Epidemiologists frequently encounter large errors of measurement in risk factors under study. Recently, there has been a proliferation of methods for treating measurement error in the types of nonlinear regression models commonly used by epidemiologists, most notably in regression models for binary outcomes. However, these methods have not made their way into standard practice, because (a) they are often not appropriate for commonly encountered study designs, (b) the proper use and interpretation of the methods requires a detailed understanding of the statistical literature on measurement errors, and a few examples exist of practical applications, and (c) the use of some of the methods requires novel software and time-consuming calculations. The work proposed in this grant will address each of these three obstacles. New and existing measurement-error methods will be applied to epidemiologic data on cancer and respiratory disease. The primary sources of data will be the Nurses' Health Study, a study of diet and cancer in which a cohort of approximately 100,000 nurses has been followed for 12 years, and the Six Cities Study of Air Pollution and Health, in which approximately 8000 children nd 6000 adults have been followed for 14 years. These two studies have allocated significant resources to the task of documenting and assessing the extent of measurement errors in the risk factors under study. The resulting """"""""validation"""""""" data will provide the information necessary for the application of the proposed measurement error methods. The two studies present a unique blend of methodologic issues, including binary outcomes, failure time data, repeated binary outcomes, measured longitudinal data, complex strategies for exposure assessment, and statistical design problems. When published, the analyses will provide other investigators with sound examples of the use of these techniques. An important benefit of this applied research will be the development of useful computer software. Research will also be initiated concerning methodologic issues of importance in a variety of other epidemiologic areas, and of fundamental theoretical interest. However, issues from cancer and respiratory epidemiology are emphasized. The primary goal of this grant is to develop methods suitable for the types of studies and data most frequently encountered by investigators in these fields.
| Aschard, Hugues; Spiegelman, Donna; Laville, Vincent et al. (2018) A test for gene-environment interaction in the presence of measurement error in the environmental variable. Genet Epidemiol 42:250-264 |
| Kim, Sehee; Li, Yi; Spiegelman, Donna (2016) A semiparametric copula method for Cox models with covariate measurement error. Lifetime Data Anal 22:1-16 |
| Khudyakov, Polyna; Gorfine, Malka; Zucker, David et al. (2015) The impact of covariate measurement error on risk prediction. Stat Med 34:2353-67 |
| Rosner, Bernard; Tworoger, Shelley; Qiu, Weiliang (2015) Correcting AUC for Measurement Error. J Biom Biostat 6: |
| Yi, Grace Y; Ma, Yanyuan; Spiegelman, Donna et al. (2015) Functional and Structural Methods with Mixed Measurement Error and Misclassification in Covariates. J Am Stat Assoc 110:681-696 |
| Rosner, Bernard; Hendrickson, Sara; Willett, Walter (2015) Optimal allocation of resources in a biomarker setting. Stat Med 34:297-306 |
| Wang, Molin; Liao, Xiaomei; Spiegelman, Donna (2013) Can efficiency be gained by correcting for misclassification? J Stat Plan Inference 143: |
| Zucker, David M; Gorfine, Malka; Li, Yi et al. (2013) A regularization corrected score method for nonlinear regression models with covariate error. Biometrics 69:80-90 |
| Liao, Xiaomei; Spiegelman, Donna; Carroll, Raymond J (2013) Regression calibration is valid when properly applied. Epidemiology 24:466-7 |
| Spiegelman, Donna; Logan, Roger; Grove, Douglas (2011) Regression calibration with heteroscedastic error variance. Int J Biostat 7:4 |
Showing the most recent 10 out of 51 publications
