課程名稱 |
多變量分析 Multivariate Analysis |
開課學期 |
107-2 |
授課對象 |
管理學院 商學研究所 |
授課教師 |
楊曙榮 |
課號 |
MBA5011 |
課程識別碼 |
741EU3520 |
班次 |
|
學分 |
3.0 |
全/半年 |
半年 |
必/選修 |
選修 |
上課時間 |
星期四A,B,C(18:25~21:05) |
上課地點 |
管一405 |
備註 |
本課程以英語授課。碩士班數量方法之一。學士班限3年級以上。 限本系所學生(含輔系、雙修生) 且 限學士班三年級以上 總人數上限:45人 |
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/1072MBA5011_ |
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 |
This English-taught course is an introduction to model-based data analytics, detailing: (1) statistical programming using R and Stan, (2) stochastic simulation, (3) computationally intensive methods, (4) mixed and multilevel models, and (5) model comparison. The practical goals of the course are to teach students how to specify, code, fit, and interpret model-based inference, and appreciate the powerful things ‘model thinking’ can do for analyzing dependent data when sampling is over time, space, or within clusters. Besides demanding for mathematical and abstract reasoning, the course is ‘heavy on code’ since having ‘computational thinking’ in the digital era entails a lot of scripting and programming. |
課程目標 |
Programming, mathematics, and statistics are powerful tools of quantitative business science for analyzing the functioning of business and management, in particular for digital operations (e.g., internet of things), platform business (e.g., Airbnb, Alibaba, Uber), and sharing economy (e.g., crowdfunding). |
課程要求 |
Prerequisites: Calculus, Statistics, Computer Programming
Grading Policy: Class Participation (10%), Assignments (30%), Group Project (30%), Final Exam (20%) |
預期每週課後學習時數 |
|
Office Hours |
另約時間 備註: Please make an appointment via email. |
指定閱讀 |
McElreath, R. 2016. Statistical Rethinking. CRC Press. |
參考書目 |
|
評量方式 (僅供參考) |
|
週次 |
日期 |
單元主題 |
Week 1 |
2/21 |
Inference, learning, and prediction |
Week 2 |
2/28 |
Independent study |
Week 3 |
3/07 |
Linear models |
Week 4 |
3/14 |
Multivariate models and causality |
Week 5 |
3/21 |
Statistical and probabilistic programming tutorial |
Week 6 |
3/28 |
Overfitting, uncertainty, and information |
Week 7 |
4/04 |
National holiday |
Week 8 |
4/11 |
Regularization, information criteria, and conditioning |
Week 9 |
4/18 |
Mid-term exam period |
Week 10 |
4/25 |
Simulation-based inference |
Week 11 |
5/02 |
Generalized linear models and classification |
Week 12 |
5/09 |
Independent study |
Week 13 |
5/16 |
Counting, mixtures, and monsters |
Week 14 |
5/23 |
Multilevel models |
Week 15 |
5/30 |
Gaussian processes and missing data |
Week 16 |
6/06 |
Group project report submission |
Week 17 |
6/13 |
Group project presentations |
Week 18 |
6/20 |
Final exam |
|