Statistical techniques in modeling of complex systems: Single and multiresponse models

An exposition of statistical techniques in modeling complex systems (single and multiresponse models) that are representative of recent work on modeling systems is provided. The paper begins with several basic concepts related to linear and nonlinear models. The authors then examine four representative techniques of model discrimination which deal with use of nonintrinsic and intrinsic parameters, use of Bayesian methods, and likelihood discrimination. Next they examine multiresponse models with issues dealing with design of experiments for parameter estimation and model discrimination. A case study on sequential model discrimination in multiresponse models is also discussed. Finally an overview on estimating parameters in models of a dynamical system is briefly discussed. The paper concludes with a summary of unresolved issues, and with suggestions on the future role of modeling in the complex situation.