Properties of the separate-bias estimation technique introduced in 1969 [1] are reviewed, including the interpretation of the result as the estimation of a constant embedded in white noise. The equations may be rearranged to permit a simpler calculation of the bias which is particularly useful if only infrequent estimates of the bias are needed. It is also shown that the assumption of a nondecreasing bias-covariance matrix leads to a time-invariant filter without steady-state errors in estimation of the state or the bias.
No takes yet. Share an insight, caveat, or question.
Bernard Friedland (1978) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: