In this paper we propose a strategy for robust estimation of a simple linear mixed model. The proposition is based on a regression depth function introduced by Rousseeuw and Hubert. We study the performance of the proposition on various two-dimensional data sets containing outliers. The Monte Carlo study shows the proposed estimator to have very good properties. Our study also shows the strategy we have put forth to have very good properties in comparison with a generalised least squares estimator on a real data set example concerning the relation between two economic variables considered in a regional classification.
In this paper I present selected applications of data depth-based statistical procedures for a preliminary analysis of time series. I focus our attention on simple methods induced by halfspace depth, regression depth and generalised band depth proposed by Pintado-Lopez and Romo. The Monte Carlo studies and empirical examples show our procedures to have good robustness properties.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.