Confidence intervals for proportions and related measures of effect size / / Robert G. Newcombe

• Record Nr.: UNINA9910791703003321
• Autore: Newcombe Robert G.
• Pubbl/distr/stampa: Boca Raton, Fla. : , : CRC Press, , 2013
• ISBN: 0-429-09261-X; 1-4398-1279-9
• Descrizione fisica: 1 online resource (463 p.)
• Collana: Chapman & Hall/CRC biostatistics series
• Disciplina: 610.72/7
• Soggetti: Biometry; Statistics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: A Chapman & Hall book.
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Front Cover; Contents; Preface; Acknowledgments; Author; Acronyms; Chapter 1 - Hypothesis Tests and Confidence Intervals; Chapter 2 - Means and Their Differences; Chapter 3 - Confidence Intervals for a Simple Binomial Proportion; Chapter 4 - Criteria for Optimality; Chapter 5 - Evaluation of Performance of Confidence Interval Methods; Chapter 6 - Intervals for the Poisson Parameter and the Substitution Approach; Chapter 7 - Difference between Independent Proportions and the Square-and-Add Approach; Chapter 8 - Difference between Proportions Based on Individually Paired Data; Chapter 9 - Methods for Triads of ProportionsChapter 10 - Relative Risk and Rate Ratio; Chapter 11 - The Odds Ratio and Logistic Regression; Chapter 12 - Screening and Diagnostic Tests; Chapter 13 - Widening the Applicability of Confidence Interval Methods: The Propagating Imprecision Approach; Chapter 14 - Several Applications of the MOVER and PropImp Approaches; Chapter 15 - Generalised Mann-Whitney Measure; Chapter 16 - Generalised Wilcoxon Measure; References; Appendix 1: Glossary of Some Statistical Terms; Appendix 2: Introduction to Logarithms and Exponentials; Back Cover
• Sommario/riassunto: Addressed primarily at researchers who have not been trained as statisticians, this book describes how to use appropriate methods to calculate confidence intervals to present research findings. It covers ; background issues, such as the link between hypothesis tests and confidence intervals and why it is usually preferable to report the latter. Chapters begin with the simplest cases of a mean or a proportion based on a single sample and then move on to more complex applications. Although the books illustrative examples are mainly health-related, the methods described can also be applied to research in a wide range of disciplines--Provided by publisher.