Summer Schools

Econometric Methods

students working with trading and computational finance software

Econometric methods for high-dimensional empirical macroeconomic models Summer School

Join Dimitris Korobilis, a Professor of Finance at the University of Essex Business School and a senior fellow of the Rimini Center for Economic Analysis as he presents the econometric methods relevant for the analysis of large financial and macroeconomic time series. 

This three day event will be taking place from Monday 9 September to Wednesday 11 September 2019. 


Key details: 

  • Date: Monday 9 September – Wednesday 11 September 2019
  • Location: Colchester Campus, Essex Business School
  • Event speaker: Professor Dimitris Korobilis
  • Event type: Lectures accompanied by lab sessions
  • Event organiser: Essex Business School
  • Contact details: econometrics_ebs@essex.ac.uk

Overview

The main aim of this course is to help develop an understanding of econometric methods relevant for the analysis of large financial and macroeconomic time series. The emphasis throughout this course is on (Bayesian) estimation and computation, and specification of flexible models. Several topics will be covered and examples from macroeconomics and finance will be given.

Teaching Programme

This summer school will introduce a very large spectrum of time series models used in macroeconomics and finance. Instead of focusing on the theoretical time-series properties of these popular models, these sessions will delve deeply into estimation issues which are of practical importance for applied researchers and PhDs/interns. Particular attention will be given to the use of Bayesian methods in order to tackle estimation with “more variables than observations”.

 

Monday 9 September 2019: 

Lecture 1: Univariate Bayesian approaches with many predictors (3 hrs)
  • Bayesian Inference
  • Bayesian Computation
  • Introduction to Bayesian regression
  • Shrinkage and model selection (penalized regression)
    Lab 1: Bayesian model selection and shrinkage algorithms for regression problems (3 hrs)
    • Stochastic Search Variable Selection
    • The Bayesian Lasso

    Tuesday 10 September 2019:

    Lecture 2: Bayesian multivariate inference (3 hrs) 
    • Multivariate regression
    • Vector autoregressions
    • Factor models (static Factor model, FAVAR, DFM)
    • Multi-country VARs (panel VARs, global factor VARs)
    • Large VARs and TVP-VARs 
      Lab 2: Bayesian VAR inference (3 hrs)
      • BVAR with different priors using MCMC
      • Factor-augmented VAR for measuring monetary policy
      • Large time-varying parameter VAR 

        Wednesday 11 September 2019:

        Lecture 3a: Univariate classical inferential procedures with many predictors (2 hrs)
        • Omitted variable bias
        • Extreme Bounds Analysis
        • Model selection, Information–theoretic model averaging
        • Dynamic factor models
        • Forecast combinations 
        Lecture 3b: Bayesian Machine Learning Inference in macroeconomics (2 hrs)
        • Parallel MCMC
        • Approximate algorithms for inference (variational Bayes, message passing algorithms)
        • Simplifying the model 
          Lab 3: Inference in regressions with many predictors (2 hrs)
          • Application 1: Inflation forecasting using Dynamic Model Averaging
          • Application 2: Variational Bayes inference in time-varying parameter models
          • Application 3: Forecasting with many predictors using message passing algorithms

            Booking and Eligibility

            This summer school would be of interest to advanced PHD students in Economics and central bank staff (e.g. European Central Bank), as well as other international organizations (e.g. OECD, European Investment Bank).

             

            Basic knowledge of regression and time series models is necessary for this course. Note that focus is on estimation methods for macroeconomic time series models, so basic time series concepts such as autocorrelation, or stationarity should be well understood.

             

            Distributions such as the Normal, Bernoulli, Gamma, and Wishart will be relied heavily on so students should be familiar with the concept of a p.d.f., a c.d.f, and their basic functional forms. Additionally, basic knowledge of state-space models and the Kalman filter is essential in order to be able to follow extensions of various models to stochastic volatility and time-varying parameters.

             

            Computations are in MATLAB. All relevant code is provided in a very accessible form, so that even delegates with no knowledge of programming can attend this class. Nevertheless, individuals who are serious about using Big Data econometrics in their research, are expected to have at least some basic MATLAB skills (e.g. know how to estimate a regression with OLS using basic commands, i.e. " >> beta_OLS = X/Y ").

            If you are interested in applying please submit your CV to econometrics_ebs@essex.ac.uk in order to pass an initial screening. If successful, you will be directed to our payment page.

            Fees

            Programme fees differ depending on whether you are an Essex Proficio student, External PHD student or a commercial delegate. 

            • Essex PhDs/MSc/MPhil students: £300
            • External PhDs/MSc/MPhil students: £400
            • All other participants, including academics and commercial delegates: £900

            This year’s Summer School fees are competitively priced and include: 

            • access to three days’ worth of courses
            • one ticket to the opening evening reception on Monday
            • lunch on each teaching day
            • complimentary car parking permits for the duration of your stay
            • a delegate pack full of resources, information, and memorabilia from your time with us
            • hardcopy certification upon course completion, endorsed by the University of Essex and the Essex Business School.

            Please note that this fee does not include accommodation. For help finding suitable accommodation please view the information below.

            Accommodation

            Colchester Campus accommodation for our summer school will need to be booked separately at a fee of £55 per night, bed andbreakfast. Instructions on how to book on campus accommodation will be sent to you once your place on the summer school is confirmed. 

            Colchester has a diverse selection of accommodation to suit a variety of budgets, ranging from friendly B&Bs, guest houses and historic and modern hotels. 

            The following websites may be useful when booking short term accommodation offsite:

            • Wivenhoe House Hotel - Just five minutes’ walk from the centre of our Colchester campus, Wivenhoe House Hotel provides the perfect setting for a more luxurious overnight stay, offering guests somewhere to dine in style, relax, work or rest.
            • Rose and Crown
            • Premier Inn
            • Booking.com

            Travel

            The University of Essex’s Colchester Campus, is just two miles from the historic centre of Colchester – England’s oldest recorded town.

            Set in over 200 acres of beautiful parkland, it is just one hour from London and Stansted Airport, and is home to over 20 academic departments and schools.

            Find out more about travelling to Colchester Campus.

            Speaker Bio

            Dimitris Korobilis

            Dimitris Korobilis

            Professor

            Finance, Essex Business School

            Dimitris Korobilis work focuses on high-dimensional inference in econometrics with emphasis on time-series models for macroeconomics and finance. He is currently in the top 4% in the world of all researchers in economics and finance according to REPEC and ranking in the top 1% in the world (~300 among 50,000+ registered economists) if only counting output and citations over the last decade.   He has extensive teaching experience, having delivered various courses at universities, central banks and government, including teaching specialized courses at the Deutsche Bundesbank on estimation and inference in high-dimensional vector auto regressions for policy evaluation. Dimitris has an excellent reputation in this field, with his work appearing in several journals, including Journal of Econometrics, International Economic Review and European Economic Review.

            Essex Business School in Colchester
            Essex Business School in Colchester
            Students sitting in winter garden at Essex Business School
            Students sitting in winter garden at Essex Business School
            Get in touch
            Get in touch
            Dimitris Korobilis Professor, Finance, Essex Business School
            Telephone: +44 (0) 1206 874463