Centre for Finance, Credit and Macroeconomics (CFCM)

Decision-Making using Macroeconomic Models - Research Programme

Overview | Research projects | Selected publications | Related research links

Overview

Considerable work has been undertaken over recent years to develop tools and procedures which facilitate the use of macroeconomic models when making decisions. The procedures focus particularly on the use of model-based forecasts of the future or, where data is published only with a delay, on model-based 'nowcasts' of the current state of the economy.

The work can be grouped according to its focus on Forecasting and decision-making or on Real-time economics (including the use of direct measures of expectations).

  • Forecasting and decision-making. Here, it is recognised that the forecasts produced by macroeconomic modellers are not helpful in making decisions when they are presented as point forecasts (even where they are accompanied by confidence intervals to indicate the degree of uncertainty surrounding the forecasts). Decision-makers are interested in the likely outcome of their decisions which means that they require forecasts of the entire range of possible outcomes (in the form of density functions or, where many variables are involved, joint density functions) or forecasts of the likelihood of specified events occurring. Tools for the production and interpretation of density forecasts and event probability forecasts are therefore important.
  • Real-time economics. The macroeconomic data required by decision-makers is often available only with a lag or, when it is made available contemporaneously, is subject to considerable subsequent revision. This makes today's decision-making more complicated while decisions that have been made in the past can be difficult to interpret when viewed using only the most up-to-date (revised) data. The analysis of real-time datasets - where all vintages of data are considered, showing data as it is first released and subsequently revised - is essential in understanding the past and in making decisions today. An important element of real-time datasets is the direct measures of expectations of future variables as published in surveys since these provide information of what agents believed the current and future state of the economy would be in real time.

The tools developed under these headings are most easily applied to simple Vector-Autoregessive (VAR) or cointegrating VAR models; see, for example, Garratt, Lee, Pesaran and Shin's (2006) volume on Global and National Macroeconometric Modelling which describes the construction of economically-meaningful macroeconomic models obtained using cointegrating VAR techniques. But the procedures are typically based on simulation methods and so they are applicable to macroeconomic model obtained through any estimation technique.

Back to top ^ 

Research projects

The work has been generously funded through various research projects including:

  • UK Monetary Policy and Probability Event Forecasting Using Real Time Data (http://www.esrc.ac.uk/my-esrc/grants/RES-000-22-1342/read/) funded by the UK's Economic and Social Research Council
  • Producing Robust Density Forecasts: Applications to Monetary Policy (http://www.esrc.ac.uk/my-esrc/grants/RES-062-23-1753/read/) funded by the UK's Economic and Social Research Council
  • Australian Real Time Data: Construction, Analysis and Implications for Real Time Policy Making (http://www.economics.unimelb.edu.au/Real-Time_Macroeconomic_Database_for_Australia/Home.html) funded by the Australian Research Council

The work undertaken during the project is described in more detail via the links above.

Back to top ^ 

Selected publications

Forecasting and Decision-Making

  • "Investing Under Model Uncertainty: Decision-Based Evaluation of Exchange Rate Forecasts in the US, UK and Japan", Journal of International Money and Finance , 2010, 29, 3, 403-422, by A. Garratt and K. Lee.
  • "Decision-Making in Hard Times: What is a Recession, Why Do We Care and When Do We Know We Are in One?", 2011, 22, 1, 43-60, North American Journal of Economics and Finance , by K. Lee and K. Shields.
  • "Nowcasting, Business Cycle Dating and the Interpretation of New Information When Real Time Data is Available", Discussion Paper in Economics no. 08/17, University of Leicester, June 2008, by K. Lee, N. Olekalns and K. Shields.
  • "Measuring the Natural Output Gap Using Actual and Expected Output Data", Discussion Paper , University of Nottingham, March 2011, by A. Garratt, K. Lee and K. Shields.
  • "The Meta Taylor Rule", Discussion Paper , University of Nottingham, March 2011, by K. Lee, J. Morley and K. Shields.
  • "Forecasting Exchange Rate Densities Using Panels and Model Averaging", Birkbeck Working Papers in Economics and Finance, August 2011, by A. Garratt and E. Mise.

Real-Time Economics

  • "UK Real-time Macro Data Characteristics", Economic Journal , 2006, 116, F119-F135, February, by A.Garratt and Shaun Vahey
  • "Overcoming Measurement Error Problems in the Use of Survey Data on Expectations", Economic Record, 2007, 83, 303-316, by K. Lee and K. Shields.
  • "Forecasting Real-Time Data Revisions in the Presence of Model Uncertainty", Economic Journal, 2008, 118, 530, 1128-1144, by A.Garratt, G. Koop and S. Vahey
  • "Real Time Representations of the Output Gap", Review of Economics and Statistics , 2008, 90, 4, 792-804, by A. Garratt, K. Lee, E. Mise and K. Shields.
  • "Real Time Probability Forecasts of UK Macroeconomic Events", National Institute Economic Review, 2008, 203, 78-90, by A. Garratt, K. Lee and S. Vahey.
  • "Real-Time Prediction with UK Monetary Aggregates in the Presence of Model Uncertainty", Journal of Business Economics and Statistics, 2009, 27, 4, 480-491, by A.Garratt, G. Koop, E. Mise and S. Vahey
  • "Real Time Representations of the UK Output Gap in the Presence of Model Uncertainty", International Journal of Forecasting , 2009, 25, 81-102, by A. Garratt, K. Lee, E. Mise and K. Shields.
  • "Real-time Inflation Forecast Densities from Ensemble Phillips Curves", North American Journal of Economics and Finance, 2011, 22, 1, 77-87, by A. Garratt, J. Mitchell, S. Vahey and E. Waverley
  • "The Australian Real-Time Database: An Overview and an Illustration of its Use in Business Cycle Analysis�, University of Melbourne Discussion Paper #??, August 2011, by K. Lee, N. Olekalns, N., K. Shields, and Z. Wang.
  • "Australian Real-Time Data: Construction, Analysis and Implications for Real-Time Policy Making", University of Melbourne Discussion Paper #??, August 2011, by K. Lee, N. Olekalns, N., K. Shields, and Z. Wang.

Long-run Structural Modelling

  • Global and National Macroeconometric Modelling: A Long-Run Structural Approach, 2006, Oxford University Press [400 pages], by A. Garratt, K. Lee, M.H. Pesaran and Y.Shin.
  • "Does One Size Fit All?; Modelling Macroeconomic Linkages in the West African Economic and Monetary Union", (forthcoming in) Economic Change and Restructuring, by D. Fielding, K. Lee and K. Shields.

Back to top ^ 

Related research links

Useful Real Time References

  • Frontiers of Real-Time Data Analysis by Dean Croushore, Journal of Economic Literature, vol. 49, issue 1, pp. 72-100, March 2011.
  • Real-Time Bibliography compiled by Dean Croushore (the University of Richmond)

Real Time Datasets

Back to top ^

 

Centre for Finance, Credit and Macroeconomics

Sir Clive Granger Building
University of Nottingham
University Park
Nottingham, NG7 2RD

Enquiries: hilary.hughes@nottingham.ac.uk