288 Pages 76 B/W Illustrations
    by Chapman & Hall

    288 Pages
    by Chapman & Hall

    Fulfilling the need for a practical user’s guide, Statistics in MATLAB: A Primer provides an accessible introduction to the latest version of MATLAB® and its extensive functionality for statistics. Assuming a basic knowledge of statistics and probability as well as a fundamental understanding of linear algebra concepts, this book:

    • Covers capabilities in the main MATLAB package, the Statistics Toolbox, and the student version of MATLAB
    • Presents examples of how MATLAB can be used to analyze data
    • Offers access to a companion website with data sets and additional examples
    • Contains figures and visual aids to assist in application of the software
    • Explains how to determine what method should be used for analysis

    Statistics in MATLAB: A Primer is an ideal reference for undergraduate and graduate students in engineering, mathematics, statistics, economics, biostatistics, and computer science. It is also appropriate for a diverse professional market, making it a valuable addition to the libraries of researchers in statistics, computer science, data mining, machine learning, image analysis, signal processing, and engineering.

    List of Tables

    Preface

    MATLAB Basics

    Desktop Environment

    Getting Help and Other Documentation

    Data Import and Export

    Data I/O via the Command Line

    The Import Wizard

    Examples of Data I/O in MATLAB

    Data I/O with the Statistics Toolbox

    More Functions for Data I/O

    Data in MATLAB

    Data Objects in Base MATLAB

    Accessing Data Elements

    Examples of Joining Data Sets

    Data Types in the Statistics Toolbox

    Object–Oriented Programming

    Miscellaneous Topics

    File and Workspace Management

    Punctuation in MATLAB

    Arithmetic Operators

    Functions in MATLAB

    Summary and Further Reading

    Visualizing Data

    Basic Plot Functions

    Plotting 2–D Data

    Plotting 3–D Data

    Examples

    Scatter Plots

    Basic 2–D and 3–D Scatter Plots

    Scatter Plot Matrix

    Examples

    GUIs for Graphics

    Simple Plot Editing

    Plotting Tools Interface

    PLOTS Tab

    Summary and Further Reading

    Descriptive Statistics

    Measures of Location

    Means, Medians, and Modes

    Examples

    Measures of Dispersion

    Range

    Variance and Standard Deviation

    Covariance and Correlation

    Examples

    Describing the Distribution

    Quantiles

    Interquartile Range

    Skewness

    Examples

    Visualizing the Data Distribution

    Histograms

    Probability Plots

    Boxplots

    Examples

    Summary and Further Reading

    Probability Distributions

    Distributions in MATLAB

    Continuous Distributions

    Discrete Distributions

    Probability Distribution Objects

    Other Distributions

    Examples of Probability Distributions in MATLAB

    disttool for Exploring Probability Distributions

    Parameter Estimation

    Command Line Functions

    Examples of Parameter Estimation

    difittool for Interactive Fitting

    Generating Random Numbers

    Generating Random Variables in Base MATLAB

    Generating Random Variables in the Statistics Toolbox

    Examples of Random Number Generation

    randtool for Generating Random Variables

    Summary and Further Reading

    Hypothesis Testing

    Basic Concepts

    Hypothesis Testing

    Confidence Intervals

    Common Hypothesis Tests

    The z–test and t–test

    Examples of Hypothesis Tests

    Confidence Intervals using Bootstrap Resampling

    The Basic Bootstrap

    Examples

    Analysis of Variance

    One–Way ANOVA

    ANOVA Example

    Summary and Further Reading

    Model–Building with Regression Analysis

    Introduction to Linear Models

    Specifying Models

    The Least Squares Approach for Estimation

    Assessing Model Estimates

    Model–Building Functions in Base MATLAB

    Fitting Polynomials

    Using the Division Operators

    Ordinary Least Squares

    Functions in the Statistics Toolbox

    Using regress for Regression Analysis

    Using regstats for Regression Analysis

    The Linear Regression Model Class

    Assessing Model Fit

    Basic Fitting GUI

    Summary and Further Reading

    Multivariate Analysis

    Principal Component Analysis

    Functions for PCA in Base MATLAB

    Functions for PCA in the Statistics Toolbox

    Biplots

    Multidimensional Scaling—MDS

    Measuring Distance

    Classical MDS

    Metric MDS

    Nonmetric MDS

    Visualization in Higher Dimensions

    Scatter Plot Matrix

    Parallel Coordinate Plots

    Andrews Curves

    Summary and Further Reading

    Classification and Clustering

    Supervised Learning or Classification

    Bayes Decision Theory

    Discriminant Analysis

    Naive Bayes Classifiers

    Nearest Neighbor Classifier

    Unsupervised Learning or Cluster Analysis

    Hierarchical Clustering

    K–Means Clustering

    Summary and Further Reading

    References

    Index of MATLAB Functions

    Subject Index

    Biography

    Wendy L. Martinez is a mathematical statistician with the Bureau of Labor Statistics in Washington, District of Columbia, USA. She has co-authored two additional successful Chapman Hall/CRC books on MATLAB and statistics, and has been using MATLAB for more than 15 years to solve problems and conduct research in statistics and engineering.

    MoonJung Cho is a mathematical statistician with the Bureau of Labor Statistics in Washington, District of Columbia, USA. She has more than10 years of experience in survey methodology research and applications, and is knowledgeable of other software packages, such as SAS and R. She is able to use this knowledge to enhance the utility of this book to users of other statistical software packages.

    "The book provides an introductory but comprehensive guide for performing data analysis in MATLAB. It not only covers the most important topics in basic statistics (along with some machine learning techniques), but also touches upon more advanced methods such as kernel density estimation, bootstrap, and principal component analysis…Most of the theories are conveyed in a concise and intuitive way, yet the explanations are quite effective. The implementation of each method in MATLAB is demonstrated using real examples. Detailed MATLAB codes and corresponding numerical and figure outputs are presented with informative MATLAB comments, which makes them easily understood even without the context. The book can be used as a good complementary book to introductory statistics courses…The book can also serve as a perfect guide for self-learners who are not familiar with MATLAB but wish to use MATLAB as a data analysis tool."
    —The American Statistician