The course provides an elementary but
comprehensive look to the practice of modern econometrics. The main topics
covered include heteroscedasticity, consequences
of heteroscedasticity, detecting heteroscedasticity, Breusch-Pagan LM Test,
Harvey-Godfrey LM Test, Goldfeld-Quandt Test, White Test, resolving
heteroscedasticity, Generalized or Weighted Least Squares, White’s
heteroscedasticity consistent variances and standard errors, autocorrelation, consequences of
autocorrelation, detecting autocorrelation, graphical method, Durbin-Watson
Test, Breusch-Godfrey LM test for serial correlation, Durbin’s h test, resolving
autocorrelation, Generalized Least Squares (GLS), Estimated GLS (EGLS), Newey-West
method, common-factor test, apparent autocorrelation, autoregressive conditional heteroscedasticity
(ARCH) model, testing for ARCH effects, estimation of ARCH models, generalized
autoregressive conditional heteroscedasticity (GARCH) model, estimation of
GARCH Models, estimating dynamic models, adjustment lags, problems in the
estimation of dynamic models, formation of Expectations: adaptive expectations,
rational expectations, consequences and detection of errors of specification,
data mining, alternative approaches to selecting the best model, selecting
models: some important criteria, general to specific modelling, stationarity
and non-stationarity, unit roots and spurious regressions, testing for unit
roots, Dickey-Fuller test, Augmented Dickey-Fuller test, Phillips-Perron test, cointegration,
cointegration and error-correction model (ECM), cointegration in single
equations (The Engle-Granger approach, drawbacks of Engle Granger approach), vector
autoregressive (VAR) models, causality tests (Granger causality test, Sims
causality test), cointegration in multiple equations, Johansen approach, steps
of Johansen approach, identification in standard and cointegrated systems
(order condition, rank condition), traditional panel data models, fixed effects
model, random effects model, Hausman test, non-stationary panels, panel unit
root tests (Levin and Lin test; Im, Pesaran and Shin test, Maddala and Wu
test), panel cointegration tests (Kao test, McCoskey test, Pedroni tests,
Larsson test), simultaneous equation models, simultaneity, identification
problem, conditions of identification, estimation of an exactly identified
equation: indirect least squares (ILS), and estimation of an over-identified
equation: two-stage least squares (TSLS).
Lecturer Dr. H. Ozan
ERUYGUR
Gazi
University, FEAS, Department of Economics, Room: 112.
E-mail:
oeruygur@gmail.com, Phone: 216 1112
Research Assistant
Course Schedule
Rec.
and Lab. Hours To be announced.
Office
Hours To be announced.
Recommended Books - Thomas, R. L. (1996) Modern Econometrics, Prentice Hall, New York.
- Asteriou, D., and Hall, S. G. (2011) Applied Econometrics, Second Edition, Palgrave Macmillan, New York.
- Gujarati, D., and Porter, D. (2009) Basic Econometrics, Fifth Edition, McGraw-Hill.
- Charemza, W.W., and Deadman, D. F. (1999) New Directions in Econometric Practice, Second Edition, Edward Elgar.
Assessment The course is
assessed by two midterm exams, a lab exam, a term project and a final examination.
The weights are as follows:
Lab Exam % 5
Term Project % 10
First Midterm % 20
Second Midterm % 30
Final Exam % 35
Course Home Page
The class web
site can be accessed through online.metu.edu.tr.
The home page will be used primarily to post lecture notes,
data sets, assignments, and announcements.
Softwares
Gretl, Eviews and Excel.
Further Requirements
You are expected to attend classes
regularly.
Detailed Course Outline*
Week |
Subjects |
1.1 |
Non-Spherical Disturbances: Heteroscedasticity I What is heteroscedasticity, consequences of heteroscedasticity, detecting
heteroscedasticity (Informal way, Breusch-Pagan LM Test, Harvey-Godfrey LM
Test, Goldfeld-Quandt Test, White Test) |
1.2 |
Non-Spherical Disturbances: Heteroscedasticity II Resolving Heteroscedasticity (when variance is known: Generalized or Weighted Least Squares, when variance is not known:
White’s heteroscedasticity consistent variances and standard errors) |
2.1 |
Non-Spherical Disturbances: Autocorrelation I What is autocorrelation, consequences of autocorrelation, detecting
autocorrelation (graphical method, Durbin-Watson Test, Breusch-Godfrey LM
test for serial correlation, Durbin’s h test) |
2.2 |
Non-Spherical Disturbances: Autocorrelation II Resolving autocorrelation (when r is known: Generalized Least Squares, when r is unknown: Estimated GLS) |
3.1 |
Non-Spherical Disturbances: Autocorrelation III Newey-West Method, Common-factor test, apparent autocorrelation. |
3.2 |
Modelling the Volatility: ARCH-GARCH Models I The autoregressive conditional heteroscedasticity (ARCH) model,
testing for ARCH effects, Estimation of ARCH models |
4.1 |
Modelling the Volatility: ARCH-GARCH Models II The generalized autoregressive conditional heteroscedasticity (GARCH)
model, Estimation of GARCH Models |
4.2 |
Estimating Dynamic Models I Basic Ideas, Adjustment Lags, Problems in the estimation of Dynamic
Models |
5.1 |
Estimating Dynamic Models II The formation of Expectations: Adaptive Expectations, Rational Expectations |
5.2 |
Choosing the Appropriate Model I The Consequences and Detection of Errors of Specification, Data Mining |
6.1 |
Choosing the Appropriate Model II Alternative Approaches to Selecting the Best Model, Selecting Models:
Some Important Criteria |
6.2 |
Time Series Econometrics: Non-Stationarity and Unit
Root Tests I Stationarity and non-stationarity, Unit Roots and Spurious Regressions |
7.1 |
Time Series Econometrics: Non-Stationarity and Unit
Root Tests II Testing For Unit Roots (Dickey-Fuller Test, Augmented Dickey-Fuller
Test, Phillips-Perron Test) |
7.2 |
Cointegration and Error-Correction Models I What is cointegration, cointegration and error-correction model (ECM) |
8.1 |
Cointegration and Error-Correction Models II Cointegration in Single Equations (The Engle-Granger Approach, Drawbacks of
Engle Granger Approach) |
8.2 |
Vector Autoregressive (VAR) Models and Causality
Tests I Vector Autoregressive (VAR) Models |
9.1 |
Vector Autoregressive (VAR) Models and Causality
Tests II Causality Tests (The Granger Causality Test, The Sims Causality Test) |
9.2 |
Cointegration in Multiple Equations I Cointegration in Multiple Equations, Johansen Approach |
10.1 |
Cointegration in Multiple Equations II Steps of Johansen Approach |
10.2 |
Cointegration in Multiple Equations III Identification in Standard and Cointegrated Systems (Order Condition,
Rank Condition) |
11.1 |
Panel Data Econometrics: Traditional Panel Data
Models Fixed Effects Model, Random Effects Model and Hausman Test |
11.2 |
Panel Data Econometrics: Non-Stationary Panels I Panel Unit Root Tests (Levin and Lin Test; Im, Pesaran and Shin Test,
Maddala and Wu Test) |
12.1 |
Panel Data Econometrics: Non-Stationary Panels II Panel Cointegration Tests (Kao Test, McCoskey Test, Pedroni Tests, The
Larsson Test) |
12.2 |
Simultaneous Equation Models I Simultaneity, The Identification Problem, Conditions of Identification |
13.1 |
Simultaneous Equation Models II Estimation of an Exactly Identified Equation: the Indirect Least
Squares (ILS), Estimation of an Over-Identified Equation: The Two-Stage Least
Squares (TSLS) |
* Tentaive, subject to change.