Should regression calibration or multiple imputation be used when calibrating different devices in a longitudinal study?

Abstract

In longitudinal studies, the devices used to measure exposures can change from visit to visit. Calibration studies, wherein a subset of participants is measured using both devices at follow-up, may be used to assess between-device differences (i.e., errors). Then, statistical methods are needed to adjust for between-device differences and the missing measurement data that often appear in calibration studies. Regression calibration and multiple imputation are two possible methods. We compared both methods in linear regression with a simulation study, considering various real-world scenarios for a longitudinal study of pulse wave velocity. Regression calibration and multiple imputation were both essentially unbiased. Regression calibration underestimated the empirical standard error by up to 50%, while multiple imputation underestimated it by at most 30%. Regression calibration was slightly more efficient than multiple imputation when the magnitude of the between device differences at follow-up was small. However, the improved representation of uncertainty from multiple imputation suggests we use it over regression calibration in longitudinal studies where a new device at follow-up might be error-prone compared to the device used at baseline.