Ã山ǿ¼é

Title: Non-Parametric Estimation of the Distribution of Episodically Consumed Food Measured with Error

Abstract: In national surveys, dietary data are typically collected to estimate the distribution of the usual intake of various nutrients and food groups in populations and subpopulations. In this context, dietary intakes are often assessed using self-report instruments that allow capturing food and nutrient intakes for a single day only. Since this snapshot cannot accurately reflect the usual intake, it has long been recognized that such observations are versions of long-term average intakes contaminated by measurement errors. When the food/nutrient is consumed daily, a vast literature on measurement errors shows how to estimate the distribution of the individuals’ usual intake. However, the classical methods cannot be used when considering the usual intake of episodically consumed food (e.g., fish or whole fruits) because in that case a significant proportion of reported intake is equal to zero. In this presentation, we address this problem by using a non-parametric approach.