Bias and consistency of the maximum Sharpe ratio

We show that the maximum Sharpe ratio obtained via the Markowitz optimization procedure from a sample of returns on a number of risky assets is, under commonly satisfied assumptions, biased upwards for the population value. Thus investment advice, decisions and assessments based on the estimated Sha...

Full description

Bibliographic Details
Main Authors: Maller, R., Durand, Robert, Lee, P.
Format: Journal Article
Published: Incisive Media Ltd. 2005
Online Access:http://hdl.handle.net/20.500.11937/21491
_version_ 1848750605202358272
author Maller, R.
Durand, Robert
Lee, P.
author_facet Maller, R.
Durand, Robert
Lee, P.
author_sort Maller, R.
building Curtin Institutional Repository
collection Online Access
description We show that the maximum Sharpe ratio obtained via the Markowitz optimization procedure from a sample of returns on a number of risky assets is, under commonly satisfied assumptions, biased upwards for the population value. Thus investment advice, decisions and assessments based on the estimated Sharpe ratio will be overly optimistic. The bias in the estimator is shown theoretically and illustrated using a data set of Spiders and iShares. We obtain bounds on the difference between the sample maximum Sharpe ratio and its population counterpart and show that the sample estimator is consistent for the population value; thus the bias disappears asymptotically under some reasonable assumptions. However, the bias can be significant in finite samples and can persist even in very large samples. We demonstrate this with simulations based on portfolios formed from normally and t-distributed returns. As expected, the over-optimistic risk-return tradeoff predicted by the procedure is not reflected in corresponding good out-of-sample portfolio performance of the Spiders and iShares.
first_indexed 2025-11-14T07:39:29Z
format Journal Article
id curtin-20.500.11937-21491
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:39:29Z
publishDate 2005
publisher Incisive Media Ltd.
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-214912017-01-30T12:25:31Z Bias and consistency of the maximum Sharpe ratio Maller, R. Durand, Robert Lee, P. We show that the maximum Sharpe ratio obtained via the Markowitz optimization procedure from a sample of returns on a number of risky assets is, under commonly satisfied assumptions, biased upwards for the population value. Thus investment advice, decisions and assessments based on the estimated Sharpe ratio will be overly optimistic. The bias in the estimator is shown theoretically and illustrated using a data set of Spiders and iShares. We obtain bounds on the difference between the sample maximum Sharpe ratio and its population counterpart and show that the sample estimator is consistent for the population value; thus the bias disappears asymptotically under some reasonable assumptions. However, the bias can be significant in finite samples and can persist even in very large samples. We demonstrate this with simulations based on portfolios formed from normally and t-distributed returns. As expected, the over-optimistic risk-return tradeoff predicted by the procedure is not reflected in corresponding good out-of-sample portfolio performance of the Spiders and iShares. 2005 Journal Article http://hdl.handle.net/20.500.11937/21491 Incisive Media Ltd. restricted
spellingShingle Maller, R.
Durand, Robert
Lee, P.
Bias and consistency of the maximum Sharpe ratio
title Bias and consistency of the maximum Sharpe ratio
title_full Bias and consistency of the maximum Sharpe ratio
title_fullStr Bias and consistency of the maximum Sharpe ratio
title_full_unstemmed Bias and consistency of the maximum Sharpe ratio
title_short Bias and consistency of the maximum Sharpe ratio
title_sort bias and consistency of the maximum sharpe ratio
url http://hdl.handle.net/20.500.11937/21491