Sampling distributions of optimal portfolio weights and characteristics in small and large dimensions. (English) Zbl 1523.62079
Random Matrices Theory Appl. 11, No. 1, Article ID 2250008, 47 p. (2022); corrigendum ibid. 12, No. 3, Article ID 2392001, 6 p. (2023).
Summary: Optimal portfolio selection problems are determined by the (unknown) parameters of the data generating process. If an investor wants to realize the position suggested by the optimal portfolios, he/she needs to estimate the unknown parameters and to account for the parameter uncertainty in the decision process. Most often, the parameters of interest are the population mean vector and the population covariance matrix of the asset return distribution. In this paper, we characterize the exact sampling distribution of the estimated optimal portfolio weights and their characteristics. This is done by deriving their sampling distribution by its stochastic representation. This approach possesses several advantages, e.g. (i) it determines the sampling distribution of the estimated optimal portfolio weights by expressions, which could be used to draw samples from this distribution efficiently; (ii) the application of the derived stochastic representation provides an easy way to obtain the asymptotic approximation of the sampling distribution. The later property is used to show that the high-dimensional asymptotic distribution of optimal portfolio weights is a multivariate normal and to determine its parameters. Moreover, a consistent estimator of optimal portfolio weights and their characteristics is derived under the high-dimensional settings. Via an extensive simulation study, we investigate the finite-sample performance of the derived asymptotic approximation and study its robustness to the violation of the model assumptions used in the derivation of the theoretical results.
MSC:
| 62P05 | Applications of statistics to actuarial sciences and financial mathematics |
| 62H10 | Multivariate distribution of statistics |
| 62H12 | Estimation in multivariate analysis |
| 62E20 | Asymptotic distribution theory in statistics |
| 91G10 | Portfolio theory |
Keywords:
sampling distribution; optimal portfolio; parameter uncertainty; stochastic representation; high-dimensional asymptoticsReferences:
| [1] | Adcock, C., Statistical properties and tests of efficient frontier portfolios, in Quantitative Financial Risk Management, (Wiley, 2015), pp. 242-269. |
| [2] | Aitchison, J., Confidence-region tests, J. Royal Statist. Soc.: Ser. B26(3) (1964) 462-476. · Zbl 0178.54402 |
| [3] | Alexander, G. J. and Baptista, A. M., Economic implications of using a mean-var model for portfolio selection: A comparison with mean-variance analysis, J. Econ. Dynam. Control26(7-8) (2002) 1159-1193. · Zbl 1131.91325 |
| [4] | Alexander, G. J. and Baptista, A. M., A comparison of var and cvar constraints on portfolio selection with the mean-variance model, Manag. Sci.50(9) (2004) 1261-1273. |
| [5] | Ao, M., Yingying, L. and Zheng, X., Approaching mean-variance efficiency for large portfolios, Rev. Financ. Stud.32(7) (2019) 2890-2919. |
| [6] | Bai, Z. and Silverstein, J. W., Spectral Analysis of Large Dimensional Random Matrices (Springer, New York, 2010). · Zbl 1301.60002 |
| [7] | Bauder, D., Bodnar, R., Bodnar, T. and Schmid, W., Bayesian estimation of the efficient frontier, Scandinavian J. Statist.46 (2019) 802-830. · Zbl 1433.62085 |
| [8] | Bodnar, O. and Bodnar, T., On the unbiased estimator of the efficient frontier, Int. J. Theor. Appl. Finan.13(07) (2010) 1065-1073. · Zbl 1205.91171 |
| [9] | Bodnar, T., Dette, H. and Parolya, N., Testing for independence of large dimensional vectors, Ann. Statist.47(5) (2019) 2977-3008. · Zbl 1436.60018 |
| [10] | Bodnar, T., Dmytriv, S., Okhrin, Y., Parolya, N. and Schmid, W., Statistical inference for the expected utility portfolio in high dimensions, IEEE Trans. Signal Process.69 (2021) 1-14. · Zbl 1543.62568 |
| [11] | Bodnar, T., Dmytriv, S., Parolya, N. and Schmid, W., Tests for the weights of the global minimum variance portfolio in a high-dimensional setting, IEEE Trans. Signal Process.67(17) (2019) 4479-4493. · Zbl 1543.91094 |
| [12] | Bodnar, T., Gupta, A. K. and Parolya, N., Direct shrinkage estimation of large dimensional precision matrix, J. Multivariate Anal.146 (2016) 223-236. · Zbl 1338.60012 |
| [13] | T. Bodnar, M. Lindholm, E. Thorsén and J. Tyrcha, Quantile-based optimal portfolio selection, Technical Report 2018:21, Stockholm University (2018). · Zbl 07432771 |
| [14] | Bodnar, T., Mazur, S. and Okhrin, Y., Bayesian estimation of the global minimum variance portfolio, Europ. J. Operat. Res.256(1) (2017) 292-307. · Zbl 1395.91395 |
| [15] | Bodnar, T., Mazur, S. and Parolya, N., Central limit theorems for functionals of large sample covariance matrix and mean vector in matrix-variate location mixture of normal distributions, Scandinavian J. Statist.46 (2019) 636-660. · Zbl 1418.62056 |
| [16] | Bodnar, T., Okhrin, O. and Parolya, N., Optimal shrinkage estimator for high-dimensional mean vector, J. Multivariate Anal.170 (2019) 63-79. · Zbl 1409.60022 |
| [17] | Bodnar, T. and Okhrin, Y., Properties of the singular, inverse and generalized inverse partitioned Wishart distributions, J. Multivariate Anal.99 (2008) 2389-2405. · Zbl 1151.62046 |
| [18] | T. Bodnar, Y. Okhrin and N. Parolya, Optimal shrinkage-based portfolio selection in high dimensions, preprint (2018), arXiv:1611.01958. · Zbl 1409.60022 |
| [19] | Bodnar, T., Parolya, N. and Schmid, W., Estimation of the global minimum variance portfolio in high dimensions, Europ. J. Operat. Res.266(1) (2018) 371-390. · Zbl 1403.91307 |
| [20] | Bodnar, T. and Reiß, M., Exact and asymptotic tests on a factor model in low and large dimensions with applications, J. Multivariate Anal.150 (2016) 125-151. · Zbl 1397.62209 |
| [21] | Bodnar, T. and Schmid, W., Estimation of optimal portfolio compositions for gaussian returns, Statist. Decis.26(3) (2008) 179-201. · Zbl 1159.62327 |
| [22] | Bodnar, T. and Schmid, W., Econometrical analysis of the sample efficient frontier, Europ. J. Finance15(3) (2009) 317-335. |
| [23] | Bodnar, T., Schmid, W. and Zabolotskyy, T., Minimum var and minimum cvar optimal portfolios: estimators, confidence regions, and tests, Statist. Risk Model. Appl. Finan. Insur.29(4) (2012) 281-314. · Zbl 1252.62106 |
| [24] | Bollerslev, T., Modelling the coherence in short-run nominal exchange rates: a multivariate generalized arch model, Rev. Econ. statist.72(3) (1990) 498-505. |
| [25] | Britten-Jones, M., The sampling error in estimates of mean-variance efficient portfolio weights, J. Finance54 (1999) 655-671. |
| [26] | Bühlmann, P. and Van De Geer, S., Statistics for High-Dimensional Data: Methods, Theory and Applications (Springer, Berlin, 2011). · Zbl 1273.62015 |
| [27] | Cai, T. and Shen, X., High-Dimensional Data Analysis (World Scientific, Singapore, 2011). · Zbl 1277.62032 |
| [28] | Cai, T. T., Hu, J., Li, Y. and Zheng, X., High-dimensional minimum variance portfolio estimation based on high-frequency data, J. Econom.214(2) (2020) 482-494. · Zbl 1456.62242 |
| [29] | Cai, T. T., Zhang, C.-H. and Zhou, H. H., Optimal rates of convergence for covariance matrix estimation, Ann. Statist.38 (2010) 2118-2144. · Zbl 1202.62073 |
| [30] | DasGupta, A., Asymptotic Theory of Statistics and Probability (Springer, New York, 2008). · Zbl 1154.62001 |
| [31] | DeMiguel, V., Garlappi, L., Francisco, N. and Uppal, R., A generalized approach to portfolio optimization: Improving performance by constraining portfolio norms, Manage. Sci.55(5) (2009) 798-812. · Zbl 1232.91617 |
| [32] | Ding, P., On the conditional distribution of the multivariate t distribution, Amer. Statist.70(3) (2016) 293-295. · Zbl 07665887 |
| [33] | Ding, Y., Li, Y. and Zheng, X., High dimensional minimum variance portfolio estimation under statistical factor models, J. Econom.222(1) (2021) 502-515. · Zbl 1471.62493 |
| [34] | Efron, B. and Morris, C., Families of minimax estimators of the mean of a multivariate normal distribution, Ann. Statist.4 (1976) 11-21. · Zbl 0322.62010 |
| [35] | Fama, E., Foundations of Finance: Portfolio Decisions and Securities Prices (Basic Books, New York, 1976). |
| [36] | Fan, J., Liao, Y. and Mincheva, M., Large covariance estimation by thresholding principal orthogonal complements, J. Royal Statist. Soc. Ser B75(4) (2013) 603-680. · Zbl 1411.62138 |
| [37] | Frahm, G. and Memmel, C., Dominating estimators for minimum-variance portfolios, J. Econ.159 (2010) 289-302. · Zbl 1441.62264 |
| [38] | Givens, G. H. and Hoeting, J. A., Computational Statistics (John Wiley & Sons, 2012). · Zbl 1267.62003 |
| [39] | Glombeck, K., Statistical inference for high-dimensional global minimum variance portfolios, Scandinavian J. Statist41 (2014) 845-865. · Zbl 1305.91220 |
| [40] | Golosnoy, V. and Okhrin, Y., Multivariate shrinkage for optimal portfolio weights, Europ. J. Finance13 (2007) 441-458. |
| [41] | Gupta, A. K. and Nagar, D. K., Matrix Variate Distributions (Chapman and Hall, 2000). · Zbl 0935.62064 |
| [42] | Gupta, A. K., Varga, T. and Bodnar, T., Elliptically Contoured Models in Statistics and Portfolio Theory (Springer, 2013). · Zbl 1306.62028 |
| [43] | Ingersoll, J. E., Theory of Financial Decision Making (Rowman & Littlefield, 1987). |
| [44] | Jagannathan, R. and Ma, T., Risk reduction in large portfolios: Why imposing the wrong constraints helps, J. Finance58(4) (2003) 1651-1683. |
| [45] | Jobson, J., Confidence regions for the mean-variance efficient set: an alternative approach to estimation risk, Rev. Quantit. Finance Account1(3) (1991) 235. |
| [46] | Jobson, J. and Korkie, B. M., Performance hypothesis testing with the Sharpe and Treynor measures, J. Finance36 (1981) 889-908. |
| [47] | Kan, R. and Smith, D. R., The distribution of the sample minimum-variance frontier, Manage. Sci.54(7) (2008) 1364-1380. · Zbl 1232.62138 |
| [48] | R. Kan, X. Wang and X. Zheng, In-sample and out-of-sample sharpe ratios of multi-factor asset pricing models, (2019), available at SSRN 3454628. |
| [49] | Kan, R. and Zhou, G., Optimal portfolio choice with parameter uncertainty, J. Financ. Quantit. Anal.42(3) (2007) 621-656. |
| [50] | Korkie, B. and Turtle, H. J., A mean-variance analysis of self-financing portfolios, Manage. Sci.48(3) (2002) 427-443. · Zbl 1232.91627 |
| [51] | Le Cam, L. and Yang, G. L., Asymptotics in Statistics: Some Basic Concepts (Springer Science & Business Media, 2012). · Zbl 0719.62003 |
| [52] | Markowitz, H., Portfolio selection, J. Finance7 (1952) 77-91. |
| [53] | Mathai, A. M. and Provost, S. B., Quadratic Forms in Random Variables: Theory and Applications (Dekker, 1992). · Zbl 0792.62045 |
| [54] | Memmel, C. and Kempf, A., Estimating the global minimum variance portfolio, Schmalenbach Business Rev.58 (2006) 332-348. |
| [55] | Muirhead, R. J., Aspects of Multivariate Statistical Theory (Wiley, New York, 1982). · Zbl 0556.62028 |
| [56] | Okhrin, Y. and Schmid, W., Distributional properties of portfolio weights, J. Econ.134 (2006) 235-256. · Zbl 1420.91430 |
| [57] | Okhrin, Y. and Schmid, W., Estimation of optimal portfolio weights, Int. J. Theor. Appl. Finan.11 (2008) 249-276. · Zbl 1152.91544 |
| [58] | Rencher, A. C., Multivariate Statistical Inference and Applications (Wiley-Interscience, 1998). · Zbl 0932.62065 |
| [59] | Rubio, F., Mestre, X. and Palomar, D. P., Performance analysis and optimal selection of large minimum variance portfolios under estimation risk, IEEE J. Sel. Topics Signal Process.6(4) (2012) 337-350. |
| [60] | Siegel, A. F. and Woodgate, A., Performance of portfolios optimized with estimation error, Manage. Sci.53(6) (2007) 1005-1015. · Zbl 1232.91636 |
| [61] | Simaan, M., Simaan, Y. and Tang, Y., Estimation error in mean returns and the mean-variance efficient frontier, Int. Rev. Econ. Finan.56 (2018) 109-124. |
| [62] | Tu, J. and Zhou, G., Data-generating process uncertainty: What difference does it make in portfolio decisions?J. Financ. Econ.72(2) (2004) 385-421. |
| [63] | Wang, C., Tong, T., Cao, L. and Miao, B., Non-parametric shrinkage mean estimation for quadratic loss functions with unknown covariance matrices, J. Multivariate Anal.125 (2014) 222-232. · Zbl 1280.62064 |
| [64] | Woodgate, A. and Siegel, A. F., How much error is in the tracking error? The impact of estimation risk on fund tracking error, J. Portfolio Manage.41(2) (2015) 84-99. |
| [65] | Yao, J., Zheng, S. and Bai, Z., Large Sample Covariance Matrices and High-Dimensional Data Analysis, (Cambridge University Press, 2015). · Zbl 1380.62011 |
| [66] | Zellner, A. and Ando, T., A direct monte carlo approach for Bayesian analysis of the seemingly unrelated regression model, J. Econ.159 (2010) 33-45. · Zbl 1431.62295 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
