Kernel density estimation in adaptive tracking
Bernard Bercu, Bruno Portier · 2008
We investigate the asymptotic properties of a recursive kernel density estimator associated with the driven noise of multivariate ARMAX models in adaptive tracking. We establish an almost sure pointwise and uniform strong law of large numbers as well as a pointwise and multivariate central limit theorem. We also carry out a goodness-of-fit test together with some simulation experiments.