Parallel sequential Monte Carlo samplers and estimation of the number of states in a Hidden Markov Model
Parallel sequential Monte Carlo samplers and estimation of the number of states in a Hidden Markov Model
复制标题
并行顺序蒙特卡洛采样器和隐马尔可夫模型中状态数的估计
DOI：
10.1007/s10463-014-0450-4
复制
发表时间：
2014
影响因子：
1
通讯作者：
Nam C
中科院分区：
文献类型：
--
作者：
Nam C
大多数关于隐马尔可夫模型 (HMM) 的建模和推理都假设基础状态的数量是先验已知的。然而，情况通常并非如此，因此确定 HMM 的适当基础状态数量具有相当大的意义。本文提出使用并行顺序蒙特卡罗采样器框架来近似状态数的后验分布。如果还需要以状态数量为条件的近似参数后验，则不需要额外的计算工作。所提出的策略在一组全面的模拟数据上进行了评估，并显示出优于该领域的最新技术：虽然该方法很简单，但它通过充分利用问题的特定结构提供了良好的性能。还介绍了商业周期分析的应用。
The majority of modelling and inference regarding Hidden Markov Models (HMMs) assumes that the number of underlying states is known a priori. However, this is often not the case and thus determining the appropriate number of underlying states for a HMM is of considerable interest. This paper proposes the use of a parallel sequential Monte Carlo samplers framework to approximate the posterior distribution of the number of states. This requires no additional computational effort if approximating parameter posteriors conditioned on the number of states is also necessary. The proposed strategy is evaluated on a comprehensive set of simulated data and shown to outperform the state of the art in this area: although the approach is simple, it provides good performance by fully exploiting the particular structure of the problem. An application to business cycle analysis is also presented.
DOI：
10.2307/3316097
发表时间：
2002-12
期刊：
Canadian Journal of Statistics
影响因子：
--
作者：
Rachel J. Mackay
通讯作者：
Rachel J. Mackay
影响因子：
0.9
作者：
Christopher F. H. Nam;J. Aston;A. M. Johansen
通讯作者：
Christopher F. H. Nam;J. Aston;A. M. Johansen
影响因子：
1.8
作者：
Beskos, Alexandros;Jasra, Ajay;Thiery, Alexandre
通讯作者：
Thiery, Alexandre