Statistical Hypothesis Testing in Context: Reproducibility, Inference, and Science

Fay and Brittain provide statistical hypothesis testing and confidence intervals, emphasizing their practical application and proper interpretation. They cover basic theory, develop tests for specific data types, and discuss essential methods for applications, including adjustments for multiple testing and non-inferiority tests. Examples and exercises support practical use with the R package asht.

Format: Hardback
Length: 450 pages
Publication date: 05 May 2022
Publisher: Cambridge University Press

Fay and Brittain delve into the realm of statistical hypothesis testing, encompassing the concepts of compatible confidence intervals. Their primary focus lies in the practical application and accurate interpretation of these tools. The authors aim to equip applied statisticians with an extensive array of techniques and guidance, enabling them to identify reasonable methodologies for virtually any problem and to adapt existing methods to tackle novel challenges.

After laying the foundational mathematical theory and scientific principles, the text proceeds to develop tests and confidence intervals tailored for specific types of data. It encompasses essential methods for real-world applications, such as general procedures for constructing tests (including likelihood ratio, bootstrap, permutation, testing from models), adjustments for multiple testing, clustering, stratification, causality, censoring, missing data, group sequential tests, and non-inferiority tests. Throughout the book, the authors introduce innovative methods of their own, such as melded confidence intervals for comparing two samples and confidence intervals associated with Wilcoxon-Mann-Whitney tests and Kaplan-Meier estimates.

To facilitate practical implementation, the authors provide ample examples, exercises, and the R package asht, which serves as a valuable resource for hands-on practice. This comprehensive guide empowers applied statisticians with the knowledge and skills necessary to effectively employ hypothesis testing and confidence intervals in their research endeavors, ultimately contributing to the advancement of statistical analysis and data interpretation.

Weight: 990g
Dimension: 183 x 260 x 34 (mm)
ISBN-13: 9781108423564