In this paper we study the properties of the location-scale depth procedures introduced by Mizera & Müller and look into the probabilistic information of the underlying time series model carried by them. We focus our attention on short term multivariate quantile based description of the possible time series model. We study robustness and utility of such the description in a decision making process. In particular we investigate properties of the moving Student median (two dimensional Tukey median in a location–scale problem).
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.