0410330 20240103182206.520060210235959.9 2 Livre des Actes. Bordeaux Université Victor Segalen 2000 4 s. 864-867NikulinM.LimniosN. cav_un_auth*0019770 Picek J. CZ cav_un_auth*0101227 Volf Petr UTIA-B Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. 12B VS97084 MŠMT CZ cav_un_auth*0025121 AV0Z1075907 A nonlinear regression model is considered for the description of survival of machine parts under different stresses. The model parameters are estimated by the method of regression quantiles. The procedure of estimation is presented and the advantages of the approach are shown on a real-data case, namely that the method is applicable without any knowledge of the distribution of errors and that it is robust against outliers. The case of censored data is discussed, too. cav_un_auth*0212642 MMR '2000 /2./ Bordeaux FR 04.07.2000-07.07.2000 BB SI http://hdl.handle.net/11104/0130421 UTIA-B 20000046 2000 2000 Bordeaux Université Victor Segalen Conférence Internationale sur les Méthodes Mathématiques en Fiabilité 864 867 Nikulin M. 340 Limnios N. 340