Filtering and parameter estimation for a jump stochastic process with discrete observations

被引：0

作者：

Makhnin, Oleg V. ^{[1
]}

机构：

[1] New Mexico Inst Min & Technol, Dept Math, Socorro, NM 87801 USA

来源：

ELECTRONIC COMMUNICATIONS IN PROBABILITY | 2008年 / 13卷

关键词：

non-linear filtering; Kalman filter; particle filtering; jump processes; target tracking;

D O I：

10.1214/ECP.v13-1363

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：

A compound Poisson process is considered. We estimate the current position of the stochastic process based on past discrete-time observations (non-linear discrete filtering problem) in Bayesian setting. We obtain bounds for the asymptotic rate of the expected square error of the filter when observations become frequent. The bounds depend linearly on jump intensity. Also, estimation of process' parameters is addressed.

引用

页码：210 / 224

页数：15

共 13 条

[1] Efficient particle filtering for jump Markov systems. Application to time-varying autoregressions
Andrieu, C
Davy, M
Doucet, A
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2003, 51 (07) : 1762 - 1770
[2] Bar-Shalom Y., 2004, Estimation With Applications to Tracking and Navigation
[3] Bremaud P., 1981, Point Processes and Queues: Martingale Dynamics
[4] Brockwell P.J, 2002, Introduction to time series and forecasting, V2nd
[5] Doucet A., 2001, SEQUENTIAL M CARLO M
[6] Ibragimov IA, 1981, STAT ESTIMATION ASYM
[7] Lehmann E., 1983, Theory of Point Estimation
[8] Moore J. B., 1995, APPL MATH NEW YORK, V29
[9] PORTENKO N, 1997, RANDOM OPER STOCHAST, V5, P1, DOI DOI 10.1515/ROSE.1997.5.1.1
[10] PORTENKO N, 1998, RANDOM OPER STOCHAST, V6, P213

← 1 2 →