Approximate Inference for Observation-Driven Time Series Models with Intractable Likelihoods

Approximate Inference for Observation-Driven Time Series Models with Intractable Likelihoods
复制标题

具有棘手似然性的观测驱动时间序列模型的近似推理

DOI:
10.1145/2592254
复制
发表时间:
2014
影响因子:
0.9
通讯作者:
Jasra A
Jasra A
中科院分区:
计算机科学4区
文献类型:
--
作者:
Jasra A

文献摘要

参考文献

被引文献

相似文献

在这篇文章中,我们考虑近似贝叶斯参数推断观测驱动的时间序列模型。这种统计模型出现在各种各样的应用中,包括计量经济学和应用数学。本文考虑的情况下,似然函数不能逐点评估;在这种情况下,不能执行精确的统计推断,包括参数估计,这往往需要先进的计算算法,如马尔可夫链蒙特卡罗(MCMC)。我们介绍了一种新的近似基于近似贝叶斯计算(ABC)。在一定的条件下,证明了当n → ∞时,在n的长度范围内,ABC后验几乎必然存在参数的最大后验(MAP)估计,而该估计往往与真实参数不同.然而,一个嘈杂的ABC MAP,扰动原始数据,渐近收敛到真正的参数,几乎肯定。为了得出统计推断,对于所采用的ABC近似,标准MCMC算法可以具有以指数速率下降的接受概率,这使得稍微更先进的算法可能混合不良。我们开发了一个新的和改进的MCMC内核,这是基于一个精确的近似的边际算法,其每次迭代的成本是随机的,但预期的成本,为良好的性能,被证明是O(n2)每次迭代。我们实现了新的MCMC内核,用于从计量经济学模型中进行参数推断。
In this article, we consider approximate Bayesian parameter inference for observation-driven time series models. Such statistical models appear in a wide variety of applications, including econometrics and applied mathematics. This article considers the scenario where the likelihood function cannot be evaluated pointwise; in such cases, one cannot perform exact statistical inference, including parameter estimation, which often requires advanced computational algorithms, such as Markov Chain Monte Carlo (MCMC). We introduce a new approximation based upon Approximate Bayesian Computation (ABC). Under some conditions, we show that asn→ ∞, withnthe length of the time series, the ABC posterior has, almost surely, a Maximum A Posteriori (MAP) estimator of the parameters that is often different from the true parameter. However, a noisy ABC MAP, which perturbs the original data, asymptotically converges to the true parameter, almost surely. In order to draw statistical inference, for the ABC approximation adopted, standard MCMC algorithms can have acceptance probabilities that fall at an exponential rate innand slightly more advanced algorithms can mix poorly. We develop a new and improved MCMC kernel, which is based upon an exact approximation of a marginal algorithm, whose cost per iteration is random, but the expected cost, for good performance, is shown to beO(n2) per iteration. We implement our new MCMC kernel for parameter inference from models in econometrics.
伪边际马尔可夫链蒙特卡罗算法的收敛性
DOI: 10.1214/14-aap1022
发表时间: 2015
期刊: The Annals of Applied Probability
影响因子: --
作者:
Andrieu C
通讯作者: Andrieu C
DOI: 10.1080/01621459.2013.864178
发表时间: 2014-03-01
影响因子: 3.7
作者:
Barthelme, Simon;Chopin, Nicolas
通讯作者: Chopin, Nicolas
DOI: 10.1080/00949658008810361
发表时间: 1980
影响因子: 1.2
作者:
S. Zacks
通讯作者: S. Zacks
粒子马尔可夫链蒙特卡罗讨论
DOI: --
发表时间: 2008
期刊:
影响因子: --
作者:
A. Golightly;D. Wilkinson
通讯作者: D. Wilkinson
用于近似贝叶斯计算的马尔可夫链蒙特卡洛核的方差有界和几何遍历性
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
Anthony Lee;Krzysztof Latuszynski
通讯作者: Krzysztof Latuszynski