課程名稱 |
迴歸分析 Regression Analysis |
開課學期 |
110-1 |
授課對象 |
理學院 數學研究所 |
授課教師 |
丘政民 |
課號 |
MATH7606 |
課程識別碼 |
221 U3940 |
班次 |
|
學分 |
3.0 |
全/半年 |
半年 |
必/選修 |
必修 |
上課時間 |
星期一8,9,10(15:30~18:20) |
上課地點 |
天數101 |
備註 |
總人數上限:40人 |
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/1101MATH7606_Reg |
課程簡介影片 |
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
課程大綱
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
課程概述 |
1. General introduction/Regression models
2. The classical linear model -- Model definition; Parameter estimation; Hypothesis testing and confidence intervals; Model choice and variable selection; Model diagnostics
3. Extensions of the classical linear model -- The general linear model; Regularization techniques; Boosting linear regression
4. Generalized linear models -- The framework of GLMs; Binary regression; Count data regression; Quasi-likelihood regression
5. Advanced topics |
課程目標 |
1. Establish the concept of regression modeling, analysis, and prediction;
2. Learn the statistical methods and theory in regression;
3. Lay the foundation to learn more advanced regression analysis and related methods;
4. Drill skills of regression analysis in practice; |
課程要求 |
Basic Calculus; Linear algebra; Introductory Statistics; |
預期每週課後學習時數 |
|
Office Hours |
另約時間 備註: Mon (2:00--3:30) or by appointment |
指定閱讀 |
L. Fahrmeir, T. Kneib, S. Lang, B. Marx (2013) Regression: Models, Methods and Applications. Springer-Verlag Berlin Heidelberg.
|
參考書目 |
Sen and M. Srivastava (1990) Regression Analysis: Theory, Methods, and Applications. Springer.
G. James, D. Witten, T. Hastie, R. Tibshirani (2013) An Introduction to Statistical Learning (with Applications in R). Springer. |
評量方式 (僅供參考) |
|
週次 |
日期 |
單元主題 |
第5週 |
10/18 |
Residuals/Properties of the estimators |
第6週 |
10/25 |
Quadratic forms/Hypothesis testing/Confidence intervals |
第7週 |
11/01 |
Model choice/Variable selection |
第8週 |
11/08 |
Model diagnosis |
第10週 |
11/22 |
Extension: Weighting/Heteroscedasticity/Correlated errors |
第11週 |
11/29 |
Extension: Regularization in regression models |
第12週 |
12/06 |
Midterm exam |
第13週 |
12/13 |
GLM: Framework/Theory |
第14週 |
12/20 |
GLM: Estimaion/Diagnosis |
第15週 |
12/27 |
Binary regression, count data regression, QL |
第16週 |
1/03 |
Advanced topics |
第17週 |
1/10 |
Final Exam |
第18週 |
1/17 |
Advanced topics |
|