk of the present science typically leads to analyzing large, possibly complex data sets. Optimal statistical procedures dealing with such data sets commonly rely on extreme values, often resulting from the necessity to have a uniform control of stochastic errors. This book focuses on analytical approximations of statistical significance tests based on extreme values, presenting a useful new technique for analyzing extremal behaviour of certain random fields. Several relatively complex applications of the technique to problems that emerge in practical situations are presented, with an emphasis on sequential procedures. All the examples are difficult to analyze using classical methods. The author presents a novel technique together with recipes and instructions, designed to be more accessible to the user. A~key feature of the method is a change of measure technique, based on the likelihood ratio approach. The general idea is motivated via basic examples and intuitions in the introduction. After explaining the method and its merits in full detail, a number of interesting examples and applications are discussed in the following chapters.NEWLINENEWLINEExtreme value analysis is widely applied in areas such as operations research, bioinformatics, computer science, finance and many other disciplines. This book will be useful for scientists, engineers and graduate students who need to develop their own statistical tools for the analysis of their data. Whilst the book does not (nor does it claim to) provide a general account of the many different techniques used in the field of extreme value theory, it offers the reader an interesting and inspiring approach that has proved to be fruitful for many statistical problems.