Adame-Garcia, Victor
[Verfasser:in]
;
Fernández Rodríguez, Fernando
[Sonstige Person, Familie und Körperschaft];
Sosvilla-Rivero, Simon
[Sonstige Person, Familie und Körperschaft]
Resolution of Optimization Problems and Construction of Efficient Portfolios
Erschienen in:Institut de Recerca en Economia Aplicada Regional i Pública, Document de Treball ; No. 2017/02
Umfang:
1 Online-Ressource (43 p)
Sprache:
Englisch
DOI:
10.2139/ssrn.2909103
Identifikator:
Entstehung:
Anmerkungen:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments January 26, 2017 erstellt
Beschreibung:
We assess the effectiveness of various portfolio optimization strategies (only long allocations) applied to the components of the Euro Stoxx 50 index during the period 2002-2015. The sample under study contemplates episodes of high volatility and instability in financial markets, such as the Global Financial Crisis and the European Debt Crisis. This implies a real challenge in portfolio optimization strategies, since all the methodologies used are restricted to the assignment of positive weights. We use the daily returns for the asset allocation with a three year estimation window, keeping the assets in portfolio for one year.In the context of strategies with short-selling constraints, we contribute to the debate on whether naive diversification proves to be an effective alternative for the construction of the portfolio, as opposed to the portfolio optimization models. To that end, we analyse the out-of-sample performance of 16 strategies for the selection of assets and weights in the main stock index of the euro area. Our results suggest that a large number of strategies outperform both the naive strategy and the Euro Stoxx 50 index in terms of the profitability and Sharpe's ratio. Furthermore, the portfolio strategy based on the maximization of the diversification ratio provides the highest return and the classical strategy of mean-variance renders the highest Sharpe ratio, which is statistically different from the Euro Stoxx 50 index in the period under study