依序介紹簡單線性迴歸模型、多元線性迴歸模型及迴歸決測樹模型之理論及應用，藉由推論、診斷和模式選擇，加強資料分析之建模與預測能力。理論部份提供學生在學習大一統計學、微積分和線性代數之後，如何進一步與專業的統計課程結合，並應用於實際的問題解決之中;同時在龐大的資料流中，透過實際問題的思索和探究，藉由基礎的摘要統計和圖表進行初步探勘，有效率的進行有用資料之探勘和採礦，並將數據轉換為有用的資訊，探討日常生活中無所不在的統計問題，以及如何正確使用迴歸分析建立量化之預測模型。透過專業之統計採礦軟體進行實務操作，建立模型配適之正確觀念統計，除了專業知識與技術學習之外，並在課程學習過程中逐漸培養國際觀、團隊合作、創新思考和口語與書寫溝通能力等職涯競爭力，將統計最重要的量化模型理論融合於實務操作，進行決策判斷之參考依據，培養學生職涯發展所需之跨領域專長。The theory and application of simple linear regression model, multiple linear regression model and regression decision tree model are introduced in sequence, and the modeling and prediction capabilities of data analysis are enhanced through inference, diagnosis and model selection. The theoretical part provides students with how to further integrate with professional statistics courses after studying freshman statistics, calculus and linear algebra and apply them to practical problem solving; at the same time, in the huge data flow, they can think through practical problems and exploration, through basic summary statistics and charts to conduct preliminary exploration, efficiently explore and mine useful data, and convert data into useful information, explore ubiquitous statistical issues in daily life, and how to correctly use regression analysis Build quantitative prediction models. Through professional statistical mining software for practical operations, establish correct concept statistics for model adaptation. In addition to learning professional knowledge and technology, we will also gradually develop international outlook, teamwork, innovative thinking, and oral and written communication skills during the course learning process. For career competitiveness, the most important quantitative model theory of statistics is integrated into practical operations, providing a reference for decision-making and judgment, and cultivating the cross-field expertise required for students' career development.
本課程主要目標在介紹迴歸分析之相關方法以及其理論。除此之外，如何利用所學迴歸方法來做實際資料分析亦是本課程之重點，課程主要涵蓋如下：
1.簡單以及多重迴歸之方法及理論
2.迴歸模式適合度檢定以及診斷
3.反應變數之轉換
4.迴歸與變異數分析
5.模式選取
6.利用迴歸相關方法之實例分析
The main goal of this course is to introduce the related methods and theories of regression analysis. In addition, how to use the regression methods learned to do actual data analysis is also the focus of this course. The course mainly covers the following:
1. Simple and multiple regression methods and theories
2. Regression model fitness test and diagnosis
3. Conversion of reaction variables
4. Regression and variation analysis
5. Mode selection
6. Example analysis using regression correlation method
1. Kutner, M.H., Nachtsheim, C., and Neter, J. （2004）, Applied Linear Regression Models, 4th edition, McGraw-Hill Book Co.（華泰文化事業股份有限公司代理）(Textbook)
2. Mendenhall, W. and Sincich, T. （2012）, A second Course in Statistics--Regression Analysis, 7th edition, Pearson Education, Inc, Boston, USA. （華泰文化事業股份有限公司代理）
3. Montgomery D.C., Peck, E. A. and Vining, G. G. (2006）, Introduction to Linear Regression Analysis, 4th edition, John Wiley & Sons, Inc. （歐亞書局有限公司代理）
1. Kutner, M.H., Nachtsheim, C., and Neter, J. (2004), Applied Linear Regression Models, 4th edition, McGraw-Hill Book Co. (Agent of Huatai Cultural Industry Co., Ltd.) (Textbook)
2. Mendenhall, W. and Sincich, T. (2012), A second Course in Statistics--Regression Analysis, 7th edition, Pearson Education, Inc, Boston, USA. (Agent of Huatai Cultural Industry Co., Ltd.)
3. Montgomery D.C., Peck, E. A. and Vining, G. G. (2006), Introduction to Linear Regression Analysis, 4th edition, John Wiley & Sons, Inc. (Agent of Eurasia Book Company Co., Ltd.)
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 平時成績平時成績 usual results |
40 | 學習態度(包括出缺席)、作業成績、平時考成績、課堂討論與互動 |
| 期中考期中考 midterm exam |
30 | 筆試進行 |
| 期末考期末考 final exam |
30 | 筆試進行 |
