Exploratory Data Analysis with MATLAB

by Steven D. Strauss

Exploratory data analysis (EDA) was conceived at a time when computers were not widely used, and thus computational ability was rather limited. As computational sophistication has increased, EDA has become an even more powerful process for visualizing and summarizing data before making model assumptions to generate hypotheses, encompassing larger and more complex data sets. There are many resources for those interested in the theory of EDA, but this is the first book to use MATLAB to illustrate the computational aspects of this discipline.

Exploratory Data Analysis with MATLAB presents the methods of EDA from a computational perspective. The authors extensively use MATLAB code and algorithm descriptions to provide state-of-the-art techniques for finding patterns and structure in data. Addressing theory, they also incorporate many annotated references to direct readers to the more theoretical aspects of the methods. The book presents an approach using the basic functions from MATLAB and the MATLAB Statistics Toolbox, in order to be more accessible and enduring. It also contains pseudo-code to enable users of other software packages to implement the algorithms.

This text places the tools needed to implement EDA theory at the fingertips of researchers, applied mathematicians, computer scientists, engineers, and statisticians by using a practical/computational approach.

424 pages, Hardcover

Published November 29, 2004

Reviews

[Jin Shusong · Rating 4 out of 5]

This book thoroughly introduced the methods used in EDA. The authors explained the theory briefly and gave the algorithms in detail. The example codes were helpful. However, I found that the author failed to explain what we could find from the results of these methods. For example, the book introduced the intrinsic dimension. The authors also gave examples. But, what could I find and how can I use these results?

[Darin]

This book discusses ways to look at data to understand the underlying structure, including quite a bit about clustering. The included Matlab code is very helpful. While this isn't really a theory book, each chapter does have a bibliography that I found useful.