Obtaining Initial Parameter Estimates for Nonlinear Systems Using Multicriteria Associative Memories

This article appeared in Computer Science in Economics and Management (now Computational Economics). Parameter estimation problems for nonlinear systems are typically formulated as nonlinear optimization problems. For such problems, one has the usual difficulty that standard successive approximation schemes require good initial estimates for the parameter vector. This article develops a simple multicriteria associative memory (MAM) method for obtaining good initial estimates for nonlinear parameter estimation problems. The method is implemented in Fortran by the MAM program. Annotated pointers to related work can be accessed here: http://www.econ.iastate.edu/tesfatsi/vita.htm#MAM