Premium
Confronting the ironies of optimal design: Nonoptimal sampling designs with desirable properties
Author(s) -
Casman Elizabeth A.,
Naiman Daniel Q.,
Chamberlin Charles E.
Publication year - 1988
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/wr024i003p00409
Subject(s) - sampling (signal processing) , optimal design , nonlinear system , nonlinear regression , sampling design , mathematical optimization , mathematics , computer science , regression analysis , statistics , population , demography , sociology , physics , filter (signal processing) , quantum mechanics , computer vision
Two sampling designs are developed for the improvement of parameter estimate precision in nonlinear regression, one for when there is uncertainty in the parameter values, and the other for when the correct model formulation is unknown. Although based on concepts of optimal design theory, the design criteria emphasize efficiency rather than optimality. The development is illustrated using a Streeter‐Phelps dissolved oxygen‐biochemical oxygen demand model.