On the asymptotic properties of non-degenerate U-statistics in the presence of MCAR data

Abstract

In this presentation, we will discuss recent results regarding the asymptotic properties of non-degenerate U-statistics in cases where the data are missing completely at random, and a complete-case approach is employed. As an illustrative example, we will focus on the problem of testing independence using the estimator of Kendall's τ. In this particular context, we will provide limiting results when employing several commonly used imputation methods.