An Introduction to Causal Inference

Sociological Methods and Research - Tập 24 Số 3 - Trang 353-379 - 1996
Michael E. Sobel1
1University of Arizona

Tóm tắt

Sociologists routinely employ regression analysis and a variety of related statistical models to draw causal inferences from survey data. Typically, the parameters of the models are interpreted as effects that indicate the change in a dependent variable that would occur if one or more independent variables were set to values other than the values actually taken. The purpose of this article is to formally demonstrate, in a fashion accessible to the social researcher who is not a methodologist, why the interpretations above do not generally hold, even when the model is correctly specified and a causal theory is given. Some implications for the way in which social research is and should be conducted are discussed. In particular, the usual strategies for testing competing causal explanations are misdirected. Further, the emphasis on causation in contemporary sociology is often misdirected.

Từ khóa


Tài liệu tham khảo

10.1080/00048403808541382

Angrist, J. D., Journal of the American Statistical Association

10.2307/1909983

Blalock, H., Causal Inferences in Nonexperimental Research

Bunge, M., Causality and Modern Science, 3

Cliff, N., Mathematical and Theoretical Systems, 69

Collingwood, R. G., An Essay on Metaphysics

Cox, D. R., The Planning of Experiments

10.1086/224256

10.2307/1164888

Geweke, J., Handbook of Econometrics, 1101

10.1093/biomet/60.1.179

10.2307/1912791

Granger, C. W., 1980, Journal of Economic Dynamics and Control, 2, 329, 10.1016/0165-1889(80)90069-X

10.1080/01621459.1989.10478848

Holland, P. W., 1986, Journal of the American Statistical Association, 81, 945, 10.1080/01621459.1986.10478354

10.2307/271055

Holland, P. W., Multilevel Analysis of Educational Data, 311

Jöreskog, K. G., Applications of Statistics, 265

Mackie, J. L., The Cement of the Universe

Manski, C., 1990, American Economic Review Papers and Proceedings, 80, 319

McCullagh, P., Generalized Linear Models, 2

Mill, J. S., The Collected Works of John Stuart Mill

10.1016/0304-4076(88)90039-5

Reichenbach, H., The Direction of Time, 10.1063/1.3059791

10.1080/01621459.1984.10477060

10.1214/ss/1177013232

10.1093/biomet/70.1.41

10.1037/h0037350

10.2307/1164933

10.1214/aos/1176344064

10.2307/2287653

Simon, H. A., 1954, Journal of the American Statistical Association, 49, 467

Sims, C. A., New Methods in Business Cycle Research: Proceedings From a Conference, 23

10.2307/271082

10.2307/270723

10.1007/BF02294763

Sobel, M. E. 1993. “Causation, Spurious Correlation and Path Analysis: A Reexamination.” Unpublished manuscript.

Sobel, M. E., Selecting Models From Data, 183

Sobel, M. E., Analysis of Latent Variables in Developmental Research, 3

Sobel, M. E., Handbook for Statistical Modeling in the Social and Behavioral Sciences, 1

Sobel, M. E., Latent Variable Modeling with Application to Causality

Suppes, P., A Probabilistic Theory of Causality

Winer, B. J., Statistical Principles in Experimental Design, 2

Zellner, A., Basic Issues in Econometrics, 35

Thông tin
Thông tin xuất bản

Sociological Methods and Research

Tập 24 Số 3

353-379

Thông tin tác giả