Scholarlink

In this book, we present a novel filtering approach for estimating the hidden states of random variables in the multiple noisy non-stationary time series dataNoisy non-stationary time series. Our methodology is particularly suited to the analysis of small sample non-stationary macroeconomic time series. The method is based on the frequency domain application of the separating information maximum likelihood (SIML) method, which was developed by Kunitomo et al. (Separating information maximum likelihood estimation for high-frequency financial data. Springer, 2018) and (Jpn J Stat Data Sci 1:297–332, 2020), and Nishimura et al. (2019). We propose to use the filtering method of hidden random variables of trend-cycleTrend-cycle, seasonal, and measurement error components.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Introduction

  • 章节

  • 发表日期：

    2025年

查看全文
  • Naoto Kunitomo,
  • Seisho Sato

摘要

In this book, we present a novel filtering approach for estimating the hidden states of random variables in the multiple noisy non-stationary time series dataNoisy non-stationary time series. Our methodology is particularly suited to the analysis of small sample non-stationary macroeconomic time series. The method is based on the frequency domain application of the separating information maximum likelihood (SIML) method, which was developed by Kunitomo et al. (Separating information maximum likelihood estimation for high-frequency financial data. Springer, 2018) and (Jpn J Stat Data Sci 1:297–332, 2020), and Nishimura et al. (2019). We propose to use the filtering method of hidden random variables of trend-cycleTrend-cycle, seasonal, and measurement error components.