標題: 具羃次轉換與一般自相關共變異數結構之成長曲線模型的貝氏分析
Bayesian Analysis of a Growth Curve Model with Power Transformations and a General Autoregressive Covariance Structure
作者: 田銀錦
Yn-Jiin Tyan
李昭勝
Jack C. Lee
統計學研究所
關鍵字: 貝氏;馬可夫鏈-蒙地卡羅;Banded 結構;Bayesian;MCMC;Banded structure
公開日期: 1998
摘要: 本論文是從貝氏分析的觀點來考慮具冪次轉換的一般成長曲線模型,而其中共變異數矩陣為 Banded 結構。這個共變異數結構是 AR(1) 相依結構的一般化。文中對於參數和未來值都有推論。我們用了一個實際的資料和一些模擬的資料來描述結果。
In this paper we consider, from Bayesian points of view, the generalized growth curve model with power transformations when the covariance matrix has a Banded structure. This covariance structure is a generalization of AR(1) dependence structure. Inferences on the parameters and the future values are included. The results are illustrated with a real data set and several simulated data sets.
URI: http://140.113.39.130/cdrfb3/record/nctu/#NT870337003
http://hdl.handle.net/11536/63992
Appears in Collections:Thesis