Statistical Models and Causal Inference: A Dialogue with the Social Sciences

by David Freedman, David Collier (Editor), Philip B. Stark (Editor)

David A. Freedman presents here a definitive synthesis of his views on the foundations and limitations of statistical modeling in the social sciences, illustrating basic arguments with examples from political science, public policy, law, and epidemiology. He maintains that many new technical approaches to statistical modeling constitute not progress, but regress, and he shows why these methods are not reliable.

Genres: Mathematics, Nonfiction, Textbooks, Science, Social Science

416 pages, Paperback

First published November 30, 2009

Reviews

[Rich · Rating 2 out of 5]

Stick with Freedman's articles or his chapter in Brady and Collier's Rethinking Social Inquiry, this is basically a compendium of his previously published critiques of observational studies.

[Claus Andersen · Rating 5 out of 5]

Thought-provoking.