Metodi non parametrici negli studi osservazionali multivariati in presenza di fattori di confondimento

Abstract

In this paper we propose a path of analysis for multivariate observational studies in presence of confounding factors. We start from a suitable post-stratification by using the propensity score method in order to provide hypotheses testing for coherent alternatives based on nonparametric techniques. Finally a comparative simulation study to compare the Rosenbaum test (Rosenbaum, 1995) and the multivariate and multistrata permutation test is also presented, even in the presence of missing abservations.