學習多變量統計方法於統計實務的應用分析。本課程介紹多個創新的多變量統計方法[例如:分段逆迴歸法(Sliced Inverse Regression)、主要黑森定向法(principal Hessian Directions)等]，用以達到資料縮減(data reduction)的目的，並且應用至大量資料集(包括生物醫學等方面)。
A Tentative Course Outline :
Week 1 : 迴歸分析之維度縮減；主成份分析 (PCA)
Week 2-4 : 分段逆迴歸法 (SIR)
Week 5-6 : 主要黑森定向法 (PHD)
Week 7-8 : Generalized Association Plots (GAP)
Week 9 : 期中報告
Week 10-11 : 曲線資料分析 (Curve Data Analysis)
Week 12-13 : 最小平均變異估計法：MAVE
Week 14-15: 超高維之變數選取法: LASSO (Least Absolute Shrinkage and Selection Operator)、SIRI
Week 16-17: 型態辨識 (Pattern Recognitions)
Week 18 : 期末報告

Learn the application analysis of multi-variable statistical methods in statistical practice. This course introduces multiple innovative multi-variable statistical methods [such as Sliced ​​Inverse Regression, principal Hessian Directions, etc.] to achieve the purpose of data reduction and apply to a large number of data sets (including biomedicine, etc.).
A Tentative Course Outline:
Week 1: Dimension reduction of resection analysis; principal component analysis (PCA)
Week 2-4: Segmented Inverse Reversal Method (SIR)
Week 5-6: Main Hessian Directional Method (PHD)
Week 7-8: Generalized Association Plots (GAP)
Week 9: Midterm Report
Week 10-11: Curve Data Analysis
Week 12-13: Minimum average variation estimation method: MAVE
Week 14-15: Ultra-high fiber variable selection method: LASSO (Least Absolute Shrinkage and Selection Operator), SIRI
Week 16-17: Pattern Recognitions
Week 18: Final Report

No textbook. Lecture notes and selected papers will be available.

No textbook. Lecture notes and selected papers will be available.