Input data analysis using neural networks

Simulation deals with real-life phenomena by constructing representative models of a system being questioned. Input data provide a driving force sor such models. The requirement for identifying the underlying distributions of data sets is encountered in many fields and simulation applications (e.g., manufacturing economics, etc.). Most of the time, after collection of the raw data, the true statistical distribution is sought by the aid of nonparametric statistical methods. In this paper, we investigate the feasibility of using neural networks in selecting appropriate probability distributions. The performance of the proposed approach is measured with a number of test problems.