• 沒有找到結果。

We attempt to cover time domain analysis of time series

N/A
N/A
Protected

Academic year: 2022

Share "We attempt to cover time domain analysis of time series"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

Fu Jen Catholic University Huei-Yu Chiu (n=Ø)

Graduate School of Economics Office hours: 13:30-16:30, Wednesday Spring 2009

Course number: G-6562-05918 Office tel: 2905-2706

Class hours: 13:40-16:30, Friday Email: [email protected]

Special topics in Econometrics (l¾%Èçùæ)

Most macroeconomic and financial data are time series. This kind of data are collected according to time. The methodology of time series analysis is construct- ing models and forecasting based on the known past information. This course is designed to introduce the characteristic of time series models and make further forecasts. We attempt to cover time domain analysis of time series. Stationary and nonstationary processes modelled with linear and nonlinear forms will be dis- cussed respectively. Topics such as ARMA models, unit root tests, cointegration, error-correction model, threshold AR models, threshold cointegration and threshold ECM will be investigated. We will also introduce various financial models. Besides, how to use econometric software, Gauss, to do simulation will be also introduced in this class.

Readings

1. Enders, W. (2003), Applied Econometric Time Series, Wiley.

2. Franses, P. H. and D. van Dijk (2000), Non-Linear Time Series Models in Empirical Finance, Cambridge University Press.

3. Fuller, W. (1995), Introduction to Statistical Time Series, Wiley-Interscience.

4. Hamilton, J. D. (1994), Time Series Analysis, Princeton University Press.

5. Kuan, C. -M. (2005), Basic Time Series Analysis, lecture notes.

6. ÏÁô (2008), vÈå}&-,ñ%ÈD‹ŽÀ¢5@à, ‰Mz.

1

(2)

Course Outline

Week 1 (2/20): Difference equations, lag operators, stochastic processes and stationarity

Week 2 (2/27): Stationary ARMA processes I: model estimation and forecast Week 3 (3/06): Stationary ARMA processes II: model estimation and forecast Week 4 (3/13): Vector AR processes

Week 5 (3/20): Threshold AR models: SETAR, STAR, LSTAR models Week 6 (3/27): Markov switching model

Week 7 (4/03): Holiday Week 8 (4/10): Holiday Week 9 (4/17): Midterm

Week 10 (4/24): Deterministic trend, stochastic trend & Wiener processes Week 11 (5/1): Unit root tests

Week 12 (5/08): Tests for stationarity

Week 13 (5/15): Cointegration I: estimation & tests Week 14 (5/22): Cointegration II: error correction model Week 15 (5/29): Holiday

Week 16 (6/05): Threshold cointegration and threshold error correction model Week 17 (6/12): Financial models: ARCH-type models

Week 18 (6/19): Final exam: term paper presentation

Grading

1. Homework (30%) 2. Midterm (30%) 3. Term paper (40%)

2

參考文獻

相關文件

1B - Time Series of the Consumer Price Index B (CPI-B) by Section 2G - Month-to-Month Change of the Composite CPI by Section 2A - Month-to-Month Change of the CPI-A by

Time constrain - separation from the presentation Focus on students’ application and integration of their knowledge. (Set of questions for written report is used to subsidize

To decide the correspondence between different sets of fea- ture points and to consider the binary relationships of point pairs at the same time, we construct a graph for each set

•The running time depends on the input: an already sorted sequence is easier to sort. •Parameterize the running time by the size of the input, since short sequences are easier

• If we want analysis with amortized costs to show that in the worst cast the average cost per operation is small, the total amortized cost of a sequence of operations must be

Model checking: residuals can be obtained by 1-step ahead forecast errors at each time point, (observations minus the fitted value) Then if the model is adequate, residuals should

The current yield does not consider the time value of money since it does not consider the present value of the coupon payments the investor will receive in the future.. A more

Once we introduce time dummy into our models, all approaches show that the common theft and murder rate are higher with greater income inequality, which is also consistent with