Since publication of the bestselling Environmental Data Analysis with MATLAB, many advances have been made in environmental data analysis. This new edition expands fundamentally on the original with an expanded tutorial approach, with new crib sheets and problem sets providing a clear learning path for students and researchers working to analyze real data sets in the environmental sciences. One only has to consider the global warming debate to realize how critically important it is to be able to derive clear conclusions from often-noisy data drawn from a broad range of sources. The work teaches the basics of the underlying theory of data analysis and then reinforces that knowledge with carefully chosen, realistic scenarios. MATLAB, a commercial data processing environment, is used in these scenarios; significant content is devoted to teaching how it can be effectively used in an environmental data analysis setting. This new edition, though written in a self-contained way, is supplemented with data and MATLAB scripts that can be used as a data analysis tutorial.
New to this edition:
- Throughout, boxed "crib sheets" help identify major results and important formulas and give brief advice on how and when they should be used
- Numerical derivatives and integrals derived and illustrated
- Expansion to include log-log plots with further examples of their use
- Discusses new datasets on precipitation and stream flow
- Topical enhancement applies the chi-squared test to the results of the generalized least squares method
- New section on cluster analysis
- New coverage of approximations techniques that are widely applied in data analysis. These include Taylor Series and low-order polynomial approximations; non-linear least-squares with Newton’s method; pre-calculation and updating techniques applicable to real time data acquisition; and neural networks for approximating complex relationships
- Corrections of typographical errors and of call outs of figures and equations
- Data analysis with MatLab
- A first look at data
- Probability and what it has to do with data analysis
- The power of linear models
- Quantifying preconceptions
- Detecting periodicities
- The past influences the present
- Patterns suggested by data
- Detecting correlations among data
- Filling in missing data
- "Approximate" is not a pejorative word
- Are my results significant?
- Notes
William Menke is a Professor of Earth and Environmental Sciences at Columbia University, USA. His research focuses on the development of data analysis algorithms for time series analysis and imaging in the earth and environmental sciences and the application of these methods to volcanoes, earthquakes and other natural hazards.
Joshua Menke is a software engineer and principal of JOM Associates. His specialty is in the design and implementation of parallel processing systems for matching and correlation of large volumes of data in order to identify and quantify trends and patterns that can assist manufacturers and retailer better serve their clientele.