Categorical Statistics for Communication Research

Bryan E. Denham is Professor of Communication at Clemson University. An expert on logistic regression and log-linear modeling, he has published articles on teaching empirical research methods and applying categorical statistics to social data in outlets such as the Journal of Communication, Journalism & Mass Communication Quarterly, Journalism & Mass Communication Educator, and the Journal of Risk Research. He has taught empirical methods at both the graduate and undergraduate levels and has frequently served as a resource for both faculty and students in the use of categorical statistics from areas such as health, political, and science communication.

Detailed Contents ix Preface xiii Acknowledgments xix About the Companion Website xx 1. Introduction to Categorical Statistics 1 2. Univariate Goodness of Fit and Contingency Tables in Two Dimensions 12 3. Contingency Tables in Three Dimensions 41 4. Log -linear Analysis 58 5. Logit Log -linear Analysis 90 6. Binary Logistic Regression 119 7. Multinomial Logistic Regression 153 8. Ordinal Logistic Regression 171 9. Probit Analysis 198 10. Poisson and Negative Binomial Regression 216 11. Interrater Agreement Measures for Nominal and Ordinal Data 232 12. Concluding Communication 255 Appendix A: Chi ]Square Table 259 Appendix B: SPSS Code for Selected Procedures 261 Index 266