Statistics for the social sciences : a general linear model approach

Written by a quantitative psychologist, this textbook explains complex statistics in accessible language to undergraduates in all branches of the social sciences. Built around the central framework of the General Linear Model (GLM), Statistics for the Social Sciences teaches students how different statistical methods are interrelated to one another. With the GLM as a basis, students with varying levels of background are better equipped to interpret statistics and learn more advanced methods in their later courses. Russell T. Warne makes statistics relevant to students' varying majors by using fascinating real-life examples from the social sciences. Students who use this book will benefit from clear explanations, warnings against common erroneous beliefs about statistics, and the latest developments in the philosophy, reporting and practice of statistics in the social sciences. The textbook is packed with helpful pedagogical features including learning goals, guided practice and reflection questions. Cover Half-title Title page Copyright information Dedication Table of contents Preface What Makes this Textbook Different For Students For Instructors Last Words Acknowledgements List of Examples 1 Statistics and Models Learning Goals Why Statistics Matters Two Branches of Statistics Models Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 2 Levels of Data Learning Goals Defining What to Measure Levels of Data So What? Other Ways to Classify Data Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 3 Visual Models Learning Goals Sample Data Frequency Tables Histograms Describing Shapes of Histograms Number of Peaks Describing Distribution Shapes: A Caveat Frequency Polygons Box Plot Bar Graphs Stem-and-Leaf Plots Line Graphs Pie Charts Scatterplots Selecting the Proper Visual Model Other Visual Models Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 4 Models of Central Tendency and Variability Learning Goals Models of Central Tendency Models of Variability Using Models of Central Tendency and Variance Together Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 5 Linear Transformations and z-Scores Learning Goals Linear Transformations z-Scores: A Special Linear Transformation Linear Transformations and Scales Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 6 Probability and the Central Limit Theorem Learning Goals Basic Probability The Logic of Inferential Statistics and the CLT Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 7 Null Hypothesis Statistical Significance Testing and z-Tests Learning Goals Null Hypothesis Statistical Significance Testing z-Test Cautions for Using NHSTs General Linear Model Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 8 One-Sample t-Tests Learning Goals Shortcomings of the z-Test – and a Solution Steps of a One-Sample t-Test The p-Value in a One-Sample t-Test Caveats for One-Sample t-Tests Confidence Intervals (CIs) Another Use of the One-Sample t-Tests Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 9 Paired-Samples t-Tests Learning Goals When to Use the Paired Two-Sample t-Test Steps of a Paired-Samples t-Test Finding p Old Concerns Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 10 Unpaired Two-Sample t-Tests Learning Goals Making Group Comparisons Steps of an Unpaired-Samples t-Test p and Type I and Type II errors Assumptions of the Unpaired Two-Sample t-Test Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 11 Analysis of Variance Learning Goals Comparing Means from Three or More Groups Problems with Multiple t-Tests Solutions to Problems of Multiple Comparisons ANOVA p and Type I and Type II Errors Additional Thoughts on ANOVA Post Hoc Tests Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 12 Correlation Learning Goals Purpose of the Correlation Coefficient Definition of a Correlation Calculating Pearson’s r Interpreting Pearson’s r Visualizing Correlations Pearson’s r in the Null Hypothesis Testing Context Warning: Correlation Is Not Causation Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 13 Regression Learning Goals Using Pearson’s r to Make Predictions The Regression Line Regression Towards the Mean Assumptions of Regression and Correlation Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 14 Chi-Squared Test Learning Goals Nominal Outcomes One-Variable Chi-Squared Test Two-Variable Chi-Squared Test Information About Odds Ratios Summary Reflection Questions: Comprehension Reflection Questions: Application Further Reading 15 Applying Statistics to Research, and Advanced Statistical Methods Learning Goals How to Choose a Statistical Method Multiple Regression and Related Procedures Nonparametric Statistics Multivariate Methods Reflection Questions: Comprehension Reflection Questions: Application Further Reading Appendix A1 z-Table Appendix A2 t-Table Appendix A3 F-Table Appendix A4 Q-table (Tukey’s Post Hoc Test) Appendix A5 Critical Values for r Appendix A6 .2-Table Glossary Answer Key References Name Index Subject Index "Written by a quantitative psychologist, this textbook explains complex statistics in accessible language to undergraduates in all branches of the social sciences. Built around the central framework of the General Linear Model (GLM), Statistics for the Social Sciences teaches students how different statistical methods are interrelated to one another. With the GLM as a basis, students with varying levels of background are better equipped to interpret statistics and learn more advanced methods in their later courses. Russell Warne makes statistics relevant to students' varying majors by using fascinating real-life examples from the social sciences. Students who use this book will benefit from clear explanations, warnings against common erroneous beliefs about statistics, and the latest developments in the philosophy, reporting and practice of statistics in the social sciences. The textbook is packed with helpful pedagogical features including learning goals, guided practice and reflection questions."-- Résumé de l'éditeur "Written by a quantitative psychologist, this textbook explains complex statistics in accessible language to undergraduates in all branches of the social sciences. Built around the central framework of the General Linear Model (GLM), Statistics for the Social Sciences teaches students how different statistical methods are interrelated to one another. With the GLM as a basis, students with varying levels of background are better equipped to interpret statistics and learn more advanced methods in their later courses. Russell Warne makes statistics relevant to students' varying majors by using fascinating real-life examples from the social sciences. Students who use this book will benefit from clear explanations, warnings against common erroneous beliefs about statistics, and the latest developments in the philosophy, reporting and practice of statistics in the social sciences. The textbook is packed with helpful pedagogical features including learning goals, guided practice and reflection questions"--Provided by publisher Machine generated contents note: Preface; Acknowledgements; List of examples; 1. Statistics and models; 2. Levels of data; 3. Visual models; 4. Central tendency and variability; 5. Linear transformations and z-scores; 6. Probability and CLT; 7. NHSST and z-tests; 8. One-sample t-tests; 9. Paired samples t-tests; 10. Unpaired two-sample t-tests; 11. Analysis of variance; 12. Correlation; 13. Regression; 14. Chi-squared test; 15. Advanced methods; Appendices; Glossary; Answer key; References; Index