MODELING BY SHORTEST DATA DESCRIPTION

被引：3551
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
收藏
页码：465 / 471
页数：7
相关论文
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 [J].
ASTROM, KJ ;
EYKHOFF, P .
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 [J].
RISSANEN, JJ .
IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1976, 20 (03) :198-203
12