The Role of a Second Control Group in an Observational Study

An observational study is an attempt to estimate the effects of a treatment when subjects are not randomly assigned to treatment or control. The possibility of using more than one control group has often been briefly mentioned in general discussions of observational studies, and many obser- vational studies have used two control groups. Here, the limited and dispersed literature on this subject is reviewed, and the topic is developed in several directions by using a formal notation for observational studies. The value of a second control group depends on the supplementary infor- mation that is available about unobserved biases that are suspected to exist. A second control group provides a test of the assumption that conventional adjustments for observed covariates suffice in estimating treatment effects. Under the best of circumstances, this test is consistent and unbiased, and its power exceeds the probability of falsely detecting a treatment effect. Indeed, under the best of circumstances, two control groups can yield consistent and unbiased estimates of bounds on the treatment effect when conventional adjustments fail. In contrast, however, in the worst of circum- stances, a second control group can be of little value.

[1]  Paul W. Holland,et al.  WHICH COMES FIRST, CAUSE OR EFFECT? , 1987 .

[2]  P. Rosenbaum.  Sensitivity analysis for certain permutation inferences in matched observational studies , 1987 .

[3]  P. Rosenbaum.  Dropping out of High School in the United States: An Observational Study , 1986 .

[4]  P. Holland.  Statistics and Causal Inference , 1985 .

[5]  D. Rubin,et al.  The Bias Due to Incomplete Matching , 1985 .

[6]  P. Rosenbaum.  The Consequences of Adjustment for a Concomitant Variable that Has Been Affected by the Treatment , 1984 .

[7]  P. Rosenbaum.  Conditional Permutation Tests and the Propensity Score in Observational Studies , 1984 .

[8]  P. Rosenbaum.  From Association to Causation in Observational Studies: The Role of Tests of Strongly Ignorable Treatment Assignment , 1984 .

[9]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[10]  D. Rubin,et al.  Assessing Sensitivity to an Unobserved Binary Covariate in an Observational Study with Binary Outcome , 1983 .

[11]  D. Rubin,et al.  ON LORD'S PARADOX , 1982 .

[12]  D. Basu,et al.  Randomization Analysis of Experimental Data: The Fisher Randomization Test Rejoinder , 1980 .

[13]  D. Basu.  Randomization Analysis of Experimental Data: The Fisher Randomization Test , 1980 .

[14]  Donald B. Rubin,et al.  Causal Inference in Prospective and Retrospective Studies. , 1980 .

[15]  Lilienfeld Am,et al.  Foundations of epidemiology. 2nd ed. , 1980 .

[16]  N. Breslow,et al.  The analysis of case-control studies , 1980 .

[17]  A. Dawid.  Conditional Independence in Statistical Theory , 1979 .

[18]  P. Cole,et al.  The evolving case-control study. , 1979, Journal of chronic diseases.

[19]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[20]  K. Yuen,et al.  Sunlight and cataract: an epidemiologic investigation. , 1977, American journal of epidemiology.

[21]  D. Rubin.  Assignment to Treatment Group on the Basis of a Covariate , 1976 .

[22]  F. Li,et al.  Hodgkin's Disease, tonsillectomy and family size. , 1975, The New England journal of medicine.

[23]  D. Rubin.  Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[24]  W. G. Cochran,et al.  Controlling Bias in Observational Studies: A Review. , 1974 .

[25]  N. Mantel.  Synthetic retrospective studies and related topics. , 1973, Biometrics.

[26]  B. Macmahon,et al.  Epidemiology: Principles and Methods , 1970 .

[27]  Michail Prodan,et al.  CHAPTER 17 – THE PLANNING OF EXPERIMENTS , 1968 .

[28]  I. Bross,et al.  Pertinency of an extraneous variable. , 1967, Journal of chronic diseases.

[29]  E. Lehmann.  Some Concepts of Dependence , 1966 .

[30]  I. Bross.  Spurious effects from an extraneous variable. , 1966, Journal of chronic diseases.

[31]  R Doll,et al.  Mortality of British doctors in relation to smoking: observations on coronary thrombosis. , 1966, National Cancer Institute monograph.

[32]  M. Bitterman.  PHYLETIC DIFFERENCES IN LEARNING. , 1965, The American psychologist.

[33]  M. W. Birch.  The Detection of Partial Association, I: The 2 × 2 Case , 1964 .

[34]  Education Welfare.,et al.  Smoking and Health. Report of the Advisory Committee to the Surgeon General of the Public Health Service. , 1964 .

[35]  W. G. Cochran.  METHODOLOGICAL PROBLEMS IN THE STUDY OF HUMAN POPULATIONS , 1963, Annals of the New York Academy of Sciences.

[36]  D. Campbell,et al.  EXPERIMENTAL AND QUASI-EXPERIMENT Al DESIGNS FOR RESEARCH , 2012 .

[37]  J. Yerushalmy,et al.  On the methodology of investigations of etiologic factors in chronic diseases. , 1959, Journal of chronic diseases.

[38]  E. C. Hammond,et al.  Smoking and lung cancer: recent evidence and a discussion of some questions. , 1959, Journal of the National Cancer Institute.

[39]  R. Doll,et al.  Study of the Aetiology of Carcinoma of the Lung , 1952, British medical journal.

[40]  Oscar Kempthorne,et al.  The Design and Analysis of Experiments , 1952 .

[41]  J. Cornfield,et al.  A method of estimating comparative rates from clinical data; applications to cancer of the lung, breast, and cervix. , 1951, Journal of the National Cancer Institute.

[42]  B. L. Welch.  ON THE z-TEST IN RANDOMIZED BLOCKS AND LATIN SQUARES , 1937 .

[43]  R Fisher,et al.  Design of Experiments , 1936 .

[44]  M. Kendall,et al.  The Logic of Scientific Discovery. , 1959 .