|
Probability theory and mathematical statistics
Existence of explicit asymptotically normal estimators in a multiple logarithmic regression problem
A. Koldaevaa, A. Sakhanenkoab a Novosibirsk State University,
Pirogova Street, 2,
630090, Novosibirsk, Russia
b Sobolev Institute of Mathematics,
Acad. Koptyug avenue, 4,
630090, Novosibirsk, Russia
Abstract:
We construct and investigate a class of
explicit estimators for an unknown multidimensional parameter in a
logarithmic regression problem. We present general conditions for
these estimators to be asymptotically normal. It is the
fourth class of non-linear regression problems for which such
explicit
estimators are found.
Keywords:
multiple logarithmic regression, difficulties in the least squares method, explicit estimators of the parameters, asymptotically normal estimators.
Received July 18, 2017, published September 26, 2017
Citation:
A. Koldaeva, A. Sakhanenko, “Existence of explicit asymptotically normal estimators in a multiple logarithmic regression problem”, Sib. Èlektron. Mat. Izv., 14 (2017), 972–979
Linking options:
https://www.mathnet.ru/eng/semr838 https://www.mathnet.ru/eng/semr/v14/p972
|
Statistics & downloads: |
Abstract page: | 187 | Full-text PDF : | 45 | References: | 36 |
|