A note on sampling and parameter estimation in linear stochastic systems

Numerical differentiation formulas that yield consistent least squares para meter estimates from sampled observations of linear, time invariant higher order systems have been introduced previously by Duncan et al. The formulas given by Duncan ct ai. have the same limiting system of equations as in th e continuous time case. The formula presented in this note can be character ized as preserving asymptotically a partial integration rule. It leads to l imiting equations for the parameter estimates that are different from the c ontinuous case, but they again imply consistency. The numerical differentia tion formulas given here can be used for an arbitrary linear system, which is not the ease in the previous paper by Duncan et al.