NMAA05025U Econometrics 2: Statistic Analysis of Econometric Time Series (StatØ2)

Volume 2015/2016
Education

MSc Programme in Mathematics-Economics
MsC Programme in Statistics

Content

 

The course introduces and analyzes models and statistical procedures for multivariate observations that are dependent over time. Examples of such data are interest rates and stock prices. The focus is on the autoregressive (AR) model and its multivariate version (VAR), including unit root inference and cointegration analysis. A brief introdution to related non-linear models (e.g. the ARCH-model) is also given. The probability theory and other mathematics necessary to analyze the models and estimation and test procedures is presented. The topics from probability theory include martingales, Markov chains, asymptotic stability, stationarity, mixing, and laws of large number and central limit theorems for time dependt processes. By means of the methods presented in the course, the students will solve theoretical econometric problems and use statistical software to analyse economic time series.

 

Learning Outcome

Knowledge: The course covers the following topics. Dependence and correlation, stationary and mixing stochastic processes, laws of large numbers for dependent sequences, martingales, central limit theorems for martingales, Markov processes, asymptotic stability, linear processes, uni- and multivariate autoregressive processes, estimation and asymptotic statistical theory for time series models, exogeneity, tests for misspecification of time series models, non-linear time series models, autoregressive processes with unit roots, cointegration.


Skills: After the course, the students are expected to be able to apply the key time series models typically used for analysis of macro econometric data, to use statistical software for time series analysis, apply key concepts and methods from the theory of stochastic processes (including martingales, laws of large numbers and central limit theorems) to analyse statistical methods for time series, to formulate and apply likelihood based tests for linear hypotheses and specification tests for time series models, and to determine whether or not a stochastic process is exogenous.


Competences: After the course, the students are expected to be able to analyse macro economic time series statistically at an advanced level and to make predictions of future values of the series, and to be able to theoretically analyse uni- and multivariate time series models and to develop statistical methodology for such models.

Statistik 2 (Stat2) or equivalent.
5 hours of lectures and 3 hours of exercises per week for 7 weeks.
  • Category
  • Hours
  • Exam
  • 35
  • Lectures
  • 35
  • Preparation
  • 90
  • Project work
  • 25
  • Theory exercises
  • 21
  • Total
  • 206
Credit
7,5 ECTS
Type of assessment
Written examination, 3 hours under invigilation
---
Exam registration requirements

2 compulsory written assignments must be handed in and approved.

Aid
All aids allowed

NB: If the exam is held at the ITX, the ITX will provide you a computer. Private computer, tablet or mobile phone CANNOT be brought along to the exam. Books and notes should be brought on paper or saved on a USB key.

Marking scale
7-point grading scale
Censorship form
No external censorship
One internal examiner
Re-exam

30 minutes oral exam with several internal examiners, 7-point grading scale. Compulsory written assignments from the course that are approved and valid do not need to be repeated. Compulsory assignments that have not been approved or are invalid must be handed in no later than one week before the start of the re-exam period.

Criteria for exam assesment

The student must in a satisfactory way demonstrate that he/she has mastered the learning outcome.