What if there were no significance tests?

Description

This series was developed to encourage the use of rigorous methodology in the study of meaningful scientific issues, and to describe the applications in easy to understand language. The viewpoints span a range of perspectives, though the overriding theme is that significance testing may still be useful if supplemented with some or all of: Bayesian logic, caution, confidence intervals, effect sizes and power, other goodness of approximation measures, replication and meta-analysis, sound reasoning, and theory appraisal and corroboration. Rather than give definitive prescriptions, the chapters are largely suggestive of central issues, concerns, and application guidelines.  Read more... Abstract: A debate stimulated by a recent meeting of the Society of Multivariate Experimental Psychology resulted in the publication of this book. Rather than providing definitive prescriptions, the chapters are largely suggestive of general issues, concerns and application guidelines.  Read more... Content: Contributors -- Reviewers -- Acknowledgments -- Preface -- About the authors -- Overview. 1. Significance testing introduction and overview / Lisa L. Harlow -- The debate : against and for significance testing. 2. The earth is round (p&lt .05) / Jacob Cohen -- 3. Eight common but false objections to the discontinuation of significance testing in the analysis of research data / Frank L. Schmidt and John E. Hunter -- 4. There is a time and place for significance testing / Stanley A. Mulaik, Nambury S. Raju, and Richard A. Harshman -- 5. A retrospective on the significance test ban of 1999 (if there were no significance tests, they would be invented / Robert P. Abelson -- Suggested alternatives to significance testing. 6. Reforming significance testing via three-valued logic / Richard J. Harris -- 7. A case study in the failure of psychology as a cumulative science : the spontaneous recovery of verbal learning / Joseph S. Rossi -- 8. Goodness of approximation in the linear model / Roderick P. McDonald -- 9. Noncentrality interval estimation and the evaluation of statistical models / James H. Steiger and Rachel T. Fouladi -- 10. When confidence intervals should be used instead of statistical significance tests, and vice versa / Charles S. Reichardt and Harry F. Gollob -- A Bayesian perspective on hypothesis testing. 11. An introduction to Bayesian inference and its applications / Robert M. Pruzek -- 12. Testing 'small', not null, hypotheses : classical and Bayesian approaches / David M. Rindskopf -- Philosophy of science issues. 13. Good science is abductive, not hypothetico-deductive / William W. Rozeboom -- 14. The problem is epistemology, not statistics : replace significance tests by confidence intervals and quantify accuracy of risky numerical predictions / Paul E. Meehl -- Author index -- Subject index.