Impact of a Confounding Variable on a Regression Coefficient

Sociological Methods and Research - Tập 29 Số 2 - Trang 147-194 - 2000
Kenneth A. Frank1
1Michigan State University

Tóm tắt

Regression coefficients cannot be interpreted as causal if the relationship can be attributed to an alternate mechanism. One may control for the alternate cause through an experiment (e.g., with random assignment to treatment and control) or by measuring a corresponding confounding variable and including it in the model. Unfortunately, there are some circumstances under which it is not possible to measure or control for the potentially confounding variable. Under these circumstances, it is helpful to assess the robustness of a statistical inference to the inclusion of a potentially confounding variable. In this article, an index is derived for quantifying the impact of a confounding variable on the inference of a regression coefficient. The index is developed for the bivariate case and then generalized to the multivariate case, and the distribution of the index is discussed. The index also is compared with existing indexes and procedures. An example is presented for the relationship between socioeconomic background and educational attainment, and a reference distribution for the index is obtained. The potential for the index to inform causal inferences is discussed, as are extensions.

Từ khóa


Tài liệu tham khảo

10.1177/0049124198027002002

10.1111/j.1467-9280.1997.tb00536.x

Anderson, Sharon, Statistical Methods for Comparative Studies, 10.1002/9780470316498

10.1080/01621459.1996.10476902

10.1080/03610927808827610

Asher, H., Causal Modeling, 10.4135/9781412983600

10.1037/h0020412

Blalock, H. M., Jr., Causal Models in the Social Sciences

Blau, P. M., The American Occupational Structure

Bourdieu, P., Handbook of Theory and Research for the Sociology of Education, 241

Bowles, S., Schooling in Capitalist America

10.1016/0021-9681(66)90062-2

10.1016/0021-9681(67)90080-X

Bryk, Anthony S., Catholic Schools and the Common Good

10.17763/haer.48.3.t490261645281841

Chatterjee, Samprit, Sensitivity Analysis in Linear Regression

10.1037/0033-2909.103.1.105

10.3102/10769986017001051

10.2105/AJPH.43.6_Pt_1.684

10.2307/2344179

Cochran, W. G., “Performance of a Preliminary Test of Comparability in Observational Studies.”

10.1037/0003-066X.45.12.1304

10.1037/0003-066X.49.12.997

Cohen, J., Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences

Cohen, M.R., An Introduction to Logic and the Scientific Method

Cook, Thomas, Quasi-Experimentation: Design and Analysis Issues for Field Settings

10.1002/ev.1431

Cornfield, J., 1959, Journal of the National Cancer Institute, 22, 173

10.1037/1082-989X.2.2.161

Davis, W. A., Probability and Causality, 133

10.1214/ss/1177012894

10.1086/289662

Draper, N. R., Applied Regression Analysis

Duncan, Otis D., Socioeconomic Background and Achievement

Einhorn, Hillel J., 1986, Psychological Review, 99, 3

10.2307/2094254

10.1006/aama.1996.0501

10.1177/095935439992002

Gage, N. L., The Scientific Basis of the Art of Teaching

Giere, R., Applications of Inductive Logic, 251

Gigerenzer, G., A Handbook for the Data Analysis in the Behavioral Sciences: Methodological Issues, 311

Godfrey, L. G., Misspecification Tests in Econometrics

10.2307/1912791

10.1111/j.2044-8295.1998.tb02687.x

Hanushek, E., Statistical Methods for Social Scientists

Harlow, L. L., What If There Were No Significance Tests

10.1111/j.1467-9280.1997.tb00535.x

10.2307/1913827

Heckman, J., Longitudinal Analysis of Labor Market Data, 156

10.1080/01621459.1986.10478354

Holland, Paul W., Sociological Methodology, 449

Hunter, John E., 1997, American Psychological Society, 8, 3

10.2307/2112252

Kitcher, P., Minnesota Studies in the Philosophy of Science, vol. 13, Scientific Explanation, 410

Lareau, A., Home Advantage: Social Class and Parental Intervention in Elementary Education

Lewis, S., 1973, Journal of Philosophy, 70, 553, 10.2307/2025310

10.2307/2533848

MacIver, R. M., Social Causation

Mackie, J., The Cement of the Universe

10.1037/0033-2909.108.2.314

10.1207/s15327906mbr3201_1

McKinlay, Sonja M., 1975, Journal of the American Statistical Association, 70, 859, 10.1080/01621459.1975.10480314

10.1037/0022-006X.46.4.806

Meeker, W. Q., Selected Tables in Mathematical Statistics, 1

10.1080/03610919408813168

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

Montgomery, D. C., Introduction to Linear Regression Analysis

Morrison, D. E., The Significance Test Controversy

Oakes, M., Statistical Inference: A Commentary for the Social and Behavioral Sciences

Pedhazur, E., Multiple Regression in Behavioral Research: Explanation and Prediction, 2

Pollard, Paul, A Handbook for the Data Analysis in the Behavioral Sciences, Methodological Issues, 449

10.1016/0304-4076(88)90039-5

Ramsey, J., Frontiers in Econometrics, 13

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

Rice, J. A., Mathematical Statistics and Data Analysis

10.3102/10769986011003207

10.1093/biomet/70.1.41

10.1037/h0042040

10.1037/h0037350

Ryan, T. P., Modern Regression Methods

Salmon, Wesley, Scientific Explanation and the Causal Structure of the World

10.1086/289801

Salmon, Wesley, Causality and Explanation

10.1207/s15327906mbr3301_3

Schlesselman, J. J., 1978, American Journal of Epidemiology, 108, 3

10.1037/1082-989X.1.2.115

10.1086/227281

Snedecor, G. W., Statistical Methods, 6

Sobel, Michael E., Handbook of Statistical Modeling for the Social and Behavioral Sciences, 1

10.1177/0049124196024003004

10.1177/0049124198027002006

Sober, E., Probability and Causality, 211

Sohn, David, 1998, Theory & Psychology, 8, 291, 10.1177/0959354398083001

Steyer, Rolf, Latent Variables Analysis: Applications for Developmental Research, 36

Suppes, P., A Probabilistic Theory of Causality

10.1177/095935439992006

Tukey, J. W., Exploratory Data Analysis

10.1214/ss/1177011945

10.1037/1082-989X.4.2.212

Weisberg, Sanford, Applied Linear Regression

10.1037/0003-066X.54.8.594

Zellner, A., Basic Issues in Econometrics