Counterfactuals and Causal Inference: Methods and Principles for Social Research

Analytical Methods for Social Research

by Stephen L. Morgan, Christopher Winship

In this second edition of Counterfactuals and Causal Inference, completely revised and expanded, the essential features of the counterfactual approach to observational data analysis are presented with examples from the social, demographic, and health sciences. Alternative estimation techniques are first introduced using both the potential outcome model and causal graphs; after which, conditioning techniques, such as matching and regression, are presented from a potential outcomes perspective. For research scenarios in which important determinants of causal exposure are unobserved, alternative techniques, such as instrumental variable estimators, longitudinal methods, and estimation via causal mechanisms, are then presented. The importance of causal effect heterogeneity is stressed throughout the book, and the need for deep causal explanation via mechanisms is discussed.

Genres: Sociology, Social Science, Economics, Mathematics, Reference, Philosophy, Technical

515 pages, Paperback

First published January 1, 2007

Reviews

[Holcombea · Rating 3 out of 5]

Caveat: I haven't gotten very far into this book - maybe only read 20% of it. It's been a bit bland, sort of an even-handed textbook approach perhaps without as clear a unifying framework as I was hoping for. Some of the writing of Judea Pearl is exciting; this isn't. I was also hoping for some descriptions of how well all these techniques have been turned out to get the causality right in the very few cases where experiments could ultimately be done. Young & Karr (2011) show what a failure the multiple linear regression approach has been for revealing causality in the case of nutrition. I have yet to see anything that grapples with that, but I'm completely outside the field, so there probably is plenty of stuff out there that I haven't come across.

[Görkem Saylam · Rating 5 out of 5]

Counterfactuals and Causal Inference | Stephen L. Morgan
Scoring Rubric
1: baseline
2: creative contextualization bcs of covering new analytical methods for social research
2: creative conceptualization bcs of new technical representation on causal inference
5: total points by 5

[Connor Oswald · Rating 4 out of 5]

took me long enough... Good stuff on IV, Weighted regression, matching and theory

[Seth Hunter · Rating 3 out of 5]

Strengths: multiple representations, PSM, IV

Words, graphs, tables, and equations are used to convey the potential outcomes framework as applied to matching and regression estimators - really liked here chapters.

Discussion of panel methods was rushed and some tabular examples weren't transparent enough.

Great as a digital edition because you can bounce between equations, text, footnotes, etc.

[Dennis · Rating 3 out of 5]

http://pro-libertate.net/20151123/281...

[Maikel · Rating 2 out of 5]

Decent introduction into causal analysis; treatment of time series and panel data methods could be expanded.