This paper addresses the open debate about the usefulness of high-frequency (HF) data in large-scale portfolio allocation. Daily covariances are estimated based on HF data of the S&P 500 universe employing a blocked realized kernel estimator. We propose forecasting covariance matrices using a multi-scale spectral decomposition where volatilities, correlation eigenvalues and eigenvectors evolve on different frequencies. In an extensive out-of-sample forecasting study, we show that the proposed approach yields less risky and more diversified portfolio allocations as prevailing methods employing daily data. These performance gains hold over longer horizons than previous studies have shown.
{"title":"The Merit of High-Frequency Data in Portfolio Allocation","authors":"N. Hautsch, Lada M. Kyj, P. Malec","doi":"10.2139/ssrn.1926098","DOIUrl":"https://doi.org/10.2139/ssrn.1926098","url":null,"abstract":"This paper addresses the open debate about the usefulness of high-frequency (HF) data in large-scale portfolio allocation. Daily covariances are estimated based on HF data of the S&P 500 universe employing a blocked realized kernel estimator. We propose forecasting covariance matrices using a multi-scale spectral decomposition where volatilities, correlation eigenvalues and eigenvectors evolve on different frequencies. In an extensive out-of-sample forecasting study, we show that the proposed approach yields less risky and more diversified portfolio allocations as prevailing methods employing daily data. These performance gains hold over longer horizons than previous studies have shown.","PeriodicalId":178382,"journal":{"name":"ERN: Portfolio Optimization (Topic)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129260252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The inquiries to return predictability are traditionally limited to the first two moments, mean and volatility. Analogously, literature on portfolio selection also stems from a moment-based analysis with up to the fourth moment being considered. This paper develops a distribution-based framework for both return prediction and portfolio selection. More specifically, a time-varying return distribution is modeled through quantile regression and copulas, using the quantile approach to extract information in marginal distributions and copulas to capture dependence structure. A nonlinear utility function is proposed for portfolio selection which utilizes the full underlying return distribution. An empirical application to US data highlights not only the predictability of the stock and bond return distributions, but also the additional information provided by the distributional approach which cannot be captured by the traditional moment-based methods.
{"title":"Return Prediction and Portfolio Selection: A Distributional Approach","authors":"Min Zhu","doi":"10.2139/ssrn.1964030","DOIUrl":"https://doi.org/10.2139/ssrn.1964030","url":null,"abstract":"The inquiries to return predictability are traditionally limited to the first two moments, mean and volatility. Analogously, literature on portfolio selection also stems from a moment-based analysis with up to the fourth moment being considered. This paper develops a distribution-based framework for both return prediction and portfolio selection. More specifically, a time-varying return distribution is modeled through quantile regression and copulas, using the quantile approach to extract information in marginal distributions and copulas to capture dependence structure. A nonlinear utility function is proposed for portfolio selection which utilizes the full underlying return distribution. An empirical application to US data highlights not only the predictability of the stock and bond return distributions, but also the additional information provided by the distributional approach which cannot be captured by the traditional moment-based methods.","PeriodicalId":178382,"journal":{"name":"ERN: Portfolio Optimization (Topic)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115347748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：