Abstract
When y = M(x) + ε, where M may be nonlinear, adaptive regression designs of the levels x1, x2,... at which y1, y2,... are observed lead to asymptotically efficient estimates of the value θ of x for which M(θ) is equal to any desired value y*. More importantly, these designs also make the “cost” of the observations, defined at the nth stage to be Σ1n (xi — θ)2, to be of the order of log n instead of n, an obvious advantage in medical and other applications.
Keywords: iterated least squares, adaptive stochastic approximation, nonlinear regression, control theory, optimal dosage estimation
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Lai T. L., Robbins H. Strong consistency of least-squares estimates in regression models. Proc Natl Acad Sci U S A. 1977 Jul;74(7):2667–2669. doi: 10.1073/pnas.74.7.2667. [DOI] [PMC free article] [PubMed] [Google Scholar]