Accounting for Outcome Misclassification in Estimates of the Effect of Occupational Asbestos Exposure on Lung Cancer Death

Abstract

In studies of the health effects of asbestos, lung cancer death is subject to misclassification. We used modified maximum likelihood to explore the effects of outcome misclassification on the rate ratio of lung cancer death per 100 fiber-years per milliliter of cumulative asbestos exposure in a cohort study of textile workers in Charleston, South Carolina, followed from 1940 to 2001. The standard covariate-adjusted estimate of the rate ratio was 1.94 (95% confidence interval: 1.55, 2.44), and modified maximum likelihood produced similar results when we assumed that the specificity of outcome classification was 0.98. With sensitivity assumed to be 0.80 and specificity assumed to be 0.95, estimated rate ratios were further from the null and less precise (rate ratio = 2.17; 95% confidence interval: 1.59, 2.98). In the present context, standard estimates for the effect of asbestos on lung cancer death were similar to estimates accounting for the limited misclassification. However, sensitivity analysis using modified maximum likelihood was needed to verify the robustness of standard estimates, and this approach will provide unbiased estimates in settings with more misclassification. asbestos; bias; sensitivity and specificity Abbreviations: CI, confidence interval; ICD, International Classification of Diseases.

Bias in estimating the cross‐sectional smoking, alcohol, obesity and diabetes associations with moderate‐severe periodontitis in the Atherosclerosis Risk in Communities study: comparison of full versus partial‐mouth estimates

“…Likewise, a more stringent case definition cut-point set at severe periodontitis, which equates to decreasing sensitivity, also resulted in PRP estimates that were biased in terms of magnitude and direction for each of the PRPs we investigated. Given changes in specificities tend to have a much larger impact on effect estimates than changes in sensitivi-ties (Copeland et al 1977, Lyles et al 2011, Edwards et al 2014, the magnitude of bias that we observed were not so severe.…”

Misclassification in Administrative Claims Data: Quantifying the Impact on Treatment Effect Estimates

“…This method would be suitable for analyses in which follow-up time varies between individuals (for estimating rates rather than risks) and the hazard is approximately constant. Edwards et al 2014 provide sample SAS code for this method [51•]. …”

A Bayesian Approach to Account for Misclassification and Overdispersion in Count Data

“…In this section we introduce the model of interest using an example from Edwards et al [ 13 ]. To aid in the description, we build the model with increasing levels of complexity communicated through the language of directed graphical models, also called Bayesian networks.…”

“…In other words, accounting for misclassification with the two parameters of sensitivity and specificity overparameterizes the model in a way that demands to be addressed. Edwards et al [ 13 ] consider and known and provide a method to obtain the maximum likelihood estimators (MLEs) while Stamey et al [ 9 ] assume information about and exist not as point estimates but rather in the form of probability distributions with which one can perform a Bayesian analysis, i.e ., prior distributions. Here, we investigate both the fixed and unknown approaches via the Bayesian paradigm.…”

“…The model described above is the same one used in both Stamey et al [ 9 ] and Edwards et al [ 13 ] and does not allow for extra Poisson variability. If the sampling is done in clusters, or if there are repeated measures, a random effects model may be appropriate as an alternative to the fixed effects model already described.…”