Monitoring residual autocorrelations in dynamic linear models

被引：4

作者：

Gargallo, P ^{[1
]}

Salvador, M ^{[1
]}

机构：

[1] Univ Zaragoza, Fac Ciencias Econ & Empresariales, Zaragoza 50005, Spain

来源：

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION | 2003年 / 32卷 / 04期

关键词：

dynamic linear models; residual autocorrelations; Bayes factor; monitoring; Monte Carlo; AR;

D O I：

10.1081/SAC-120023879

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

In this article we analyze the problem of sequential monitoring residual autocorrelations in DLM's. To that end, we propose a specific algorithm to detect and correctly identify them, given that the monitoring schemes of level and variance changes proposed in West and Harrison (1997) are generally not capable of detecting this kind of deterioration. We also study the frequentist behavior of the three algorithms, providing guidelines on how to choose the values of their parameters.

引用

页码：1079 / 1104

页数：26

共 7 条

[1]

GARGALLO P, 2001, THESIS U ZARAGOZA

[2]

HARRISON PJ, 1976, J R STAT SOC B, V38, P205

[3] Statistical process control and model monitoring [J].

Harrison, PJ ;

Lai, ICH .

JOURNAL OF APPLIED STATISTICS, 1999, 26 (02) :273-292

[4]

Pole A., 1994, APPL BAYESIAN FORECA

[5]

WEST M, 1986, J ROY STAT SOC B MET, V48, P70

[6] MONITORING AND ADAPTATION IN BAYESIAN FORECASTING MODELS [J].

WEST, M ;

HARRISON, PJ .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1986, 81 (395) :741-750

[7]

West M., 2006, Bayesian forecasting and dynamic models

← 1 →