.In the framework of the quality assessment of land cover databases, we have proposed the two-phase approach with permanent random numbers (TPPRN) and we have compared it with the adaptive sequential quality control with permanent random numbers (ASPRN) and with the two-phase sample design proposed by Thompson and Seber. Whatever the weights assigned to the estimators of the TPPRN, it is much more efficient than the two phase sample design proposed by Thompson and Seber. Moreover, in all the simulations, the efficiency of the TPPRN is comparable with the one of the ASPRN, although the TPPRN is much simpler.In the framework of the quality assessment of land cover databases, we have compared the two-phase approach with permanent random numbers (TPPRN) with the adaptive sequential quality control with permanent random numbers (ASPRN) and with the two-phase sample design proposed by Thompson and Seber. Whatever the weights assigned to the estimators of the TPPRN, it is much more efficient than the two phase sample design proposed by Thompson and Seber. Moreover, in all the simulations, the efficiency of the TPPRN is comparable with the one of the ASPRN, although the TPPRN is much simpler.
Sequential and Two Phase Sample Designs for Quality Control
CARFAGNA, ELISABETTA;MARZIALETTI, JOHNNY;
2008
Abstract
.In the framework of the quality assessment of land cover databases, we have proposed the two-phase approach with permanent random numbers (TPPRN) and we have compared it with the adaptive sequential quality control with permanent random numbers (ASPRN) and with the two-phase sample design proposed by Thompson and Seber. Whatever the weights assigned to the estimators of the TPPRN, it is much more efficient than the two phase sample design proposed by Thompson and Seber. Moreover, in all the simulations, the efficiency of the TPPRN is comparable with the one of the ASPRN, although the TPPRN is much simpler.In the framework of the quality assessment of land cover databases, we have compared the two-phase approach with permanent random numbers (TPPRN) with the adaptive sequential quality control with permanent random numbers (ASPRN) and with the two-phase sample design proposed by Thompson and Seber. Whatever the weights assigned to the estimators of the TPPRN, it is much more efficient than the two phase sample design proposed by Thompson and Seber. Moreover, in all the simulations, the efficiency of the TPPRN is comparable with the one of the ASPRN, although the TPPRN is much simpler.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
