Data Analysis with SPSS A First Course in Applied Statistics Fourth Edition Stephen Sweet Ithaca College Karen Grace-Martin The Analysis Factor Allyn & Bacon Boston Columbus Indianapolis New York San Francisco Upper Saddle River Amsterdam Cape Town Dubai London Madrid Milan Munich Paris Montreal Toronto Delhi Mexico City Sao Paulo Sydney Hong Kong Seoul Singapore Taipei Tokyo
Preface Acknowledgements About the Authors Dedication vii viii ix ix Chapter 1 Key Concepts in Social Science Research 1 Overview 1 Why Do We Need Statistics? 1 Framing Topics into Research Questions 2 Theories and Hypotheses 5 Population and Samples 6 Relationships and Causality 7 Association 8 Time Order 8 Nonspuriousness 8 Data Sets 9 Parts of a Data Set 10 Reliability and Validity 11 Summary 11 Key Terms 12 Exercises 13 Chapter 2 Getting Started: Accessing, Examining, and Saving Data 23 Overview 23 The Layout of SPSS 23 Types of Variables 26 String Variables 26 Categorical Variables 26 Scale Variables 26 Initial Settings 27 Defining and Saving a New Data Set 28 Managing Data Sets: Dropping and Adding Variables, Merging Data Sets 33 Dropping and Adding Variables 33 Merging and Importing Files 34 Loading and Examining an Existing File 35 Summary 37 Key Terms 37 Exercises 39 Chapter 3 Univariate Analysis: Descriptive Statistics 45 Overview 45 Why Do Researchers Perform Univariate Analysis? 45 Exploring Distributions of Scale Variables 46 Listing, Summarizing, and Sorting Observations 46 Histograms 49 Shapes of Distributions 52 Measures of Central Tendency 53 Measures of Spread 56
iv Box Plots 58 Exploring Distributions of Categorical Variables 60 Pie Charts 62 Bar Charts 66 Summary 67 Key Terms 68 Exercises 69 Chapter 4 Constructing Variables 77 Overview 77 Why Construct New Variables From Existing Data? 77 Recoding Existing Variables 77 Computing New Variables 82 Recording Computations Using Syntax 84 Minimizing Missing Values in Computing New Variables 87 Summary 91 Key Terms 92 Exercises 93 Chapter 5 Assessing Association through Bivariate Analysis 105 Overview 105 Why Do We Need Significance Tests? 105 Hypotheses and Significance Tests 107 Significance Levels 108 Sample Sizes, Magnitudes of Effect and Significance. Levels 109 Analyzing Bivariate Relationships Between Two Categorical Variables 110 Cross Tabulations 110 Bar Charts 114 Analyzing Bivariate Relationships Between Two Scale Variables 116 Correlations 116 Scatterplots 120 Summary 124 Key Terms 124 Exercises 125 Chapter 6 Comparing Group Means through Bivariate Analysis 135 Overview 135 One-Way Analysis of Variance 135 Post-hoc Tests 137 Assumptions ofanova 139 Independence Assumption 139 Normality Assumption 140 Equal Variance Assumption 142 Graphing the Results of ANOVA 142 Bar Charts 142 Box Plots 144 T tests 146 Independent Samples T Test 146 Paired-Samples T Test 147 Summary 149 Key Terms 149
When Contents v Exercises 151 Chapter 7 Modeling Relationships of Multiple Variables with Linear Regression 161 Overview 161 The Advantages of Modeling Relationships in Multiple Regression 161 Putting Theory First - to Pursue Linear Regression 163 Linear Regression: A Bivariate Example 164 Interpreting The ANOVA F-test 165 Interpreting Linear Regression Coefficients 166 Interpreting the R-Square Statistic 166 Putting the Statistics Together 167 Using Linear Regression Coefficients to Make Predictions 167 Using Coefficients to Graph Bivariate Regression Lines 168 Multiple Linear Regression 171 Interpreting Multiple Linear Regression Coefficients 173 Graphing a Multiple Regression 174 Other Concerns In Applying Linear Regression 176 Residuals 176 Constant Variation 177 Normality of Residuals 178 Building Multiple Variable Models 179 Degrees of Freedom 179 Collinearity 179 Dummy Variables 180 Outliers 181 Causality 181 Summary 182 Key Terms 182 Exercises 183 Chapter 8 Logistic Regression 189 Overview 189 What Is Logistic Regression? 189 When Can I Use a Logistic Regression? 190 Understanding Relationships through Probabilities 191 Logistic Regression: A Bivariate Example 192 Interpreting Odds Ratios and Logistic Regression Coefficients 193 Using Logistic Regression Coefficients to Make Predictions 194 Using Coefficients to Graph a Logistic Regression Line 195 Model Chi-Squares and Goodness of Fit 198 Multiple Variable Logistic Regression: An Example 198 Interpreting Logistic Regression Output 200 Using Multiple Variable Logistic Regression Coefficients to Make Predictions 201 Using Multiple Variable Coefficients to Graph a Logistic Regression Line 202 Summary 204 Key Terms 204 Exercises 205
vi Chapter 9 Writing a Research Report 213 Overview 213 Writing Style and Audience 213 The Structure of a Report 214 The Title 215 The Abstract 215 The Introduction 217 The Literature Review 218 The Methods 218 The Findings 219 The Conclusion 221 The References 222 Summary 222 Key Terms 222 Exercises 223 Chapter 10 Research Projects 225 Potential Research Projects 225 Research Project 1: Racism 227 Research Project 2: Suicide 228 Research Project 3: Criminality 229 Research Project 4: Welfare and Other Public Aid Consumption 230 Research Project 5: Sexual Behavior 231 Research Project 6: Education 232 Research Project 7: Health 233 Research Project 8: Happiness 234 Research Project 9: Your Topic 235 Appendix 1: STATES 10 Descriptives 237 Appendix 2: GSS08 File Information 242 Appendix 3: GSS08 Question Phrasing 267 Appendix 4: Variable Label Abbreviations 273 Permissions 273 References and Further Reading 274 Index 276