Stochastic simulation and modelling

Previous research has shown that stochastic models are advantageous tools for representation of the real world. Due to actual spread of fast and inexpensive computational power everywhere in the world, the best approach is to model a real phenomenon as faithfully as possible, and then rely on a simulation study to analyse it. Based on theoretical fundamentals in stochastic modelling and simulation defined by Ross (1990), an incremental development of an object-oriented Java framework containing the main elements for building and implementing stochastic models is realized in the Department of Mathematics and Informatics of Iuliu Haţieganu University, Cluj-Napoca. The main result of this research is a collection of Java class libraries, which are used to model and to simulate classical distributions, stochastic processes and Monte Carlo methods. The basic design philosophy of our object-oriented approach to simulation of the random variables by means of classical distributions is presented in Prodan et al. (1999). The object-oriented Java framework containing the set of base-line classes for stochastic Abstract: The paper demonstrates the advantages of stochastic models for representation of real world activities. The Department of Mathematics and Informatics from Iuliu Haţieganu University Cluj-Napoca has created and implemented a collection of Java class libraries for stochastic simulation and modelling. The paper reports on the incremental development of an object-oriented Java framework, based on theoretical fundamentals in simulation and stochastic modelling, that supports the creation of the main elements for building and implementing stochastic models. The stochastic models constructed accurately represent real world phenomena and processes particularly in health care and patient monitoring. One application modelled the patient flow through chronic diseases departments. The model uses a Poisson process with parameter estimated by using the inter-arrival times. The model covers in-patient care time as a mixed-exponential phase-type distribution. Geriatricians and hospital administrators both agreed that such a model can be applied to optimise the use of hospital resources in order to improve hospital care.