Parameter identification for state-space models with nuisanceparameters

The problem of identifying parameters in a dynamic model is considered based on the premise that certain parameters not being estimated are not known precisely. A procedure is described for accounting for these imprecisely known nuisance parameters when estimating the primary parameters of interest. The technique uses the asymptotic normality of the estimate together with the implicit function theorem to determine a correction to the estimate uncertainty evaluated from the Fisher information matrix. Efficient evaluation of the correction using Kalman filters is discussed and a numerical example for the X-22A aircraft is presented