Bias in the estimation of exposure effects with individual- or group-based exposure assessment

Abstract

In this paper, we develop models of bias in estimates of exposure-disease associations for epidemiological studies that use group-and individual-based exposure assessments. In a study that uses a group-based exposure assessment, individuals are grouped according to shared attributes, such as job title or work area, and assigned an exposure score, usually the mean of some concentration measurements made on samples drawn from the group. We considered bias in the estimation of exposure effects in the context of both linear and logistic regression disease models, and the classical measurement error in the exposure model. To understand group-based exposure assessment, we introduced a quasi-Berkson error structure that can be justified with a moderate number of exposure measurements from each group. In the quasi-Berkson error structure, the true value is equal to the observed one plus error, and the error is not independent of the observed value. The bias in estimates with individual-based assessment depends on all variance components in the exposure model and is smaller when the between-group and between-subject variances are large. In group-based exposure assessment, group means can be assumed to be either fixed or random effects. Regardless of this assumption, the behavior of estimates is similar: the estimates of regression coefficients were less attenuated with a large sample size used to estimate group means, when between-subject variability was small and the spread between group means was large. However, if groups are considered to be random effects, bias is present, even with large number of measurements from each group. This does not occur when group effects are treated as fixed. We illustrate these models in analyses of the associations between exposure to magnetic fields and cancer mortality among electric utility workers and respiratory symptoms due to carbon black.

The effect of the presence and characteristics of an outlying group on exposure–outcome associations

“…Thus, the mean exposures in the 19 groups were determined with differing levels of precision. Regression coefficients will be biased in a group-based approach if group mean exposures are imprecise, as shown in theoretical studies (18,19), but the size of this bias is difficult to assess on theoretical grounds in realistic study designs as the present one, where groups differ considerably in both size and exposure variability. Empirical simulation studies are an attractive alternative to analytical statistics in such cases.…”

“…If these properties are met, a group-based exposure assessment might lead to more stable exposure estimates compared to individual exposures measured over a limited time period, which typically suffer from considerable random measurement error (15). A regression of outcomes on group-based exposure estimates will therefore be less biased than a regression based on individualized data, in particular if groups are sufficiently large (16)(17)(18)(19). Thus, in theory, exposure-outcome associations are stronger and more correct when based on a group-based approach than when using individual exposures (20).…”

Farming in childhood, diet in adulthood and asthma history

“…pesticide usage). The use of aggregated data, isolated and/or in conjugation with individuals' indices, could be further exploited [20]. It offers a way of decreasing the misclassification Berkson error (which occur where the same approximate exposure is used for many subjects), as emphasised in numerous theoretical reports [21].…”

Towards population-wide exposure assessment

“…The choice of modelling approaches should ideally be supported by research into the measurement errors associated with the various alternatives. Errors in grouped data are often ignored or assumed to conform to a Berkson model that does not result in bias, but recent research has shown this is not always so 11 12…”