Hi A recent paper by Ledoit and Wolf (http://www.iew.uzh.ch/chairs/wolf/team/wolf/publications/jef_2008pdf.pd f) gives you a robust test for two Sharpe ratios being different. Even better is if you go on one of their web sites (Wolf's I believe), you'll find a R routine to do the test for you. And you should definitely look out of sample. Regards, David Jessop ------------------------------ Message: 4 Date: Tue, 09 Dec 2008 16:50:57 +0100 From: Bastian Offermann <bastian2507hk at yahoo.co.uk> Subject: [R-SIG-Finance] performance evaluation and sharpe ratio To: r-sig-finance at stat.math.ethz.ch Content-Type: text/plain; charset=ISO-8859-15; format=flowed Hello all, i am currently doing some portfolio resampling experiments and wonder how to best evaluate different investment strategies based on the sharpe ratio. i do have a time series for 2 equity indices from jan 2002 till dec 2007 of daily log returns (1548 observations) and perform an unconstrained markowitz optimization to obtain both portfolio weights for a given return level. my experiment is based on deMiguel (2007) performing further markowitz optimizations on subsamples of 1300 observations each, i.e. the first sample is r_1, r_2, ..., r_1300, the 2nd sample is r_2, r_3, ..., r_1301 and so on. i finally obtain 249 subsamples and as many portfolio weight vectors. how do i best examine each strategy using the sharpe ratio? in-sample-test? out-of-sample test? any suggestion is highly appreciated. thanks in advance. kind regards b ------------------------------ Issued by UBS AG or affiliates to professional investors for information only and its accuracy/completeness is not guaranteed. All opinions may change without notice and may differ to opinions/recommendations expressed by other business areas of UBS. UBS may maintain long/short positions and trade in instruments referred to. Unless stated otherwise, this is not a personal recommendation, offer or solicitation to buy/sell and any prices/quotations are indicative only. UBS may provide investment banking and other services to, and/or its employees may be directors of, companies referred to. To the extent permitted by law, UBS does not accept any liability arising from the use of this communication. ? UBS 2008. All rights reserved. Intended for recipient only and not for further distribution without the consent of UBS. UBS Limited is a company registered in England & Wales under company number 2035362, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom. UBS AG (London Branch) is registered as a branch of a foreign company under number BR004507, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom. UBS Clearing and Execution Services Limited is a company registered in England & Wales under company number 03123037, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom.
performance evaluation and sharpe ratio
2 messages · david.jessop at ubs.com, Bastian Offermann
thats what i was looking for actually, i am not so much interested in testing, but rather in which time period to use to calculate sharpe ratios. david.jessop at ubs.com schrieb:
Hi A recent paper by Ledoit and Wolf (http://www.iew.uzh.ch/chairs/wolf/team/wolf/publications/jef_2008pdf.pd f) gives you a robust test for two Sharpe ratios being different. Even better is if you go on one of their web sites (Wolf's I believe), you'll find a R routine to do the test for you. And you should definitely look out of sample. Regards, David Jessop ------------------------------ Message: 4 Date: Tue, 09 Dec 2008 16:50:57 +0100 From: Bastian Offermann <bastian2507hk at yahoo.co.uk> Subject: [R-SIG-Finance] performance evaluation and sharpe ratio To: r-sig-finance at stat.math.ethz.ch Message-ID: <493E93E1.3080503 at yahoo.co.uk> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Hello all, i am currently doing some portfolio resampling experiments and wonder how to best evaluate different investment strategies based on the sharpe ratio. i do have a time series for 2 equity indices from jan 2002 till dec 2007 of daily log returns (1548 observations) and perform an unconstrained markowitz optimization to obtain both portfolio weights for a given return level. my experiment is based on deMiguel (2007) performing further markowitz optimizations on subsamples of 1300 observations each, i.e. the first sample is r_1, r_2, ..., r_1300, the 2nd sample is r_2, r_3, ..., r_1301 and so on. i finally obtain 249 subsamples and as many portfolio weight vectors. how do i best examine each strategy using the sharpe ratio? in-sample-test? out-of-sample test? any suggestion is highly appreciated. thanks in advance. kind regards b ------------------------------ Issued by UBS AG or affiliates to professional investors for information only and its accuracy/completeness is not guaranteed. All opinions may change without notice and may differ to opinions/recommendations expressed by other business areas of UBS. UBS may maintain long/short positions and trade in instruments referred to. Unless stated otherwise, this is not a personal recommendation, offer or solicitation to buy/sell and any prices/quotations are indicative only. UBS may provide investment banking and other services to, and/or its employees may be directors of, companies referred to. To the extent permitted by law, UBS does not accept any liability arising from the use of this communication. ? UBS 2008. All rights reserved. Intended for recipient only and not for further distribution without the consent of UBS. UBS Limited is a company registered in England & Wales under company number 2035362, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom. UBS AG (London Branch) is registered as a branch of a foreign company under number BR004507, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom. UBS Clearing and Execution Services Limited is a company registered in England & Wales under company number 03123037, whose registered office is at 1 Finsbury Avenue, London, EC2M 2PP, United Kingdom.