ARC Discovery Early Career Researcher Award

New approaches to estimating nonlinear time-varying macroeconometric models
Joshua Chan
Funded by The Australian Research Council, $365,000, 2015-2017

Summary of Proposal

Quantitative models are essential for formulating good policies. In a changing world, the analysis should be based on models that allow the behavior of the economy to change over time. However, due to computational limitations, one is often restricted to linear models, even when nonlinear ones are more appropriate. This project develops new methods for estimating time-varying nonlinear models. Two important applications are considered: one investigates how the zero lower bound on interest rates affects the monetary policy transmission mechanism and the other examines how uncertainties about monetary and fiscal policy affect economic growth and inflation. Both have a strong practical significance for conducting macroeconomic policy.

Impact Statement

This project develops a new method for analyzing time-varying, nonlinear relationships among economic variables. It is used to better understand how policy uncertainties affect economic growth and to examine how the transmission mechanism of monetary policy is affected by the low interest rate that is currently prevalent in many developed economies. This project will therefore provide valuable information to central banks and other policymakers, allowing them to design more effective policies.

Completed Research

My coauthors and I have completed the development of new Bayesian methodology for estimating a class of nonlinear time series models. An important aspect of this project is to develop new computational methods for comparing these models with standard benchmarks. To that end, we have derived a variety of efficient algorithms to compute the marginal likelihood and the deviance information criterion for stochastic volatility models.

The following is a list of papers that have been completed under this project:

  1. Large Bayesian VARs: A Flexible Kronecker Error Covariance Structure
    Joshua Chan (2018)
    Journal of Business and Economic Statistics, forthcoming
    [ Journal Version | Working Paper | Code ]
  2. Bayesian Model Comparison for Time-Varying Parameter VARs with Stochastic Volatility
    Joshua Chan and Eric Eisenstat (2018)
    Journal of Applied Econometrics, 33(4), 509-532
    [ Journal Version | Working Paper | Code ]
  3. Specification Tests for Time-Varying Parameter Models with Stochastic Volatility
    Joshua Chan (2018)
    Econometric Reviews, 37(8), 807-823
    [ Journal Version | Working Paper | Code | Trend Inflation Estimates ]
  4. Efficient Estimation of Bayesian VARMAs with Time-Varying Coefficients
    Joshua Chan and Eric Eisenstat (2017)
    Journal of Applied Econometrics, 32(7), 1277-1297
    [ Journal Version | Working Paper | Code ]
  5. The Stochastic Volatility in Mean Model with Time-Varying Parameters: An Application to Inflation Modeling
    Joshua Chan (2017)
    Journal of Business and Economic Statistics, 35(1), 17-28
    [ Journal Version | Working Paper | Code ]
  6. On the Observed-Data Deviance Information Criterion for Volatility Modeling
    Joshua Chan and Angelia Grant (2016)
    Journal of Financial Econometrics, 14(4): 772-802
    [ Journal Version | Working Paper | Code ]
  7. Modeling Energy Price Dynamics: GARCH versus Stochastic Volatility
    Joshua Chan and Angelia Grant (2016)
    Energy Economics, 54, 182-189
    [ Journal Version | Working Paper | Code ]