Stochastic Simulation & Monte Carlo Methods
Stochastic simulation basically refers to Monte Carlo simulation methods. Thereby various variables and parameters of a system are scattered independently from each other according their probability distributions and then the effect of the resulting variables is described with the help of numeric simulation.
On the one side these methods can be used to describe and estimate probabilities and uncertainties quantitatively. Especially for complex and nonlinear systems, Monte Carlo methods are often the only available pragmatic and practically feasible approaches for the simulation based quantitative description of probabilities, uncertainties and risks.
On the other side, Monte Carlo methods can be used for the identification and quantification of correlations and dependencies within complex systems with many variables and parameters.
The efficient exploratory investigation of complex systems is one of the main applications for stochastic simulation beside robustness assessments and robustness management.
Tools & References
A special competence of ANDATA is the usage of multi level stochastic simulations, which are helpful for conditional probabilities, Bayesian approaches and Monte Carlo Markov Chains with the software tool SceneInspector.
The protagonists of ANDATA are one of the pioneers in the application of Monte Carlo methods in the field of automotive safety.