Symanski E, Kupper L L, Kromhout H, Rappaport S M
Department of Environmental Sciences and Engineering, School of Public Health, University of North Carolina, Chapel, Hill, NC 27599-7400, USA.
Am Ind Hyg Assoc J. 1996 Aug;57(8):724-35. doi: 10.1080/15428119691014585.
Nonstationary behavior in occupational exposure was examined among a number of job groups from different industries. A change in the mean level of exposure between two survey periods was evaluated by applying mixed-effects models. Overall, differences between surveys were observed in slightly more than one-third of the industries analyzed and in about one-quarter of the total number of comparisons performed. Exposures in the majority of cases decreased in the later survey. Further analyses examined the impact of nonstationary exposures on the estimation of the between- and within-worker components of variance. When changes in the mean exposure level were detected, point estimates of the variance components generated under the mixed model were compared with those estimates obtained under the one-way random-effects model, which assumes that the mean exposure level remains constant over time. The results indicate that the magnitude of the bias in the variance component estimates can be substantial when the misspecified model is applied. It is concluded that, in the absence of changes known to affect exposure, data collected within a year are likely to result in relatively valid inferences about mean and variance parameters using models that assume stationarity; for periods extending beyond a year, systematic changes in exposure are more likely to occur. Thus, exposure assessment strategies should be designed so that sufficient data are collected among groups of workers to investigate systematic changes and to ensure that appropriate statistical models are applied. In this way, occupational hygienists will be able to make reliable inferences about the underlying distribution of exposures pertinent to each occupational group.
