Intermediate Statistics: A Conceptual Course

Description

Intermediate Statistics: A Conceptual Course is a student-friendly text for advanced undergraduate and graduate courses. It begins with an introductory chapter that reviews descriptive and inferential statistics in plain language, avoiding extensive emphasis on complex formulas. The remainder of the text covers 13 different statistical topics ranging from descriptive statistics to advanced multiple regression analysis and path analysis. Each chapter contains a description of the logic of each set of statistical tests or procedures and then introduces students to a series of data sets using SPSS, with screen captures and detailed step-by-step instructions. Students acquire an appreciation of the logic of descriptive and inferential statistics, and an understanding of which techniques are best suited to which kinds of data or research questions. Dedication Title Copyright Brief Contents Detailed Contents Preface Acknowledgments About the Author Chapter 1: A Review of Basic Statistical Concepts Introduction How Numbers and Language Revolutionized Human History Descriptive Statistics Central Tendency and Dispersion The Shape of Distributions Inferential Statistics Probability Theory A Study of Cheating Things That Go Bump in the Light: Factors That Influence the Results of Significance Tests Alpha Levels and Type I and II Errors Effect Size and Significance Testing Measurement Error and Significance Testing Sample Size and Significance Testing Restriction of Range and Significance Testing The Changing State of the Art: Alternate Perspectives on Statistical Hypothesis Testing Estimates of Effect Size Meta-Analysis Summary Appendix 1.1: Some Common Statistical Tests and Their Uses Notes Chapter 2: Descriptive Statistics The Very Small Survey of Moderately Large Shoe Sizes Estimating Spending in the U.S. Population Missing Data and Variable Values Describing the Ethnic Diversity of U.S. States Descriptive Statistics in Public Opinion Polls Shape Matters: The Normal Distribution, Skewness, and Kurtosis Sometimes Shape Really Matters How Much Skewness or Kurtosis Is Too Much (or Too Little)? Correcting for Skewness and Kurtosis For Further Thought Chapter 3: Linear and Curvilinear Correlation Introduction: A Brief Tribute to Karl Pearson A Hypothetical Study of How Unfair Life Is A Hypothetical Correlational Study of Afrocentrism A Study of Freedom of the Press and Perceived Corruption in Europe The Power of Impossible Outliers A Look at Brandeis’s Hypothesis Through a Curved Lens Appendix 3.1: A Primer for Predicting Scores on Y From Scores on X Chapter 4: Nonparametric Statistics (Tests Involving Nominal Variables) Introduction: The Correlation Coefficient’s Nominal Cousins A Pilot Study of Name-Letter Preferences A Second Pilot Study of Name-Letter Preferences The Chi-Square Statistic, Phi Coefficients, and Odds Ratios A Correlational Study of Interpersonal Attraction A Small Change of Pace: From Marriage to Mental Illness How to Report the Results of a Chi-Square Analysis of Nominal Variables Appendix 4.1: How to Report the Results of a Chi-Square Analysis Notes Chapter 5: Reliability (and a Little Bit of Factor Analysis) Chapter Overview Introduction: The Concept of Reliability “Just the Factors, Ma’am” Caveats Regarding Real Data Principal Components Analysis With Real Data Checking Out the Eigenvalues Reliability Analysis Adding Items Together to Make a Scale A Comparison of Cronbach’s Alpha and Split-Half Reliability Applying What You Learned to a Hypothetical Study of Self-Esteem A Return to Extraversion: Reliability Analysis as a Tool for Item Development Limitations of Cronbach’s Alpha Appendix 5.1: Why Psychological Scales Are More Reliable Than the Average of Their Imperfectly Reliable Components Appendix 5.2: Reporting the Results of a Factor Analysis and a Reliability Analysis Notes Chapter 6: Single-Sample and Two-Sample t Tests Introduction Bending the Rules About Happiness Simplifying the Outcome The Independent Samples (Two-Samples) t Test Results of the Teacher Expectancy Study More Simplification Yet Another Name-Letter Preference Study An Archival Study of Heat and Aggression A Blind Cola Taste Test Appendix 6.1: Reporting the Results of One-Sample and Two-Sample t Tests Appendix 6.2 Some Useful SPSS Syntax Statements and Logical Operands Appendix 6.3: Running a One-Sample Chi-Square Test in Older Versions of SPSS (SPSS 19 or Earlier) Chapter 7: One-Way and Factorial Analysis of Variance (ANOVA) Introduction: The Trouble With Levels Understanding One-Way ANOVAs by Experimenting With Alcohol Finding Meaning in Means: Using Contrasts Looking at More Than One Independent Variable: Factorial ANOVAs A Hypothetical Example of When and How “It Depends” More Practice Understanding Main Effects and Interactions Practice Study 1: A Lab Study of Aggression Among Kids Practice Study 2: A Lab Study of Self-Pay Three-Way ANOVAs and Beyond Putting It All Together Appendix 7.1: Results of a Unique Memory Study That Used Planned Contrasts Chapter 8: Within-Subjects and Mixed Model Analyses Introduction: Controlling for Individual Differences Some Bogus Within-Subjects Studies of Bogus Traits Examining Three Within-Subjects Versions of the Same Study Combining Between-Subjects and Within-Subjects Designs: Mixed Model Designs A Repeated Measures Study of Optimism With Countries as the Unit of Analysis A Mixed Model Study of Implicit Political Attitudes Appendix 8.1: Sample Results of a Study Using a Mixed Model Design Chapter 9: Multiple Regression Introduction: Ceteris Paribus Predictor Variables and Criterion Variables The Logic of Multiple Regression Analysis Considering More Data Checking Your Answers in SPSS Correlation, Multiple Regression, and Multiple Predictor Variables R-Square, Adjusted R-Square, and Standard Errors in Multiple Regression A Real-World Multiple Regression Application Logistic Regression: Multiple Regression Analysis With Categorical Criterion Variables Back to Missing Cookies Logistic Regression Analysis of Cookie Thefts: Disentangling Bart and Fred Understanding Odds Ratios in Logistic Regression Misunderstanding Odds Ratios in Logistic Regression Back to Missing Cookies Confidence Intervals in Logistic Regression It Sure Is Messy Out There: Multivariate Data Cleaning Appendix 9.1: Terms for Further Reading or Discussion Chapter 10: Examining Interactions in Multiple Regression Analysis Introduction: Type of Variable Determines Type of Analysis Moderators and Interactions in Multiple Regression A More Realistic Example: Centering and Simple Slopes Tests in Multiple Regression Analysis Beyond Median Splits: Isolating and Analyzing Subgroups in Multiple Regression Some Practice With Real Data More Real Practice Data Important Moderator Effects Sometimes Add Minimally to R-Square Values Examining Interactions Between Categorical and Continuous Predictors in Multiple Regression Why Does This Technique for Estimating Simple Slopes Work? It’s Not Easy Studying Green: Dealing With Interactions Involving Categorical Predictors With More Than Two Levels Appendix 10.1: Testing for and Interpreting Three-Way Interactions in Multiple Regression Appendix 10.2: An Example of How to Report the Results of a Two-Way Interaction in Multiple Regression Notes Chapter 11: ANCOVA, Covariate-Adjusted Means, and Predicted Scores Introduction: Ends to a Mean The Analysis of Covariance (ANCOVA) Data Set 1: Gender Differences in Income The Ghosts in the Machine: Generating Predicted Scores in a Multiple Regression Analysis Data Set 2: Political Party Affiliation and Attitudes Data Set 3: A Survey of Smoking and Well-Being Chapter 12: Suppressor Variables Introduction: Multiple Regression and Suppression Uncovering Causes: Attribution Theory and Suppression A Practice Example of Suppression: Running and Squatting Practice With Suppression: Three Data Sets to Analyze Data Set 1: Anagram Difficulty and Self-Pay Data Set 2: Predicting Voting Behavior Data Set 3: Predicting Homicide Rates From Country-Level Statistics A Cautionary Note Regarding Multicollinearity Coda: Why Suppression? Note Chapter 13: Mediation and Path Analysis Introduction: Disentangling Competing Causes Third Variables Versus Causal Starting Points Causal Plausibility Empirical Plausibility Moderation in All Things—Except for Mediation A Mediational Model of How Frustration Leads to Aggression Formal Testing for the Significance of Mediation Requires Knowledge of Standard Errors What Mediates the Association Between Self-Esteem and Relationship Satisfaction? Mediation Analysis as a Specific Case of Path Analysis The Logic of Path Analysis A Hypothetical Path Model Involving Positive Beliefs and Health For Further Reading Useful Web Pages Appendix 13.1: An Analysis of Teasing From Kruger, Gordon, and Kuban (2006) Notes Chapter 14: Data Cleaning Introduction: Data Cleaning Missing Data That’s Not Normal: Outliers Identifying and Dealing With Univariate Outliers Identifying and Dealing With Multivariate Outliers Putting Your Data-Cleaning Skills to Work A Final Worry: Multicollinearity For Further Reading Appendix 14.1: An Illustration of Multicollinearity Chapter 15: Data Merging and Data Management 387 Chapter 16: Avoiding Bias: Characterizing Without Capitalizing Introduction: Some Common Errors and Biases in Human Thinking Confirmatory Biases + Human Statisticians = Statistical Bias Phineas and Ferb Are Just the Tip of the Iceberg Four Simple Rules for Avoiding Bias in Data Analysis References Author Index Subject Index