Abstract
In analyses of radiation epidemiology, the regression method is applied to investigate the dose-response curve. Errors in the outcome variable is assumed in the usual regression model, and this may resulted in wider confidence intervals, not in biased estimates. Although errors in covariates are not included in the models, and this may be resulted in biased estimates. To decrease the bias, the measurement error models are proposed, which adjust the bias by quantifying the magnitude of covariate errors and using the information of these. In radiation epidemiology, two kinds of covariate errors (Berkson and classical) are known to exist, and several models which assume these errors and adjust them. We have continued the evaluation of these methods since last year.
