An analysis pipeline for estimating true intake from repeated measurements with random errors

ABSTRACT

The accurate estimation of an individual's usual dietary intake is an important topic in nutritional epidemiology. This paper considers the best linear unbiased predictor (BLUP) computed from repeatedly measured dietary data and derives several nonparametric prediction intervals for true intake. However, the performance of the BLUP and the validity of prediction intervals depends on whether required model assumptions for the true intake estimation problem hold. To address this issue, the paper examines how the BLUP and prediction intervals behave in the case of a violation of model assumptions, and then proposes an analysis pipeline for checking them with data.

KEYWORDS:

• Analysis pipeline
• Best linear unbiased predictor
• Nonparametric prediction interval
• Repeated measurements
• Shrinkage estimator
• Usual dietary intake.

MATHEMATICS SUBJECT CLASSIFICATION:

• 62G05, 62P10

Funding

Seongil Jo was supported by research funds for newly appointed professors of Chonbuk National University in 2017. Jeongseon Kim was supported by a grant from the Korean Food and Drug Administration (10162KFDA994). Woojoo Lee was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2016R1D1A1B03936100).