This is the authors' abstract. We don't add key points for this paper.
The search for a maximum of a response function is of great concern to experimenters in various disciplines. The ordinate and coordinate of the maximum are usually estimated through finding the local stationary point of the estimated response function regressed through the ordinary least squares procedure.However, despite the fact that the OLSEs are the best linear unbiased estimators (BLUE) for the polynomial coefficients, it is well known that those for the ordinate and coordinate are not BLUE.In search of an estimator which might perform better than OLSE, we present in this paper a linear estimator called LIME which minimizes an integrated mean-squared-error. Based on the statistical properties established for both OLSE and LIME, their relative performances are compared by both numerical evaluation and simulation
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
S et al. (1991) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: