Research methods in practice : strategies for description and causation / Dahlia K. Remler, Gregg G. Van Ryzin.

Includes bibliographical references and index.

Research in the real world -- Theory, models, and research questions -- Qualitative research -- Measurement -- Sampling -- Secondary data -- Surveys and other primary data -- Making sense of the numbers -- Making sense of inferential statistics -- Making sense of multivariate statistics -- Causation -- Observational studies -- Using regression to estimate causal effects -- Randomized experiments -- Natural and quasi experiments -- The politics, production, and ethics of research -- How to find, review, and present research.

"Authors Dahlia K. Remler and Gregg G. Van Ryzin are back with the third edition of their innovative, standard-setting text, Research Methods in Practice: Strategies for Description and Causation. Imbued with a deep commitment to making social and policy research methods accessible and meaningful, the third edition of this text motivates readers to examine the logic and limits of social science research from academic journals and government reports. A central theme of causation versus description runs through the text, with an emphasis on the idea that causal research is essential to understanding the original of social problems and their potential solutions. Readers will find excitement in the research experience as the best hope for improving the world in which we live, while also acknowledging the trade-offs and uncertainties in real-world research. The new edition of this text has been thoroughly updated to reflect changes in both research and methods. An entirely revamped chapter on secondary data expands to cover big data, including ethics, as well focusing more on the variety and challenges of using public and research data including data on COVID. The chapter on logic models now focuses on examples of community policing to demonstrate effectiveness. Survey coverage now includes a much greater focus on online surveys, with detailed examples of non-response bias using data from the 2016 and 2020 US presidential elections. The open access and open data movements, along with preregistration, now feature prominently in the politics of research"-- Provided by publisher.