Investment decisions are made ex ante, that is based on parameters that are not known at the time of decision making. Scenario generators are used not only in the models for (optimum) decision making under uncertainty, they are also used for evaluation of decisions through simulation modelling. In this paper, we review those properties of scenario generators which are regarded as desirable; these are not sufcient to guarantee the ?goodness? of a scenario generator. We also review classical models for scenario generation of asset prices. In particular we consider some recently reported methods which have been proposed for distributions with ‘heavy tails’.
Click here to read full paper