BAEcon Economics

In this unit students will progress their development of econometrics knowledge and skills continuing from Year 2 Econometrics. Students will learn about the important method of maximum likelihood estimation which will open up estimation for a large class of models. Students will also learn about the main building blocks of time-series modelling which will allow them to continue on to the studies of more advanced methods. 

ECON20110

To extend the material introduced in Econometrics to; a) cover models used for the analysis of microdata (particularly data with limited dependent responses), and to; b) introduce models for the analysis of macro-economic time series data.

Students should be able to:

1. understand the use of the method of Maximum Likelihood to estimate and test IID econometric models,
2. extend the range of their microdata modelling capabilities to deal with non-linear, particularly binary, response variables,
3. understand stationary time series processes
4. formalize the notion of non-stationarity and test for its presence,
5. use VARs to model multivariate time series.

Provisional  

Part I: Theory and Microdata models

IA: OLS using matrix algebra

IB. Theory: Parametric Maximum Likelihood  
for IID data.

IC. Binary Response Data models

ID. Another model from the following set {count, ordinal, multinomial, sample selection}

Software: R

Part II: Time series (Macrodata)  
models.

IIA. Stationary time series processes (ARIMA modeling, including seasonality)

IIB. Unit roots.

IIC. Introduction to VARs  

Software:  
R  

Synchronous activities (such as Lectures or Review and Q&A sessions, and tutorials), and guided self-study

Understand the theory and practice of Maximum Likelihood estimation and how it is applied in a variety of different modelling contexts 

Understand the importance of time-series properties (like stationarity) and testing for these properties in the context of time-series modelling 

Develop a solid, intuitive and theoretical grasp of the dangers, pitfalls and problems encountered in applied modelling

Critically analyse, appraise and interpret work in the area of applied economics 

Have practical experience of the application of econometric methods based on practical exercises using economic datasets

Further develop statistical software skills 

Select and deploy relevant information and use these effectively in the written communication of ideas

One Coursework –  emprical analysis in R for Part I 1,000 words (25%)

Exam – 2 hours (75%) 

In tutorial discussions and solutions provided

On-script and group level feedback

While there is a core text, other references (journals articles as well as texts) maybe be cited as appropriate.

Core text: 

Verbeek (2017), A Guide to Modern Econometrics. (earlier editions may also be suitable).