The random walk as a forecasting benchmark: drift or no drift?

We examine the proposition that the random walk without drift is more powerful in predicting exchange rates than the random walk with drift. It is demonstrated that there is no theoretical reason why the random walk without drift always outperforms the random walk with drift and that this is an empi...

Full description

Bibliographic Details
Main Authors: Moosa, I., Burns, Kelly
Format: Journal Article
Published: Routledge 2016
Online Access:http://hdl.handle.net/20.500.11937/51456
_version_ 1848758702046183424
author Moosa, I.
Burns, Kelly
author_facet Moosa, I.
Burns, Kelly
author_sort Moosa, I.
building Curtin Institutional Repository
collection Online Access
description We examine the proposition that the random walk without drift is more powerful in predicting exchange rates than the random walk with drift. It is demonstrated that there is no theoretical reason why the random walk without drift always outperforms the random walk with drift and that this is an empirical issue. The results show that while the random walk without drift can outperform the random walk with drift in terms of the RMSE, it fails to do so in terms of the ability to predict the direction of change, measures that take into account magnitude and direction, and in terms of profitability. If the drift factor is allowed to change over time by estimating the model in time-varying parameter terms, the random walk with drift performs even better.
first_indexed 2025-11-14T09:48:11Z
format Journal Article
id curtin-20.500.11937-51456
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:48:11Z
publishDate 2016
publisher Routledge
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-514562017-09-13T15:46:01Z The random walk as a forecasting benchmark: drift or no drift? Moosa, I. Burns, Kelly We examine the proposition that the random walk without drift is more powerful in predicting exchange rates than the random walk with drift. It is demonstrated that there is no theoretical reason why the random walk without drift always outperforms the random walk with drift and that this is an empirical issue. The results show that while the random walk without drift can outperform the random walk with drift in terms of the RMSE, it fails to do so in terms of the ability to predict the direction of change, measures that take into account magnitude and direction, and in terms of profitability. If the drift factor is allowed to change over time by estimating the model in time-varying parameter terms, the random walk with drift performs even better. 2016 Journal Article http://hdl.handle.net/20.500.11937/51456 10.1080/00036846.2016.1153788 Routledge restricted
spellingShingle Moosa, I.
Burns, Kelly
The random walk as a forecasting benchmark: drift or no drift?
title The random walk as a forecasting benchmark: drift or no drift?
title_full The random walk as a forecasting benchmark: drift or no drift?
title_fullStr The random walk as a forecasting benchmark: drift or no drift?
title_full_unstemmed The random walk as a forecasting benchmark: drift or no drift?
title_short The random walk as a forecasting benchmark: drift or no drift?
title_sort random walk as a forecasting benchmark: drift or no drift?
url http://hdl.handle.net/20.500.11937/51456