時間序列(Time Series Master Level 1) Master of Statistics Course of Announcement Text Books: Introduction to Time Series and Forecasting by P.J. Brockwell and R.A. Davis., Springer ISBN 0-387-94719-1 (滄海代理 04-2588787) Reference: Time Series Analysis: Univariate and Multivariate Methods by W. W. S. Wei, Addison Wesley 1990. ISBN 0-201-15911-2. Applied Econometric Time Series, Second Edition, Walter Enders, Wiley Papers: Announce in appropriate time (will focus on estimation and model selections) Software: for the course: A CD containing the time series package ITSM2000, is contained in the text. Installation instructions for ITSM2000, which requires a PC running Windows 95/98/00, Windows NT or a more recent version of Windows, are given at the back of the text. The professional version, which can be used to analyze data sets longer than 250. R/S: might important for Master Student research. Instructor: Tsair-chuan Lin 林財川 Office:商 0714 office hours:Tu, Th am10~12 Tel: 02-86746775; 03-3277568 E-mail: tsair@mail.ntpu.edu.tw web.ntpu.edu.tw/~tsair 1 Course Main Contents: (80% theory; 20% application): Examples, objectives, general approaches, stationary models. [1.1,1.2, 1.3, 1.4] Removing trend and/or seasonality, testing an estimated noise sequence. [1.5, 1.6] Stationary random processes: basic properties, linear processes, introduction to ARMA processes, properties of the sample mean and autocorrelation function. [2.1, 2.2, 2.3, 2.4] Forecasting stationary time series, the Wold decomposition. [2.5, 2.6] ARMA models: ARMA(p,q) processes, the ACF and PACF, forecasting ARMA processes [3.1-3.3] Introduction to spectral theory and linear filtering. Spectral densities of ARMA processes. [4.1-4.4] Modelling and forecasting with ARMA processes. [5.1-5.5] Non-stationary and seasonal time series models: ARIMA models, identification, unit roots, seasonal models, regression with time series errors. [6.1-6.6] Required: Regresssion Other References: Time Series: Theory and Methods, 2nd Edition, Brockwell and Davis The Analysis of Time Series, An Introduction, Chatfield Introduction to Statistical Time Series, Fuller Time Series Analysis: Forecasting and Control, Box, Jenkins and Reinsel Time Series Analysis and its Applications, Shumway and Stoffer Grading: Homework30%; Exams 35%; Final Exam 35% 2 週數 日期 內容 講義自行列印 1 09/20 課程介紹 2 09/27 Ch1. Introduction 3 10/04 Ch1. Introduction ch1.pdf 4 10/11 Ch2. Stationary Process ch2.pdf 5 10/18 Ch2. Stationary Process 6 10/25 Ch2. Stationary Process 7 11/01 Ch3. ARMA Model 8 11/08 Ch3. ARMA Model 9 11/15 暫定期中考 2(Ch3-6) 10 11/22 Ch4. Spectral Analysis 11 11/29 Ch4. Spectral Analysis 12 12/06 Ch5. Modeling and Forecasting 13 12/13 Ch5. Modeling and Forecasting 14 12/20 Ch6. Non-stationary Time Series 15 12/27 Ch6. Non-stationary Time Series 16 01/03 Ch7. Multivariate Time Series 17 01/10 Ch7. Multivariate Time Series 18 01/17 暫定 Final Test 習 題 課程大綱 Splus for time series ch3.pdf 當然要考啦!! import data ch5.pdf unit root test ch6.pdf ITSM.rar PEST Package Introduction 範例: 書面(.doc) 簡報(.ppt) 【最新公告】 12/09, 期末計畫使用資料何處尋? 3 o (92 年使 用) http://www-personal.buseco.monash.edu.au/~hyndman/TSDL/ 選擇 Finance 或 Macro-Econ 大項 o (91 年使用) http://www.economagic.com/ o Splus: ARIMA modeling 10/12, 期末計畫如何書寫? 範例: 書面(.doc) 1012, 如何 oral? 範例: 簡報(.ppt) Some Other Resources Introduction to Time Series Analysis and Forecasting With Applications of SAS and Spss Seasonal Model for the Airline Series Subset, Seasonal, and Factored ARMA Models Fine 4