The $k$ nearest neighbors local linear estimator of functional conditional density when there are missing data

Our key aim is to propose effective estimators for the conditional probability density of a scalar response variable given functional co-variable, where considered have missing data at random. Such are constructed by combining approaches local linear method and kernel nearest neighborhood. The main feature this estimation possibility model phenomena. Under less restrictive conditions, we show strong consistency proposed estimators. To assess efficacy developed estimators, empirical analysis as well real analyses performed.