American Journal of Epidemiology Practice of Epidemiology Instrumental Variable Analysis for Estimation of Treatment Effects with Dichotomous Outcomes

Instrumental variable analyses are increasingly used in epidemiologic studies. For dichotomous exposures and outcomes, the typical 2-stage least squares approach produces risk difference estimates rather than relative risk estimates and is criticized for assuming normally distributed errors. Using 2 example drug safety studies evaluated in 3 cohorts from Pennsylvania (1994-2003) and British Columbia, Canada (1996-2004), the authors compared instrumental variable techniques that yield relative risk and risk difference estimates and that are appropriate for dichotomous exposures and outcomes. Methods considered include probit structural equation models, 2-stage logistic models, and generalized method of moments estimators. Employing these methods, in the first study the authors observed relative risks ranging from 0.41 to 0.58 and risk differences ranging from -1.41 per 100 to -1.28 per 100; in the second, they observed relative risks of 1.38-2.07 and risk differences of 7.53-8.94; and in the third, they observed relative risks of 1.45-1.59 and risk differences of 3.88-4.84. The 2-stage logistic models showed standard errors up to 40% larger than those of the instrumental variable probit model. Generalized method of moments estimation produced substantially the same results as the 2-stage logistic method. Few substantive differences among the methods were observed, despite their reliance on distinct assumptions.

[1]  M Alan Brookhart,et al.  Evaluating Short-Term Drug Effects Using a Physician-Specific Prescribing Preference as an Instrumental Variable , 2006, Epidemiology.

[2]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[3]  J. Avorn,et al.  Risk of death in elderly users of conventional vs. atypical antipsychotic medications. , 2005, The New England journal of medicine.

[4]  B J McNeil,et al.  Does more intensive treatment of acute myocardial infarction in the elderly reduce mortality? Analysis using instrumental variables. , 1994, JAMA.

[5]  J. Mullahy Instrumental-Variable Estimation of Count Data Models: Applications to Models of Cigarette Smoking Behavior , 1997, Review of Economics and Statistics.

[6]  W A Ray,et al.  Antipsychotics and the risk of sudden cardiac death. , 2001, Archives of general psychiatry.

[7]  J. Pearl Causality: Models, Reasoning and Inference , 2000 .

[8]  W. Greene,et al.  计量经济分析 = Econometric analysis , 2009 .

[9]  Semiparametric Estimation of Instrumental Variable Models for Causal Effects , 2000 .

[10]  M. Laan,et al.  Estimating Causal Parameters in Marginal Structural Models with Unmeasured Confounders Using Instrumental Variables , 2002 .

[11]  C. Salzman Clinical geriatric psychopharmacology , 1984 .

[12]  Didelez,et al.  Mendelian randomisation and instrumental variables: What can and what can't be done. , 2005 .

[13]  Donna Spiegelman,et al.  Easy SAS calculations for risk or prevalence ratios and differences. , 2005, American journal of epidemiology.

[14]  Els Goetghebeur,et al.  Structural mean models for compliance analysis in randomized clinical trials and the impact of errors on measures of exposure , 2005, Statistical methods in medical research.

[15]  B. Kuehn FDA warns antipsychotic drugs may be risky for elderly. , 2005, JAMA.

[16]  J. Robins,et al.  Instruments for Causal Inference: An Epidemiologist's Dream? , 2006, Epidemiology.

[17]  J. Angrist,et al.  Estimation of Limited Dependent Variable Models With Dummy Endogenous Regressors , 2001 .

[18]  T. Amemiya QUALITATIVE RESPONSE MODELS: A SURVEY , 1981 .

[19]  B Rosner,et al.  Correction of logistic regression relative risk estimates and confidence intervals for measurement error: the case of multiple covariates measured with error. , 1990, American journal of epidemiology.

[20]  Jeffrey M. Wooldridge,et al.  Introductory Econometrics: A Modern Approach , 1999 .

[21]  Alan Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[22]  M Alan Brookhart,et al.  Simultaneous assessment of short-term gastrointestinal benefits and cardiovascular risks of selective cyclooxygenase 2 inhibitors and nonselective nonsteroidal antiinflammatory drugs: an instrumental variable analysis. , 2006, Arthritis and rheumatism.

[23]  Joshua D. Angrist,et al.  Identification of Causal Effects Using Instrumental Variables , 1993 .

[24]  J. Robins Correcting for non-compliance in randomized trials using structural nested mean models , 1994 .

[25]  Elliott S Fisher,et al.  Analysis of observational studies in the presence of treatment selection bias: effects of invasive cardiac management on AMI survival using propensity score and instrumental variable methods. , 2007, JAMA.

[26]  E. Michael Foster,et al.  Instrumental Variables for Logistic Regression: An Illustration ☆ ☆☆ ★ , 1997 .

[27]  D. Ruppert,et al.  Measurement Error in Nonlinear Models , 1995 .

[28]  P Gustafson,et al.  Use of instrumental variables in the analysis of generalized linear models in the presence of unmeasured confounding with applications to epidemiological research , 2008, Statistics in medicine.

[29]  Peter E. Kennedy A Guide to Econometrics , 1979 .

[30]  Takeshi Amemiya,et al.  The nonlinear two-stage least-squares estimator , 1974 .

[31]  W. Ray,et al.  Evaluating medication effects outside of clinical trials: new-user designs. , 2003, American journal of epidemiology.

[32]  Sebastian Schneeweiss,et al.  Preference-Based Instrumental Variable Methods for the Estimation of Treatment Effects: Assessing Validity and Interpreting Results , 2007, The international journal of biostatistics.

[33]  R. Moffitt Estimations of Limited Dependent Variable Models with Dummy Endogenous Regressors: Simple Strategies for Empirical Practice: Comment , 2001 .