NECESSARY AND SUFFICIENT CONDITIONS FOR LOCAL 2ND-ORDER IDENTIFIABILITY

被引：7

作者：

GOODRICH, RL ^{[1
]}

CAINES, PE ^{[1
]}

机构：

[1] HARVARD UNIV,DIV APPL SCI,CAMBRIDGE,MA 02138

来源：

IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 1979年 / 24卷 / 01期

关键词：

D O I：

10.1109/TAC.1979.1101953

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This note presents a new formulation and proof of the result that the Hessian of the likelihood function of an observed process at the point 8 in a parameter space, computed under the assumption that the process is i.i.d. Gaussian, is asymptotically nonsingular if and only if 8 is locally second-order identifiable. That is to say, if and only if the parameters in a neighborhood of 0 are in one-to-one correspondence with the second-order statistics of the observed process. Copyright © 1979 by The Institute of Electrical and Electronics Engineers, Inc.

引用

页码：125 / 127

页数：3

共 11 条

[1] MAXIMUM LIKELIHOOD ESTIMATION OF PARAMETERS IN MULTIVARIATE GAUSSIAN STOCHASTIC-PROCESSES [J].