Julien Stirnemann (MAP5, Maternité et médecine materno-foetale, GHU Necker-Enfants Malades, Université Paris Descartes et CNRS)

Estimation de densité d’une variable biomédicale mesurée avec erreur à partir d’un échantillon de mesures répétées

vendredi 18 novembre 2011, 9h30 - 10h45

Salle de réunion, espace Turing

Correcting for measurement error the density of a routinely collected
biomedical variable is an important issue when describing reference values for
both healthy and pathological states. The present work addresses the problem
of estimating the density of a biomedical variable observed with measurement
error without any {a priori} knowledge on the error density. Assuming
the availability of a sample of replicate observations, either internal or
external, which is generally easily obtained in clinical settings, an
estimator is proposed based on non-parametric deconvolution theory with an
adaptive procedure for cut-off selection, the replicates being used for an
estimation of the error density. This approach is illustrated in two
applicative examples: i) the systolic blood pressure distribution density
using the Framingham Study dataset, and ii) the distribution of the timing of
onset of pregnancy within the female cycle, using ultrasound measurements in
the first trimester of pregnancy.