Premium
SIMULTANEOUS EQUATION SYSTEMS: A CONSISTENT ESTIMATOR FOR UNKNOWN PARAMETERS IN CONFINED AQUIFERS 1
Author(s) -
Loaiciga Hugo A.,
Mariño Miguel A.
Publication year - 1987
Publication title -
jawra journal of the american water resources association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.957
H-Index - 105
eISSN - 1752-1688
pISSN - 1093-474X
DOI - 10.1111/j.1752-1688.1987.tb00831.x
Subject(s) - least squares function approximation , aquifer , ordinary differential equation , mathematics , maximum likelihood , non linear least squares , estimator , partial differential equation , ordinary least squares , inverse problem , flow (mathematics) , nonlinear system , identification (biology) , estimation theory , mathematical optimization , stage (stratigraphy) , inverse , statistics , differential equation , geology , groundwater , mathematical analysis , geotechnical engineering , physics , geometry , botany , quantum mechanics , biology , paleontology
This paper presents criteria for establishing the identification status of the inverse problem for confined aquifer flow. Three linear estimation methods (ordinary least squares, two‐stage least squares, and three‐stage least squares) and one nonlinear method (maximum likelihood) are used to estimate the matrices of parameters embedded in the partial differential equation characterizing confined flow. Computational experience indicates several advantages of maximum likelihood over the linear methods.