×

Higher dimensional nonlinear regression - A statistical use of the Riemannian curvature tensor. (English) Zbl 0811.62062

Summary: Results presented in previous author’s papers are extended from the case of a low dimension of the parameter to the case of an arbitrary dimension. In particular, for arbitrary nonlinear regression models with normal errors, we present in an explicit form the “almost exact” density of the maximum likelihood estimator. It is a better approximation than the one obtained by the saddle-point method. In all obtained results the Riemannian curvature tensor is of great importance.

MSC:

62J02 General nonlinear regression
53C20 Global Riemannian geometry, including pinching
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Amari S., Lecture Notes in Statistics 28 (1985)
[2] DOI: 10.1093/biomet/70.2.343 · Zbl 0532.62006 · doi:10.1093/biomet/70.2.343
[3] Hougaard P., Scand. J. Statist 13 pp 207– (1986)
[4] DOI: 10.2307/1403350 · Zbl 0707.62126 · doi:10.2307/1403350
[5] Johansen S., Lecture Notes in Statistics 22 (1984)
[6] DOI: 10.1080/02331889008802220 · Zbl 0712.62059 · doi:10.1080/02331889008802220
[7] DOI: 10.1080/02331889008802222 · Zbl 0712.62060 · doi:10.1080/02331889008802222
[8] DOI: 10.1080/02331889008802249 · Zbl 0724.62063 · doi:10.1080/02331889008802249
[9] DOI: 10.1080/02331889108802300 · Zbl 0809.62053 · doi:10.1080/02331889108802300
[10] DOI: 10.1214/aos/1176347625 · Zbl 0709.62029 · doi:10.1214/aos/1176347625
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.