Heterogeneous agents, the financial crisis and exchange rate predictability

Heterogeneous agents, the financial crisis and exchange rate predictability

•We build an empirical heterogeneous agent model for 6 currencies.•Individual agent forecasts are constructed from DMA framework.•Our daily out-of-sample R2 relative to RW can be as high as 1.41% and are highly significant.•Our model forecasts yield annualized Sharpe ratios of up to 0.89 and perform...

Full description

Saved in:
Bibliographic Details
Published in:Journal of international money and finance Vol. 60; pp. 313 - 359
Main Authors: Buncic, Daniel, Piras, Gion Donat
Format: Journal Article
Language:English
Published: Kidlington Elsevier Ltd 01-02-2016
Elsevier Science Ltd
Subjects:
Economic crisis
Economic forecasting
Economic forecasts
Empirical heterogeneous agent model
Exchange rate predictability
Exchange rates
Financial crisis
Forecasting
Foreign exchange rates
International trade
Macroeconomics
Model combination
State-space modelling
Studies
C53
Model combination
C52
Empirical heterogeneous agent model
C22
State-space modelling
Exchange rate predictability
F31
E17
G17
Forecasting
Financial crisis
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•We build an empirical heterogeneous agent model for 6 currencies.•Individual agent forecasts are constructed from DMA framework.•Our daily out-of-sample R2 relative to RW can be as high as 1.41% and are highly significant.•Our model forecasts yield annualized Sharpe ratios of up to 0.89 and performance fees above 460 basis points.•Our predictability results break down after February 2009, are strongest after Lehman Brothers collapse. We construct an empirical heterogeneous agent model which optimally combines forecasts from fundamentalist and chartist agents and evaluates its out-of-sample forecast performance using daily data covering an overall period from January 1999 to June 2014 for six of the most widely traded currencies. We use daily financial data such as level, slope and curvature yield curve factors, equity prices, as well as risk aversion and global trade activity measures in the fundamentalist agent's predictor set to obtain a proxy for the market's view on the state of the macroeconomy. Chartist agents rely upon standard momentum, moving average and relative strength index technical indicators in their predictor set. Individual agent specific forecasts are constructed using a flexible dynamic model averaging framework and are then aggregated into a model combined forecast using a forecast combination regression. We show that our empirical heterogeneous agent model produces statistically significant and economically sizeable forecast improvements over a random walk benchmark.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0261-5606
1873-0639
DOI:10.1016/j.jimonfin.2015.09.006