Analysis of Multivariate and High-Dimensional Data

This modern approach integrates classical and contemporary methods, fusing theory and practice and bridging the gap to statistical learning.

Inge Koch (Author)

9780521887939, Cambridge University Press

Hardback, published 2 December 2013

526 pages, 5 b/w illus. 98 colour illus. 76 tables 138 exercises
26 x 18.2 x 2.8 cm, 1.29 kg

'I must highly commend the author for writing an excellent comprehensive review of multivariate and high dimensional statistics … The lucid treatment and thoughtful presentation are two additional attractive features … Without any hesitation and with admiration, I would give the author a 10 out of 10 … The feat she has accomplished successfully for this difficult area of statistics is something very few could accomplish. The wealth of information is enormous and a motivated student can learn a great deal from this book … I highly recommend [it] to researchers working in the field of high dimensional data and to motivated graduate students.' Ravindra Khattree, International Statistical Review

'Big data' poses challenges that require both classical multivariate methods and contemporary techniques from machine learning and engineering. This modern text equips you for the new world - integrating the old and the new, fusing theory and practice and bridging the gap to statistical learning. The theoretical framework includes formal statements that set out clearly the guaranteed 'safe operating zone' for the methods and allow you to assess whether data is in the zone, or near enough. Extensive examples showcase the strengths and limitations of different methods with small classical data, data from medicine, biology, marketing and finance, high-dimensional data from bioinformatics, functional data from proteomics, and simulated data. High-dimension low-sample-size data gets special attention. Several data sets are revisited repeatedly to allow comparison of methods. Generous use of colour, algorithms, Matlab code, and problem sets complete the package. Suitable for master's/graduate students in statistics and researchers in data-rich disciplines.

Part I. Classical Methods: 1. Multidimensional data
2. Principal component analysis
3. Canonical correlation analysis
4. Discriminant analysis
Part II. Factors and Groupings: 5. Norms, proximities, features, and dualities
6. Cluster analysis
7. Factor analysis
8. Multidimensional scaling
Part III. Non-Gaussian Analysis: 9. Towards non-Gaussianity
10. Independent component analysis
11. Projection pursuit
12. Kernel and more independent component methods
13. Feature selection and principal component analysis revisited
Index.

Subject Areas: Machine learning [UYQM], Probability & statistics [PBT], Epidemiology & medical statistics [MBNS], Economic statistics [KCHS], Econometrics [KCH], Data analysis: general [GPH]