2019/01/15 by Bas B. L. Penning de Vries, Maarten van Smeden, de Vries, Bas B. L. Penning +3
Economics, Econometrics and Finance · Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Health Systems, Economic Evaluations, Quality of Life #Methodology (stat.ME) #Statistical Methods in Epidemiology
paper · pdf · doi:10.48550/arxiv.1901.04795
openalex publication_date 2019/01/15 · openalex created_date 2022/07/30 · openalex updated_date 2026/07/28
Joint misclassification of exposure and outcome variables can lead to\nconsiderable bias in epidemiological studies of causal exposure-outcome\neffects. In this paper, we present a new maximum likelihood based estimator for\nthe marginal causal odd-ratio that simultaneously adjusts for confounding and\nseveral forms of joint misclassification of the exposure and outcome variables.\nThe proposed method relies on validation data for the construction of weights\nthat account for both sources of bias. The weighting estimator, which is an\nextension of the exposure misclassification weighting estimator proposed by\nGravel and Platt (Statistics in Medicine, 2018), is applied to reinfarction\ndata. Simulation studies were carried out to study its finite sample properties\nand compare it with methods that do not account for confounding or\nmisclassification. The new estimator showed favourable large sample properties\nin the simulations. Further research is needed to study the sensitivity of the\nproposed method and that of alternatives to violations of their assumptions.\nThe implementation of the estimator is facilitated by a new R function in an\nexisting R package.\n