Acknowledgments

This textbook draws on decades of pioneering work in political science, survey methodology, data journalism, and computational social science. We gratefully acknowledge the intellectual foundations laid by scholars and practitioners whose contributions appear throughout these pages.

We are indebted to the researchers who have shaped the field of political analytics: Philip Converse and the Michigan school of voting behavior; Warren Mitofsky and the development of modern exit polling; Andrew Gelman, whose work on multilevel regression and poststratification (MRP) transformed small-area estimation; Nate Silver, whose probabilistic approach to election forecasting brought statistical thinking to mass audiences; and the many scholars whose work on public opinion, political communication, and democratic theory informs every chapter.

We thank the organizations that make political data publicly available: the American National Election Studies (ANES), the Cooperative Election Study (CES), the Pew Research Center, the Federal Election Commission, ProPublica, and the many other institutions whose commitment to open data makes teaching — and accountability — possible.

The Python chapters benefited from the extraordinary open-source scientific computing ecosystem. We thank the developers and maintainers of NumPy, pandas, matplotlib, scikit-learn, NLTK, and the many other libraries that power modern political analytics.

We are grateful to colleagues who reviewed drafts, suggested improvements, and caught errors. Any remaining mistakes are, of course, our own.

Finally, we thank the students who will use this book. Your questions, your skepticism, and your commitment to understanding how data and democracy intersect give this project its purpose.