Three different kinds of median type estimators for use in applications where the underlying probability distributions are multivariate are proposed and analyzed. The numerical complexity and the statistical characteristics of the estimators are studied and discussed. Numerical results give evidence that the estimator which is a simple extension of the scalar median has an overall performance that is the same or better than the other two proposed estimators.
No takes yet. Share an insight, caveat, or question.
Pomalaza‐Ráez et al. (1988) studied this question.