Differential misclassification arising from nondifferential errors in exposure measurement

Division of Health Examination Statistics, Centers for Disease Control, Hyattsville, MD.
American Journal of Epidemiology (Impact Factor: 4.98). 12/1991; 134(10):1233-44.
Source: PubMed

ABSTRACT Misclassification into exposure categories formed from a continuous variable arises from measurement error in the continuous variable. Examples and mathematical results are presented to show that if the measurement error is nondifferential (independent of disease status), the resulting misclassification will often be differential, even in cohort studies. The degree and direction of differential misclassification vary with the exposure distribution, the category definitions, the measurement error distribution, and the exposure-disease relation. Failure to recognize the likelihood of differential misclassification may lead to incorrect conclusions about the effects of measurement error on estimates of relative risk when categories are formed from continuous variables, such as dietary intake. Simulations were used to examine some effects of nondifferential measurement error. Under the conditions used, nondifferential measurement error reduced relative risk estimates, but not to the degree predicted by the assumption of nondifferential misclassification. When relative risk estimates were corrected using methods appropriate for nondifferential misclassification, the "corrected" relative risks were almost always higher than the true relative risks, sometimes considerably higher. The greater the measurement error, the more inaccurate was the correction. The effects of exposure measurement errors need more critical evaluation.

Download full-text


Available from: Katherine Mayhew Flegal, Jan 03, 2014
1 Follower
  • Source
    • "Exposure measurement error can lead to exposure misclassification when exposure surrogates for individual participants are classified into categories for analysis. Differential misclassification can arise in categorical exposure metrics even when there is nondifferential error (i.e., independent of disease status) in an exposure variable that is measured on a continuous scale (Flegal et al. 1991). In order for epidemiologic studies to be evaluated and utilized appropriately in risk assessment, it is important that exposure measurement error is characterized and evaluated thoroughly with consideration of the magnitude and direction of any potential exposure misclassification bias (for example, see Bergen et al. 2013). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Background: There is a recognized need to improve the application of epidemiologic data in human health risk assessment especially for understanding and characterizing risks from environmental and occupational exposures. Although there is uncertainty associated with the results of most epidemiologic studies, techniques exist to characterize uncertainty that can be applied to improve weight-of-evidence evaluations and risk characterization efforts. Methods: This report derives from a Health and Environmental Sciences Institute (HESI) workshop held in Research Triangle Park, North Carolina, to discuss the utility of using epidemiologic data in risk assessments, including the use of advanced analytic methods to address sources of uncertainty. Epidemiologists, toxicologists, and risk assessors from academia, government, and industry convened to discuss uncertainty, exposure assessment, and application of analytic methods to address these challenges. Synthesis: Several recommendations emerged to help improve the utility of epidemiologic data in risk assessment. For example, improved characterization of uncertainty is needed to allow risk assessors to quantitatively assess potential sources of bias. Data are needed to facilitate this quantitative analysis, and interdisciplinary approaches will help ensure that sufficient information is collected for a thorough uncertainty evaluation. Advanced analytic methods and tools such as directed acyclic graphs (DAGs) and Bayesian statistical techniques can provide important insights and support interpretation of epidemiologic data. Conclusions: The discussions and recommendations from this workshop demonstrate that there are practical steps that the scientific community can adopt to strengthen epidemiologic data for decision making. Citation: Burns CJ, Wright JM, Pierson JB, Bateson TF, Burstyn I, Goldstein DA, Klaunig JE, Luben TJ, Mihlan G, Ritter L, Schnatter AR, Symons JM, Yi KD. 2014. Evaluating uncertainty to strengthen epidemiologic data for use in human health risk assessments. Environ Health Perspect 122:1160–1165;
    Environmental Health Perspectives 07/2014; 122(11). DOI:10.1289/ehp.1308062 · 7.03 Impact Factor
  • Source
    • "I kohortestudier vil dette problemet vaere betraktelig mindre, da man vil samle inn data om eksponering før responsvariabelen registreres . Man skal imidlertid vaere klar over at man kan innføre differensiell målefeil ved å kategorisere en kontinuerlig forklaringsvariabel målt med ikkedifferensiell feil (Flegal et al. 1991). Vi vil i denne artikkelen konsentrere oss om situasjoner med ikkedifferensielle målefeil. "
  • Source
    • "For each variable, we compared the observed mean urinary creatinine level with the expected mean value for persons in the interviewed sample after we adjusted for that variable. The comparison assumed no statistical significance from differential nonresponse if the estimates were within 10% of the expected means (Flegal et al. 1991). We did not detect bias resulting from differential nonresponse for any of the previously listed variables. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Biologic monitoring (i.e., biomonitoring) is used to assess human exposures to environmental and workplace chemicals. Urinary biomonitoring data typically are adjusted to a constant creatinine concentration to correct for variable dilutions among spot samples. Traditionally, this approach has been used in population groups without much diversity. The inclusion of multiple demographic groups in studies using biomonitoring for exposure assessment has increased the variability in the urinary creatinine levels in these study populations. Our objectives were to document the normal range of urinary creatinine concentrations among various demographic groups, evaluate the impact that variations in creatinine concentrations can have on classifying exposure status of individuals in epidemiologic studies, and recommend an approach using multiple regression to adjust for variations in creatinine in multivariate analyses. We performed a weighted multivariate analysis of urinary creatinine concentrations in 22,245 participants of the Third National Health and Nutrition Examination Survey (1988-1994) and established reference ranges (10th-90th percentiles) for each demographic and age category. Significant predictors of urinary creatinine concentration included age group, sex, race/ethnicity, body mass index, and fat-free mass. Time of day that urine samples were collected made a small but statistically significant difference in creatinine concentrations. For an individual, the creatinine-adjusted concentration of an analyte should be compared with a "reference" range derived from persons in a similar demographic group (e.g., children with children, adults with adults). For multiple regression analysis of population groups, we recommend that the analyte concentration (unadjusted for creatinine) should be included in the analysis with urinary creatinine added as a separate independent variable. This approach allows the urinary analyte concentration to be appropriately adjusted for urinary creatinine and the statistical significance of other variables in the model to be independent of effects of creatinine concentration.
    Environmental Health Perspectives 03/2005; 113(2):192-200. DOI:10.1289/ehp.7337 · 7.03 Impact Factor
Show more