Sparse and robust normal and t- portfolios by penalized Lq-likelihood minimization

Two important problems arising in traditional asset allocation methods are the sensitivity to estimation error of portfolio weights and the high dimensionality of the set of candidate assets. In this paper, we address both issues by proposing a new criterion for portfolio selection. The new criterion is a two-stage description of the available information, where the q-entropy, a generalized measure of information, is used to code the uncertainty of the data given the parametric model and the uncertainty related to the model choice. The information about the model is coded in terms of a prior distribution that promotes asset weights sparsity. Our approach carries out model selection and estimation in a single step, by selecting a few assets and estimating their portfolio weights simultaneously. The resulting portfolios are doubly robust, in the sense that they can tolerate deviations from both assumed data model and prior distribution for model parameters. Empirical results on simulated and real-world data support the validity of our approach.

[1]  John E. Beasley,et al.  An evolutionary heuristic for the index tracking problem , 2003, Eur. J. Oper. Res..

[2]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .

[3]  M. Carrasco.  Optimal Portfolio Selection using Regularization Marine Carrasco and Nérée Noumon , 2010 .

[4]  Stephen J. Wright,et al.  Simultaneous Variable Selection , 2005, Technometrics.

[5]  Stéphane Canu,et al.  Recovering Sparse Signals With a Certain Family of Nonconvex Penalties and DC Programming , 2009, IEEE Transactions on Signal Processing.

[6]  P. Frost,et al.  For better performance , 1988 .

[7]  Mário A. T. Figueiredo,et al.  Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems , 2007, IEEE Journal of Selected Topics in Signal Processing.

[8]  Olivier Ledoit,et al.  Honey, I Shrunk the Sample Covariance Matrix , 2003 .

[9]  Peter Winker,et al.  Cardinality versus q-norm constraints for index tracking , 2010 .

[10]  R. Cont.  Empirical properties of asset returns: stylized facts and statistical issues , 2001 .

[11]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[12]  Frank J. Fabozzi,et al.  60 Years of portfolio optimization: Practical challenges and current trends , 2014, Eur. J. Oper. Res..

[13]  Tuo Zhao,et al.  Pathwise Coordinate Optimization for Sparse Learning: Algorithm and Theory , 2014, ArXiv.

[14]  C. Tsallis.  Possible generalization of Boltzmann-Gibbs statistics , 1988 .

[15]  S. Paterlini,et al.  Constructing Optimal Sparse Portfolios Using Regularization Methods , 2014 .

[16]  José A.F. Machado,et al.  Robust Model Selection and M-Estimation , 1993, Econometric Theory.

[17]  M. Best,et al.  On the Sensitivity of Mean-Variance-Efficient Portfolios to Changes in Asset Means: Some Analytical and Computational Results , 1991 .

[18]  Davide Ferrari,et al.  Efficient and Robust Estimation for Financial Returns: An Approach Based on q-Entropy , 2010 .

[19]  R. Jagannathan,et al.  Risk Reduction in Large Portfolios: Why Imposing the Wrong Constraints Helps , 2002 .

[20]  Shie-Shien Yang.  [Multiresponse Estimation with Special Application to Linear Systems of Differential Equations]: Discussion , 1985 .

[21]  Raman Uppal,et al.  A Generalized Approach to Portfolio Optimization: Improving Performance by Constraining Portfolio Norms , 2009, Manag. Sci..

[22]  Elvezio Ronchetti,et al.  Robustness Aspects of Model Choice , 1997 .

[23]  Richard O. Michaud.  The Markowitz Optimization Enigma: Is 'Optimized' Optimal? , 1989 .

[24]  Bernhard Schölkopf,et al.  Use of the Zero-Norm with Linear Models and Kernel Methods , 2003, J. Mach. Learn. Res..

[25]  Yuhong Yang,et al.  Maximum Lq-likelihood estimation. , 2010, 1002.4533.

[26]  R. C. Merton,et al.  On Estimating the Expected Return on the Market: An Exploratory Investigation , 1980 .

[27]  Beatriz Vaz de Melo Mendes,et al.  Robust multivariate modeling in finance , 2005 .

[28]  Richard O. Michaud,et al.  The Markowitz Optimization Enigma: Is ‘Optimized’ Optimal? , 2005 .

[29]  Ke Yu,et al.  Constraints , 2019, Sexual Selection.

[30]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[31]  Nico van der Wijst,et al.  Optimal portfolio selection and dynamic benchmark tracking , 2005, Eur. J. Oper. Res..

[32]  John E. Beasley,et al.  Mixed-integer programming approaches for index tracking and enhanced indexation , 2009, Eur. J. Oper. Res..

[33]  Jan Havrda,et al.  Quantification method of classification processes. Concept of structural a-entropy , 1967, Kybernetika.

[34]  Davide Ferrari,et al.  On robust estimation via pseudo-additive information , 2012 .

[35]  Francisco J. Nogales,et al.  Portfolio Selection with Robust Estimates of Risk , 2006 .

[36]  Xinfeng Zhou,et al.  Application of robust statistics to asset allocation models , 2006 .

[37]  Runze Li,et al.  Regularization Parameter Selections via Generalized Information Criterion , 2010, Journal of the American Statistical Association.

[38]  C. De Mol,et al.  Forecasting Using a Large Number of Predictors: Is Bayesian Regression a Valid Alternative to Principal Components? , 2006, SSRN Electronic Journal.

[39]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

[40]  S. Vanduffel,et al.  Mean-Variance Optimal Portfolios in the Presence of a Benchmark with Applications to Fraud Detection , 2013 .

[41]  Chih-Ling Tsai,et al.  A note on the unification of the Akaike information criterion , 1998 .

[42]  Sandra Paterlini,et al.  Regular(Ized) Hedge Fund Clones , 2009 .