1st Edition

Sequential Methods and Their Applications

    512 Pages
    by Chapman & Hall

    512 Pages
    by Chapman & Hall

    Interactively Run Simulations and Experiment with Real or Simulated Data to Make Sequential Analysis Come Alive

    Taking an accessible, nonmathematical approach to this field, Sequential Methods and Their Applications illustrates the efficiency of sequential methodologies when dealing with contemporary statistical challenges in many areas.

    The book first explores fixed sample size, sequential probability ratio, and nonparametric tests. It then presents numerous multistage estimation methods for fixed-width confidence interval as well as minimum and bounded risk problems. The book also describes multistage fixed-size confidence region methodologies, selection methodologies, and Bayesian estimation. Through diverse applications, each chapter provides valuable approaches for performing statistical experiments and facilitating real data analysis.

    Functional in a variety of statistical problems, the authors’ interactive computer programs show how the methodologies discussed can be implemented in data analysis. Each chapter offers examples of input, output, and their interpretations. Available online, the programs provide the option to save some parts of an output so readers can revisit computer-generated data for further examination with exploratory data analysis.

    Through this book and its computer programs, readers will better understand the methods of sequential analysis and be able to use them in real-world settings.

    Preface. Objectives, Coverage, and Hopes. Why Sequential? Sequential Probability Ratio Test. Sequential Tests for Composite Hypotheses. Sequential Nonparametric Tests. Estimation of the Mean of a Normal Population. Location Estimation: Negative Exponential Distribution. Point Estimation of the Mean of an Exponential Population. Fixed-Width Intervals from MLEs. Distribution-Free Methods in Estimation. Multivariate Normal Mean Vector Estimation. Estimation in a Linear Model. Estimating the Difference of Two Normal Means. Selecting the Best Normal Population. Sequential Bayesian Estimation. Selected Applications. Appendix. References. Index.


    Mukhopadhyay, Nitis; de Silva, Basil M.