Advanced econometrics II : time series - part 1

lecon2601a  2019-2020  Louvain-la-Neuve

Advanced econometrics II : time series - part 1
Note du 29 juin 2020
Sans connaitre encore le temps que dureront les mesures de distances sociales liées à la pandémie de Covid-19, et quels que soient les changements qui ont dû être opérés dans l’évaluation de la session de juin 2020 par rapport à ce que prévoit la présente fiche descriptive, de nouvelles modalités d’évaluation des unités d’enseignement peuvent encore être adoptées par l’enseignant ; des précisions sur ces modalités ont été -ou seront-communiquées par les enseignant·es aux étudiant·es dans les plus brefs délais.
2 crédits
15.0 h
Langue
d'enseignement
Anglais
Thèmes abordés
The course must cover the important and essential themes of the econometrics of time series analysis and their application in some fields of economics, like macroeconomics and finance. The basic concepts of stationarity and ergodicity are taught in the prerequisite course. The main themes for this course are those of linear time series models (autoregressive and moving average models), unit roots and cointegration. Both univariate and multivariate models must be taught. For non linear time series models, a selection of topics has to be done mainly among ARCH models, Makov-switching models, and state-space models. In all topics, the themes of model building, evaluation and prediction are included.
Contenu
The course aims to find models that explain dynamical observations in economics. It considers the model-based method and attempts to infer model parameters by iteratively fitting observations with theoretical predictions from trial models. To this aim, it provides a necessary introduction to the basic theory of the following three types series: discrete-time Markov chain, continuous-time Markov chain, and continuous-time and continuous-state Markov processes.
The structure of the course is given as follows (subject to change)
1. Numerical methods
2. Stochastic numerical methods
3. Markov chains
4. Branching process
5. Continuous-time Markov chains
6. Birth and death processes
7. Continuous time Markov processes
8. Diffusion processes
9. Stochastic differential equations
10. Applications: competition, epidemic, population and spatial models
Méthodes d'enseignement
Weekly lecture.
Modes d'évaluation
des acquis des étudiants
Students are expected to complete a take-home final project by themselves. The project will consist of both analytical and empirical questions.
Ressources
en ligne
Bibliographie
William J. Stewart (2009), Probability, Markov Chains, Queues, and Simulation: The mathematical basis of performance modeling, Princeton University Press
Crispin Gardiner (2009), Stochastic Methods: A handbook for the natural and social sciences, 4th Edition , Springer 
Faculté ou entité
en charge
ECON


Programmes / formations proposant cette unité d'enseignement (UE)

Intitulé du programme
Sigle
Crédits
Prérequis
Acquis
d'apprentissage
Master [120] en sciences économiques, orientation économétrie