| Authors: |
Christopher J. Neely
and Paul A. Weller
and Joshua M. Ulrich
|
| URL: |
http://research.stlouisfed.org/wp/2006/2006-046.pdf |
| Tags: |
algorithms,
genetic
programming
|
| Abstract: |
We analyse the intertemporal stability of returns to
technical trading rules in the foreign exchange market
by conducting true, out-of-sample tests on previously
published rules. The excess returns of the 1970s and
1980s were genuine and not just the result of data
mining. But these profit opportunities had disappeared
by the mid-1990s for filter and moving average (MA)
rules. Returns to less-studied rules, such as channel,
ARIMA, genetic programming and Markov rules, also have
declined, but have probably not completely disappeared.
The volatility of returns makes it difficult to
estimate mean returns precisely. The most likely time
for a structural break in the MA and filter rule
returns is the early 1990s. These regularities are
consistent with the Adaptive Markets Hypothesis (Lo,
2004), but not with the Efficient Markets Hypothesis. |
@techreport{neely:2006-046,
title = {The adaptive markets hypothesis: evidence from the
foreign exchange market},
address = {P.O. Box 442, St. Louis, MO 63166, USA},
author = {Christopher J. Neely and Paul A. Weller and Joshua M. Ulrich},
institution = {Federal Reserve Bank of St. Louis, Research Division},
month = {August},
note = {Revised March 2007},
number = {2006-046B},
type = {Working Paper},
url = {http://research.stlouisfed.org/wp/2006/2006-046.pdf},
year = {2006},
abstract = {We analyse the intertemporal stability of returns to
technical trading rules in the foreign exchange market
by conducting true, out-of-sample tests on previously
published rules. The excess returns of the 1970s and
1980s were genuine and not just the result of data
mining. But these profit opportunities had disappeared
by the mid-1990s for filter and moving average (MA)
rules. Returns to less-studied rules, such as channel,
ARIMA, genetic programming and Markov rules, also have
declined, but have probably not completely disappeared.
The volatility of returns makes it difficult to
estimate mean returns precisely. The most likely time
for a structural break in the MA and filter rule
returns is the early 1990s. These regularities are
consistent with the Adaptive Markets Hypothesis (Lo,
2004), but not with the Efficient Markets Hypothesis.},
size = {52 pages}, notes = {No Download Restriction},
keywords = {algorithms, genetic programming }
}
::