Read more
Traditional approaches focused on significance tests have often been difficult for linguistics researchers to visualise.
Statistics in Corpus Linguistics Research: A New Approach breaks significance tests down for researchers in corpus linguistics and linguistic analysis, promoting a visual approach to understanding the performance of tests with real data, and demonstrating how to derive new confidence intervals and tests.
This fully-revised second edition includes a brand-new chapter describing a novel extended 'MOVER' method to derive accurate confidence intervals for numerous properties. With sample datasets and easy-to-read visuals, this book focuses on practical issues, such as how to:
¿ pose meaningful research questions in terms of choice and constraint;
¿ employ confidence intervals correctly (including in graph plots);
¿ select a significance test (and interpret its results);
¿ construct confidence intervals for functions of independent proportions;
¿ measure the size of the effect of one variable on another or the similarity between two distributions; and
¿ evaluate whether the results of two experiments significantly differ.
Appropriate for anyone from the student just beginning their career to the seasoned researcher, this book is both a practical overview and valuable resource.
A website with downloadable resources for the calculations in this book is published at https://corplingstats.wordpress.com/siclr.
List of contents
Preface Acknowledgments A Note on Terminology and Notation
PART 1: Motivations 1 What Might Corpora Tell Us About Language?
PART 2: Designing Experiments With Corpora 2 The Idea of Corpus Experiments 3 That Vexed Problem of Choice 4 Choice Versus Meaning 5 Balanced Samples and Imagined Populations
PART 3: Confidence Intervals and Significance Tests 6 Introducing Inferential Statistics 7 Plotting With Confidence 8 From Intervals to Tests 9 An Algebra of Intervals 10 Competition Between Choices Over Time 11 The Replication Crisis and the New Statistics 12 Choosing the Right Test
PART 4: Effect Sizes and Meta-Tests 13 The Size of an Effect 14 Meta- Tests for Comparing Tables of Results
PART 5: Statistical Solutions for Corpus Samples 15 Conducting Research With Imperfect Data 16 Adjusting Intervals for Random-Text Samples
PART 6: Concluding Remarks 17 Plotting the Wilson Distribution 18 In Conclusion Appendix A The Interval Equality Principle Appendix B Pseudo-Code for Computational Procedures Glossary References Index
About the author
Sean Wallis is Principal Research Fellow and Deputy Director of the Survey of English Usage at UCL.
