|
另外附赠研一上学期的计量大纲,以攒人品,祝好!
Course Outline
I Classical Linear Regression- single equation
(1) Parameter estimation and finite sample distribution under normality.
(2) Large Sample: Modes of convergence, LLN and CLT
(3) Asymptotics of OLS
(4) Generalized least squares
(5) Model misspecification-Omitting variable bias.
(6) Sample selection bias and simultaneous equation bias.
II Maximum Likelihood Estimation
(1) Asymptotics of MLE
(2) Information matrix equality
(3) White’s test for Heteroskedasticity
(4) MLE-related tests: LM. Wald, LR tests. Breusch-Pagan test.
(5) Examples of Application: Binary response model, Poisson count model.
III Stationary Time series and Time series regression
(1) ARMA(p,q)- Stationarity and Estimation.
(2) Univariate time series model: ADL/ARMAX
(3) Diagnostics in Time series regression: Durbin-Watson/LM test for autocorrelated errors.
(4) GARCH models for conditional variance.
(5) Parameter constancy: Chow test and Sup Wald test.
IV Unit Root, Spurious regression and Co-integration
(1) Nonstationary time series with unit root.
(2) Spurious regression
(3) DF and ADF tests
(4) Problems of Unit Root Tests
V Multi-equation models- Reduced form
(1) SUR model
(2)VAR(p): Stationarity and Estimation.
(3) Co-integration and Error correction mechanism.
(4) Usefulness of VAR: Limitations and comments.
版权归朱家祥教授所有
|