Type of Credit: Elective
Credit(s)
Number of Students
[2/4 更新] 在考量教學資源的限制後，碩班將不再加簽，維持最多十人的名額。
This course will cover fundamental time series models and their application to financial data, especially equity returns, interest rates, and exchange rates. Throughout the course, we will use Python to display time-series data with graphs, conduct preliminary examinations, and work on simple empirical tasks.
能力項目說明
The topics we are going to cover this semester include:
1. Python Fundamentals
2. The Nature of Time Series Data and Data Processing
3. ARMA processes
4. Random Walks and Structural Change
5. Cointegration
6. ARCH/GARCH Models
7. Vector Autoregression models
8. Simple Neural Network Forecasting
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
1. Introduction to the Time Series Data and the Course Requirement
2. Python Fundamentals
3. Data Processing
4. Difference Equations (WE Ch.1, 2.1)
5. ARMA Models and Model Selection (WE Ch. 2)
6. ARCH, GARCH Models (WE Ch. 3)
7. Unit Roots and Structural Change (WE Ch.4)
8. Cointegration (WE Ch.6)
9. Vector Autoregression (VAR) (WE Ch.5)
10. Simple Neural Network Forecasting
Homework (70%):
- Peer-reviewed problem sets with Python
- Plagiarism is strictly forbidden
Term paper (30%) – a small project to show how much you learned from this course.
- No more than 8 pages
- Don't make a front page
- Please describe your findings in the executive summary on the first page
Main Textbook:
Walter Enders "Applied Econometric Time Series" 4th edition
Important Time Series Reference:
Tsay (2010) Analysis of Financial Time Series, 3rd edition
陳旭昇 “時間序列分析”
Python Reference for beginners:
蔡炎隆、季佳琪、陳先灝 (2020) “少年Py的大冒險：成為 Python 數據分析達人的第一門課”，全華圖書
Moodle