Generalised Regression Estimation Given Imperfectly Matched Auxiliary Data

Abstract Generalised regression estimation allows one to make use of available auxiliary information in survey sampling. We develop three types generalised estimator when the data cannot be matched perfectly sample units, so that standard is inapplicable. The inference remains design-based. Consistency proposed estimators either given by construction or else can tested observed and links. Mean square errors estimated. A simulation study used explore potentials estimators.