MODELING BY SHORTEST DATA DESCRIPTION

被引：3504

作者：

RISSANEN, J

机构：

[1] IBM Research Laboratory, San Jose

来源：

AUTOMATICA | 1978年 / 14卷 / 05期

关键词：

identification; Modeling; parameter estimation; statistics; stochastic systems;

D O I：

10.1016/0005-1098(78)90005-5

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The number of digits it takes to write down an observed sequence x1, ..., xN of a time series depends on the model with its parameters that one assumes to have generated the observed data. Accordingly, by finding the model which minimizes the description length one obtains estimates of both the integer-valued structure parameters and the real-valued system parameters. © 1978.

引用

页码：465 / 471

页数：7

共 13 条

[1] ABRAMSON N, 1963, INFORMATION THEORY C
[2] AKAIKE H, 1977, APPLICATIONS STATIST
[3] AKAIKE H, 2ND INT S INF THEOR, P267
[4] SYSTEM IDENTIFICATION - SURVEY
ASTROM, KJ
EYKHOFF, P
[J]. AUTOMATICA, 1971, 7 (02) : 123 - +
[5] Hannan J., 2013, TECH NOTE, V43153
[6] KOLMOGOROV A, 1968, PROBL INF TRANSMISSI, V1
[7] KULLBACK S, 1959, INFORMATION THEORY S
[8] Rissanen J., 1976, SYSTEM IDENTIFICATIO, P97
[9] RISSANEN J, 1976, MATH SYST THEORY, V131, P76
[10] GENERALIZED KRAFT INEQUALITY AND ARITHMETIC CODING
RISSANEN, JJ
[J]. IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1976, 20 (03) : 198 - 203

← 1 2 →