0411244 20240103182312.520060210235959.9 A new class of metric divergences on probability spaces and its applicability in statistics 15 s. cav_un_epca*02507910020-3157Annals of the Institute of Statistical Mathematics553 (2003)639-653 dissimilarities metric divergences minimum distance estimators cav_un_auth*0101218 Vajda Igor UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0213136 Öesterreicher F. AT 12A 579 Commission EU XE CEZ:AV0Z1075907 The paper introduces an infinite class of f-divergences of probability distributions which metrize spaces of probability distributions. The total variation, Hellinger divergence and information radius of Sibson are examples of divergences from this class. The remaining divergences seem to be new in the literature on this topic. An important applicability of these divergences in the statistical point estimation is demonstrated. BB SI http://hdl.handle.net/11104/0131329 UTIA-B 20030231 2003 cav_un_epca*0250791 Annals of the Institute of Statistical Mathematics 0020-3157 1572-9052 Roč. 55 č. 3 2003 639 653