0410992 20240103182254.220060210235959.9 20 s. cav_un_epca*02930251212-074X917 (2002)31-50 multistage stochastic programming empirical estimates Markov dependence cav_un_auth*0101122 Kaňková Vlasta UTIA-B Department of Econometrics Ústav teorie informace a automatizace AV ČR, v. v. i. 12B GA402/01/0539 GA ČR cav_un_auth*0008959 GA402/02/1015 GA ČR cav_un_auth*0000527 GA402/01/0034 GA ČR cav_un_auth*0008950 CEZ:AV0Z1075907 A multistage stochastic programming problem can be introduced as a system of parametric optimization problems considered w.r.t. the Euclidean space with an inner (recurrent) dependence and mathematical (mostly conditional) expectation in the objective functions of the individual problems. Consequently, this type of the problems belongs to the class of problems depending on a measure. The aim of the paper is to treat the case when the theoretical probability measure is replaced by an "empirical" one. BB E http://hdl.handle.net/11104/0131079 UTIA-B 20020206 2002 cav_un_epca*0293025 Bulletin of the Czech Econometric Society 1212-074X Roč. 9 č. 17 2002 31 50