1,720,977 research outputs found
Are Smart Beta strategies suitable for hedge fund portfolios?
No full textIn the equity context different Smart Beta strategies (such as the equally weighted, global minimum variance, equal risk contribution and maximum diversified ratio) have been proposed as alternatives to the cap-weighted index. These new approaches have attracted the attention of equity managers as different empirical analyses demonstrate the superiority of these strategies with respect to cap-weighted and to strategies that consider only mean and variance. In this paper we focus our attention to hedge fund index portfolios and analyze if the results reported in the equity framework are still valid. We consider hedge fund index and equity portfolios, the approaches used for portfolio selection are the four 'Smart Beta' strategies, mean-variance and mean-variance-skewness. In the two latter approaches the Taylor approximation of a CARA expected utility function and the Polynomial Goal Programing (PGP) have been used. The obtained portfolios are analyzed in the in-sample as well as in the out-of-sample perspectives
Portfolio optimization using modified herfindahl constraint
No full textModern portfolio theory started with Markowitz (J Financ 7(1):77–91, 1952; Portfolio selection efficient diversification of investments. Wiley, New York, 1959). Early works developed necessary conditions on utility function that would result in mean-variance theory being optimal, see Tobin (Rev Econ Stud 25(2):65–86, 1958). Recently, considering the stylized facts of asset returns, mean-variance model has been extended to higher moments. Despite all, empirical evidence has shown that mean-variance model and its variants often yield overly concentrated portfolios. Portfolio diversification is still an open question. To avoid this problem different constraints have been introduced in the portfolio optimization procedure. In this paper we study from an empirical point of view the impact of imposing a constraint on the Modified Herfindahl index of the portfolio, in case of mean-variance and mean-variance-skewness optimization. We find that imposing a constraint on the level of the portfolio diversification leads to better out of sample performance and significant gains, despite the use of shrinkage estimators for moments and comoments, in particular when long estimation periods are considered
A welcome to the jungle of continuous-time multivariate non-Gaussian models based on Lévy processes applied to finance
Full text linkIn this paper we review the large and growing literature on continuous-time multivariate non-Gaussian models based on Levy processes applied to finance and proposed in the literature in the last years. We explain the empirical motivation and the idea behind each approach. Then, we study the models focusing on the parsimony of the number of parameters, the properties of the dependence structure, and the computational tractability. For each parametric class we analyze the main features, we provide the characteristic function, the marginal moments up to order four, the covariances and the correlations. Furthermore, we survey the methods proposed in literature to calibrate these models on the time-series of log-returns, with a view toward practical applications and possible numerical issues. Finally, to empirically assess the differences between models, we conduct an analysis on a five-dimensional series of stock index log-returns
Optimal hedge fund allocation with improved estimates for coskewness and cokurtosis parameters
No full textRobust bi-objective mean-CVaR portfolio selection: Applications to energy sector
Full text linkA new approach to optimizing or hedging a portfolio of financial positions is presented and tested with applications to energy market. Motivated by uncertainty in the estimation of problem data we consider robust bi-objective optimization problems with mean and conditional value-at-risk objective functions where the underlying probability distribution of portfolio return is only known to belong to a certain set. To tackle the problem of uncertainty we consider two different approaches: in the first one, uncertainty is represented by an elliptic set centered at the sample estimators of mean and covariance matrix; in the second one, uncertainty takes into account experts beliefs. For both approaches, we derive analytical semi-closed-form solutions for the worst case mean-CVaR portfolio; in addition, we provide a characterization of the location of the robust Pareto frontier with respect to the corresponding original Pareto frontier
Portfolio allocation using multivariate variance gamma models
No full textIn this paper we investigate empirically the effect of using higher moments in portfolio allocation when parametric and non parametric models are used. The non parametric model considered in this paper is the sample approach while the parametric one is constructed assuming Multivariate Variance Gamma (MVG henceforth) joint distribution for asset returns. We consider the MVG models proposed by Madan and Seneta (1990), Semeraro (2006) and Wang (2009).We perform an out-of-sample analysis comparing the optimal portfolios obtained using the MVG models and the sample approach. Our portfolio is composed of 18 assets selected from the S&P500 Index and the dataset consists in daily returns observed in the period ranging from 01/04/2000 to 01/09/201
Lambda value at risk and regulatory capital: a dynamic approach to tail risk
Full text linkThis paper presents the first methodological proposal of estimation of the ΛVaR . Our approach is dynamic and calibrated to market extreme scenarios, incorporating the need of regulators and financial institutions in more sensitive risk measures. We also propose a simple backtesting methodology by extending the VaR hypothesis-testing framework. Hence, we test our ΛVaR proposals under extreme downward scenarios of the financial crisis and different assumptions on the profit and loss distribution. The findings show that our ΛVaR estimations are able to capture the tail risk and react to market fluctuations significantly faster than the VaR and expected shortfall. The backtesting exercise displays a higher level of accuracy for our ΛVaR estimations
A new discrete exponential distribution: properties and applications
Full text linkIn this work, we propose a novel discrete counterpart to the continuous exponential random variable. It is defined on N0=0,1,2,⋯ and is constructed to have a step-wise cumulative distribution function that minimizes the Cramér distance to the continuous cumulative distribution function of the exponential random variable. We show that its distribution is a particular case of the zero-modified geometric distribution. The probability mass function is analyzed in detail, and the characteristic function is derived, from which the moments of the distribution can be readily obtained. The failure rate function, the zero-modification index, Shannon’s entropy, and the stress-strength reliability parameter are also derived and discussed. Parameter estimation is examined, by considering the maximum likelihood method, the method of moments, and the least-squares method. A two-parameter generalization is also introduced and investigated. A real data analysis is provided, where the proposed distribution is fitted to a data set and compared to a well-known counting distribution. Finally, an application of the proposed discrete model is presented, focusing on the determination of the distribution of a compound sum of i.i.d. continuous random variables, with a specific application to the insurance field
Lévy CARMA models for shocks in mortality
No full textRecent literature on mortality modeling suggests to include in the dynamics of mortality rates the effects of time, age, the interaction of these two and a term for possible shocks. In this paper we investigate models that use Legendre polynomials for the inclusion of age and cohort effects. In order to capture the dynamics of the shock term it is suggested to consider continuous autoregressive moving average (CARMA) models due to their flexibility in reproducing different autoregressive profiles of the shock term. In order to validate the proposed model, different life tables are considered. In particular the male life tables for New Zealand, Taiwan and Japan are used for the presentation of in-sample fitting. Empirical analysis suggests that the inclusion of more flexible models such as higher-order CARMA(p,q) models leads to better in-sample fitting
- …
