2019/08/22 by Nigel Meade, N. Meade, Meade, N. +5
Decision Sciences · Economics, Econometrics and Finance · Mathematics · Social Sciences · #Artificial intelligence #Computer science #Consistency (knowledge bases) #Econometrics #Economics #Efficient frontier #Ex-ante #FOS: Economics and business #Financial Markets and Investment Strategies #Financial economics #Forecasting Techniques and Applications #Insurance, Mortality, Demography, Risk Management #Mathematics #Modern portfolio theory #Portfolio #Portfolio Management (q-fin.PM) #Portfolio optimization #Selection (genetic algorithm) #Statistic #Statistics #q-fin.PM
paper · pdf · doi:10.48550/arxiv.1908.08442
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/08/22 · arxiv created 2020/06/28 · arxiv updated 2020/06/30 · openalex created_date 2021/02/01 · openalex updated_date 2026/07/28
In the knowledge that the ex-post performance of Markowitz efficient\nportfolios is inferior to that implied ex-ante, we make two contributions to\nthe portfolio selection literature. Firstly, we propose a methodology to\nidentify the region of risk-expected return space where ex-post performance\nmatches ex-ante estimates. Secondly, we extend ex-post efficient set\nmathematics to overcome the biases in the estimation of the ex-ante efficient\nfrontier. A density forecasting approach is used to measure the accuracy of\nex-ante estimates using the Berkowitz statistic, we develop this statistic to\nincrease its sensitivity to changes in the data generating process. The area of\nrisk-expected return space where the density forecasts are accurate, where\nex-post performance matches ex-ante estimates, is termed the consistency\nregion. Under the 'laboratory' conditions of a simulated multivariate normal\ndata set, we compute the consistency region and the estimated ex-post frontier.\nOver different sample sizes used for estimation, the behaviour of the\nconsistency region is shown to be both intuitively reasonable and to enclose\nthe estimated ex-post frontier. Using actual data from the constituents of the\nUS Dow Jones 30 index, we show that the size of the consistency region is time\ndependent and, in volatile conditions, may disappear. Using our development of\nthe Berkowitz statistic, we demonstrate the superior performance of an\ninvestment strategy based on consistent rather than efficient portfolios.\n