Monday

What will you learn and implement?

A refresher of descriptive statistics and least squares.

What are the fundamental elements of EViews?

What are the assumptions of least squares?

A refresher of confidence intervals and of hypothesis testing.

How to compute confidence intervals and how to test in EViews.

Tuesday

What will you learn and implement?

How to test on normality, functional form, stability and on linear restrictions.

How to implement these tests in EViews.

How to test on heteroskedasticity and on serial correlation.

How to estimate the model or correct the standard errors in case of heteroskedasticity and/or serial correlation.

How to implement these tests in EViews and how to estimate the model.

What are the consequences of omitted or redundant variables and how to test?

How to detect outliers.

How to implement these tests and how to detect outliers in EViews.

What are the consequences of stochastic regressors? How to test and how to estimate in case regressors are stochastic.

Wednesday

What will you learn and implement?

How to test on stochastic regressors in EViews.

How to estimate simultaneous equation models.

How to estimate Klein’s I simultaneous equation model in EViews.

Wednesday afternoon is free. Enjoy yourself:)  

Thursday

What will you learn and implement?

Building a small model of the French economy. General goal, of the expected economic mechanisms and framework, and of the available data.

Production of a model frame, with fully defined identities and indicative behaviors.

Production of the associated data set.

Control of the consistency between the model and the data.

Estimating the (five) behavioral equations: economic justification, evaluation of the quality of results, convergence to a satisfying version.

Checking the consistency of the completed model.

Friday

What will you learn and implement?

The algorithms for solving models: Newton versus Gauss-Seidel. The control of convergence, and the techniques for improving its speed and probability.

Processing the results.

Discussion on the methods for quality assessment.

Ex-post simulation: evaluation of the predictive quality.

Response to changes in assumptions: techniques, interpretation of results, evaluation of the quality of properties.

The reasons for introducing supply mechanisms.

Re-estimating equations (investment and trade).

Applying cointegration, error correction models.

Updating the model specifications: data, equations.

Comparison of specifications and framework with the first version.

Saturday

What will you learn and implement?

Simulation of the second model version.

Applying the previous tests on the new model.

Comparison of economic properties with the first version.

Assessment of the improvements in predictive ability and properties.

Forecasting techniques.

Introducing the assumptions over the future.

Extrapolating the residuals.

Convergence problems.

Evaluating the quality of the results.

Creating a short term forecast. Adapting the solution to a partly known equilibrium in the short run.

Adapting the specifications to the constraints of a long term solution. Control of the long run stability. Observing how a long term shock improves the diagnosis.