A generalized least-squares model

Summary A interpolation method is given for the case in which a function consisting of a systematic and a random part is to be estimated from measurements affected by errors. This is a combined problem of parameter estimation, filtering and prediction, which has applications in different fields of geodesy and gravimetry. The solution of the problem is derived from a least-squares principle; it is formally very similar to a general case of least-squares adjustment. Address: Hardenbergstr. 34, 1 Berlin 12.