Riassunto:
This book thoroughly discusses the varying problems that occur in data mining, including their sources, consequences, detection, and treatment. Specific strategies for data pretreatment and analytical validation that are broadly applicable are described, making them useful in conjunction with most data mining analysis methods. Examples illustrate the performance of the pretreatment and validation methods in a variety of situations. The book, which deals with a wider range of data anomalies than are usually treated, includes a discussion of detecting anomalies through generalized sensitivity analysis (GSA), a process of identifying inconsistencies using systematic and extensive comparisons of results obtained by analysis of exchangeable datasets or subsets. Real data is made extensive use of, both in the form of a detailed analysis of a few real datasets and various published examples. A succinct introduction to functional equations illustrates their utility in describing various forms of qualitative behavior for useful data characterizations.
Recensione:
'An accessible presentation of statistical methods and analysis to deal with imperfect data in real data mining applications.' Joydeep Ghosh, University of Texas at Austin
'An appealing feature of this book is the use of fresh datasets that are much larger than those currently found in standard books on outliers and statistical diagnostics.' Anthony Atkinson, London School of Economics
'The book provides the reader with clear descriptions and accessible discussions of problems, motivations, methods and interpretations. The author excels when describing the importance of tools and their applications. The first chapter is a prime example of how to introduce important concepts and methods to a wide readership that may be composed of students, researchers and non-specialists.' Francisco J. Azuaje, BioMedical Engineering OnLine
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.