Mismeasurement and the Resonance of Strong Confounders: Uncorrelated Errors

Abstract

Greenland first documented (Am J Epidemiol 1980; 112:564-9) that error in the measurement of a confounder could resonate--that it could bias estimates of other study variables, and that the bias could persist even with statistical adjustment for the confounder as measured. An important question is raised by this finding: can such bias be more than trivial within the bounds of realistic data configurations? The authors examine several situations involving dichotomous and continuous data in which a confounder and a null variable are measured with error, and they assess the extent of resultant bias in estimates of the effect of the null variable. They show that, with continuous variables, measurement error amounting to 40% of observed variance in the confounder could cause the observed impact of the null study variable to appear to alter risk by as much as 30%. Similarly, they show, with dichotomous independent variables, that 15% measurement error in the form of misclassification could lead the null study variable to appear to alter risk by as much as 50%. Such bias would result only from strong confounding. Measurement error would obscure the evidence that strong confounding is a likely problem. These results support the need for every epidemiologic inquiry to include evaluations of measurement error in each variable considered.

Ambient Particles and Health: Lines that Divide

“…127,128 Finally, it is now understood that measurement error in the exposure in settings where several covariates are considered (which is nearly universal), with each covariate also being measured with some error, can result in biasing the estimates of effect in any direction. [129][130][131][132] Therefore, measurement error in the exposure therefore cannot be relied upon to result in conservative effect estimates; sometimes the true effect will be overestimated and sometimes underestimated in an unpredictable fashion.…”

Misclassification of physical work exposures as a design issue for musculoskeletal intervention studies

“…Misclassification of a confounder, as outlined for this population of retail merchandise workers, is more of a threat to validity when the study variable is a weak risk factor in comparison with the confounding factor (12,13). The rate ratio for the highest to lowest level of work exposure, as estimated conservatively from the workers' compensation data, is at least 2.…”

Is consumption of sugar‐sweetened soft drinks during pregnancy associated with birth weight?

“…As our data were largely based on information provided by mothers, the possibility of recall and report bias cannot be excluded. However, such bias is likely to be nondifferential and may result in attenuation of the observed associations (Marshall & Hastrup, 1996). The low participation rate in MoBa (40.6%) may have introduced a selection bias because the women were older and better educated, and the proportion of smokers was lower than among pregnant women in general.…”