查詢結果分析
相關文獻
- The Comparison of BIC and Corrected BIC Criteria for Model Selection of Time Series
- Information Criteria for Multiple Data Sets and Restricted Parameters
- The Review and Study of Some Order Determing Critera for ARMA Process
- 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
- 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
- 雙線性時間序列模式選取方法之比較
頁籤選單縮合
題名 | Information Criteria for Multiple Data Sets and Restricted Parameters |
---|---|
作者姓名(外文) | Dudley,Richard M.; HaughtonDominique; | 書刊名 | Statistica Sinica |
卷期 | 7:2 1997.04[民86.04] |
頁次 | 頁265-284 |
分類號 | 319.5 |
關鍵詞 | 貝氏訊息準則; 模式選取; BIC; Jeffreys' prior; Model selection; |
語文 | 英文(English) |
英文摘要 | In this paper, we extend information criteria for model selection to the case of K independent data sets corresponding to different true parameters θ₁, …, θ[8e52] and to situations where some of the models may have the same dimension and may include boundaries. New criteria are introduced: SBICR, which combines criteria from different data sets, and IBICR, which treats one data set at a time. We apply the criteria to a set of 2 × 2 contingency tables (mosquito data) and to some data on baseball players' performance. Consistency results are given for the criteria under some assumptions. The best model will be the smallest one containing all theθ[93bc]. A model m□ is called competitive if the vector θ□ of true parameters is in the closure of the set m □ of ψ□'s where m□ is the best model. We find that, under reasonable assumptions, for submodels of an exponential family, if for all competitive m□, m□ is not too thin close toθ□, the SBICR procedure is asymptotically close to Bayes procedures. This article extends results in Haughton (Ann. Statist. 1988, Sankhyā 1989) and Poskitt (J. Roy. Statist. Soc. Ser. B 1987). |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。