Type of Credit: Partially Required
Credit(s)
Number of Students
The objective of this course is to equip students with forecasting techniques and knowledge on statistical methods for analyzing time series data.
Prerequisite Capacities(先備課程): programming in R (at least 1 semester) and Mathematical Statistics
註：
1. 先備課程「程式設計與統計軟體」：可由其它一學期的R程式設計課程替代 (由任課老師認定，以加簽的方式選課)。
2. 先備課程「數理統計學」：2月開學前，需修過二學期。
3. 期中考一、期中考二，僅為暫定之日期，會視課程進度調整時間。
能力項目說明
The topics include ACF and PACF functions, ARIMA processes, best linear prediction, model building and model selection, frequency domain analysis, GARCH and Stochastic Volatility models, VAR models, and other multivariate time series models.
| 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 |
|---|---|---|
|
週次 Week |
課程主題 Topic |
課程內容與指定閱讀 Content and Reading Assignment |
教學活動與作業 Teaching Activities and Homework |
學生學習投入時間 Student workload expectation |
|
|
課堂講授 In-class Hours |
課程前後 Outside-of-class Hours |
||||
|
1 |
(Feb. 22) Introduction |
(S&S, 2016) Chapter 1 |
Lecture |
3 |
2 |
|
2 |
(Feb. 29) ACF and PACF functions |
(S&S, 2016) Chapter 1 |
Lecture |
3 | 2 |
|
3 |
(Mar. 7) ACF and PACF functions; AR(p) |
(S&S, 2016) Chapter 3 |
Lecture HW |
3 |
7 |
|
4 |
(Mar. 14) MA(q) process |
(S&S, 2016) Chapter 3 |
Lecture R lab |
3 |
2 |
|
5 |
(Mar. 21) ARIMA processes |
(S&S, 2016) Chapter 3 |
Lecture |
3 |
2 |
|
6 |
(Mar. 28) Midterm Exam 1 SARIMA processes |
(S&S, 2016) Chapter 3 |
Lecture |
3 |
2 |
|
7 |
(Apr. 4) School Holiday |
|
|
|
|
|
8 |
(Apr. 11) model building and model selection |
(S&S, 2016) Chapter 3 |
Lecture |
3 |
7 |
|
9 |
(Apr. 18) model building and model selection: R lab |
(S&S, 2016) Chapter 3 and 4 |
R lab and HW |
3 |
3 |
|
10 |
(Apr. 25) frequency domain analysis |
(S&S, 2016) Chapter 4 |
Lecture |
3 |
2 |
|
11 |
(May 2) Real data presentation |
|
Presentation |
3 |
10 |
|
12 |
(May 9) ARCH and GARCH models |
(Tsay, 2012) Chapter 4 |
Lecture R lab |
3 |
2 |
|
13 |
(May 16) Stochastic Volatility models and VAR models |
(Tsay, 2014) Chapter 2 and 4 |
Lecture HW |
3 | 2 |
|
14 |
(May 23) Midterm Exam 2 |
|
3 |
2 | |
|
15 |
(May 30) multivariate time series models |
(Tsay, 2014) Chapter 2 ~ 7 |
Lecture |
3 |
2 |
|
16 |
(June 6) Real data analysis |
|
|
3 |
10 |
|
17 |
(June 13) final project presentation (part 1) |
|
oral presentation |
3 |
10 |
|
18 |
(June 20) final project presentation (part 2) |
|
oral presentation |
3 |
3 |
Midterm Exam (twice): 40%
Final Project: 35%
Homework: 10%
Attendance/Participation: 15% (出席5~10%、期末報告參與討論5~10%)
All the data analysis (homework and final project) will be implemented using software R.
Reference (參考書目):
1. Shumway and Sto ffer. (2016). Time Series Analysis and its Applications with R Examples.
2. Tsay. (2012). An Introduction to Analysis of Financial Data with R.
3. Tsay. (2014). Multivariate Time Series Analysis.
http://moodle.nccu.edu.tw/