Abstract
We define multivariate Self–Exciting Threshold Autoregressive (MSETAR) Models and present an adaptive algorithm for the estimation of the AR coefficients. This algorithm has a similar structure as stochastic gradient procedures (so–called LMS algorithms) which have been frequently used in linear models. It is shown that conditions of convergence known from the linear case can be reformulated for the nonlinear MSETAR model.
ACKNOWLEDGMENT
This work was partially supported by D.F.G. WI 1166/5-1.