查詢結果分析
相關文獻
- 雙線性時間序列模式選取方法之比較
- The Comparison of BIC and Corrected BIC Criteria for Model Selection of Time Series
- 長期資料迴歸均數函數的決定
- 貝氏廣義隱藏式類別分析法在心理計量學的應用
- An Asymptotic Theory for Linear Model Selection
- Information Criteria for Multiple Data Sets and Restricted Parameters
- Bootstrap Estimate of Kullback-Leibler Information for Model Selection
- A Unified Approach to Estimating and Modeling Linear and Nonlinear Time Series
- A Bootstrap Variant of AIC for State-Space Model Selection
頁籤選單縮合
題名 | 雙線性時間序列模式選取方法之比較 |
---|---|
作者姓名(中文) | 鄭天澤; 劉瑞芝; 蔡輝榮; | 書刊名 | 中國統計學報 |
卷期 | 33:4 1995.12[民84.12] |
頁次 | 頁581-602 |
分類號 | 319.5 |
關鍵詞 | 雙線性時間序列模式; 模式選取; 高斯-賽德迭代法; Binlinear time series models; Model selection; Gauss-seidel iteration; |
語文 | 中文(Chinese) |
中文摘要 | 在過去二十年中,時間序列分析領域中大多數的論文都在探討線性時間序列模式。然而現實生活中,有很多時間序列顯然並不符合線性假設;因此近十年來有些學者乃致力於非線性時間序列模式之研究,並提出各種假設檢定方法,以判斷資料是否為線性。一旦確定資料為非線性,則更進一步配適合適的非線性時間序列模式。一般而言,非線性時間序列模式有三種:雙線性模式、指數自迴歸模式以及起始自迴歸模式。此三類模式中的雙線性模式,由於其性質與傳統線性模式類似,經常容易混淆,是以本主旨在探討雙線性模式選取的各種方法,並比較其選模能力。我們使用高斯-賽德迭代法估計參數,藉電腦模擬資料來比較Subba Rao and Gabr (1984)選模法、修正PKK選模法、AIC和 BIC等四種方法或準則的選模能力。 |
英文摘要 | In the past 15 years, there have been a lot of researchers working on model selection problems for bilinear (B L) time series models. Several model selection criteria or methods, such as the Subba Rao's nested search procedure, AIC and BIC criteria, have been suggested and used in the literature. In this paper, the performance of the above model selection criteria/methods are presented and compared, using simulated data, with the modified PKK procedure we have proposed. It is found that the Subba Rao's nested search procedure has a better performance on average than do modified PKK procedure, AIC and BIC criteria. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。