Robust doubly protected estimators for quantiles with missing data

YOHAI, VÍCTOR; SUED, MARIELA; VALDORA, MARINA

TEST

SPRINGER

Año: 2019

1133-0686

Doubly protected methods are widely used for estimating the population mean ofan outcome Y from a sample where the response is missing in some individuals. Tocompensate for the missing responses, a vector X of covariates is observed at eachindividual, and the missing mechanism is assumed to be independent of the response,conditioned on X (missing at random). In recent years, many authors have turnedfrom the estimation of the mean to that of the median, and more generally, doublyprotected estimators of the quantiles have been proposed. In this work, we presentdoubly protected estimators for the quantiles in semiparametric models that are alsorobust, in the sense that they are resistant to the presence of outliers in the sample.