The unbeatable random walk in exchange rate forecasting: Reality or myth?

It is demonstrated that the conventional monetary model of exchange rates can (irrespective of the specification, estimation method or the forecasting horizon) outperform the random walk in out-of-sample forecasting if forecasting power is measured by direction accuracy and profitability. Claims of...

Full description

Bibliographic Details
Main Authors: Moosa, I., Burns, Kelly
Format: Journal Article
Published: Elsevier 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/11881
_version_ 1848747923222822912
author Moosa, I.
Burns, Kelly
author_facet Moosa, I.
Burns, Kelly
author_sort Moosa, I.
building Curtin Institutional Repository
collection Online Access
description It is demonstrated that the conventional monetary model of exchange rates can (irrespective of the specification, estimation method or the forecasting horizon) outperform the random walk in out-of-sample forecasting if forecasting power is measured by direction accuracy and profitability. Claims of outperforming the random walk in terms of the root mean square error are false because they are typically based on the introduction of dynamics, hence a random walk component, commonly without testing for the statistical significance of the difference between root mean square errors. And even if proper hypothesis testing reveals that a dynamic model outperforms the random walk, this amounts to beating the random walk by a random walk with the help of some explanatory variables. The failure of conventional macroeconomic models to outperform the random walk in terms of the root mean square error should be expected rather than considered to be a puzzle.
first_indexed 2025-11-14T06:56:51Z
format Journal Article
id curtin-20.500.11937-11881
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:56:51Z
publishDate 2014
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-118812017-09-13T16:06:10Z The unbeatable random walk in exchange rate forecasting: Reality or myth? Moosa, I. Burns, Kelly Exchange rate models Random walk Forecasting Monetary model Direction accuracy It is demonstrated that the conventional monetary model of exchange rates can (irrespective of the specification, estimation method or the forecasting horizon) outperform the random walk in out-of-sample forecasting if forecasting power is measured by direction accuracy and profitability. Claims of outperforming the random walk in terms of the root mean square error are false because they are typically based on the introduction of dynamics, hence a random walk component, commonly without testing for the statistical significance of the difference between root mean square errors. And even if proper hypothesis testing reveals that a dynamic model outperforms the random walk, this amounts to beating the random walk by a random walk with the help of some explanatory variables. The failure of conventional macroeconomic models to outperform the random walk in terms of the root mean square error should be expected rather than considered to be a puzzle. 2014 Journal Article http://hdl.handle.net/20.500.11937/11881 10.1016/j.jmacro.2014.03.003 Elsevier restricted
spellingShingle Exchange rate models
Random walk
Forecasting
Monetary model
Direction accuracy
Moosa, I.
Burns, Kelly
The unbeatable random walk in exchange rate forecasting: Reality or myth?
title The unbeatable random walk in exchange rate forecasting: Reality or myth?
title_full The unbeatable random walk in exchange rate forecasting: Reality or myth?
title_fullStr The unbeatable random walk in exchange rate forecasting: Reality or myth?
title_full_unstemmed The unbeatable random walk in exchange rate forecasting: Reality or myth?
title_short The unbeatable random walk in exchange rate forecasting: Reality or myth?
title_sort unbeatable random walk in exchange rate forecasting: reality or myth?
topic Exchange rate models
Random walk
Forecasting
Monetary model
Direction accuracy
url http://hdl.handle.net/20.500.11937/11881