Simulated maximum likelihood in nonlinear continuous-discrete state space models: Importance sampling by approximate smoothing

被引：5

作者：

Singer, H ^{[1
]}

机构：

[1] Fernuniv, Lehrstuhl Angew Stat & Methoden Empir Sozialforsc, D-58084 Hagen, Germany

来源：

COMPUTATIONAL STATISTICS | 2003年 / 18卷 / 01期

关键词：

stochastic differential equations; nonlinear filtering; discrete noisy measurements; maximum likelihood estimation; Monte Carlo simulation; importance sampling;

D O I：

10.1007/s001800300133

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：

The likelihood function of a continuous-discrete state space model is computed recursively by Monte Carlo integration, using importance sampling techniques. A functional integral representation of the transition density is utilized and importance densities are obtained by smoothing. Examples are the likelihood surfaces of an AR(2) process, a Ginzburg-Landau model and stock price models with stochastic volatilities.

引用

页码：79 / 106

页数：28

共 54 条

[1] NONLINEAR BAYESIAN ESTIMATION USING GAUSSIAN SUM APPROXIMATIONS
ALSPACH, DL
SORENSON, HW
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1972, AC17 (04) : 439 - &
[2] Anderson B., 1979, OPTIMAL FILTERING
[3] [Anonymous], ECONOMET THEOR
[4] [Anonymous], 1989, NOISE NON D
[5] *APPL COMP, 2001, MAC PROGR WORKSH
[6] Arnold L., 1974, Stochastic Differential Equations, DOI [DOI 10.1002/ZAMM.19770570413, https://doi.org/10.1002/zamm.19770570413]
[7] Arnold VI, 1998, ORDINARY DIFFERENTIA
[8] ARNOLD VI, 1986, CATASTROPHY THEORY
[9] Bergstrom A. R., 1990, CONTINUOUS TIME ECON
[10] A MONTE-CARLO APPROACH TO NONNORMAL AND NONLINEAR STATE-SPACE MODELING
CARLIN, BP
POLSON, NG
STOFFER, DS
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1992, 87 (418) : 493 - 500

← 1 2 3 4 5 6 →