Lars-Lasso回归算法是近年来统计选元的一个新兴方法.针对资产数量众多的投资市场,本文将Lars-Lasso方法运用到资产配置的第一步资产选择中,针对已选择的小数量资产进行资产组合配置.对中国沪深股市股票进行实证分析.结果证明,在Lasso选元下得到的投资组合总体表现优于市场指数.
Lars-Lasso regression algorithm is a popular statistical element method. For the investment markets with large amount of assets, we apply the Lars-Lasso method to the asset selection, which is the first step of portfolio selection, and then use the portfolio optimization model. The utility of this approach is illustrated by empirical studies on Chinese stock market, and it is verified to have better performance than the market index.
[1] Markowitz H. Portfolio selection [J]. Journal of Finance, 1952, 7(1):77-91.
[2] Markowitz H. Portfolio selection: efficient diversification of investments[M]. New York: John Wile and Sons, Ltd.1959.
[3] Bawa V S. Optimal rules for ordering uncertain prospects [J]. Journal of Finance Economics Letters, 1975, 2(1):95-121.
[4] Fishburn P C. Mean-risk analysis with risk associated with below-target returns [J]. American Econimic Review, 1977, 67:116-126.
[5] Ahn D H, Jacob B, Matthew R. et al. Optimal risk management using options [J]. Journal of Finance, 1999, 54(1):359- 375.
[6] Basak S, Shapiro A. Value-at-risk-based risk management: optimal policies and asset prices [J]. Review of Financial Studies, 2001, 14(2):371-405.
[7] Rockfellar R T, Uryasev S. Optimization of conditional value-at-risk [J]. The Journal of Risk, 2000, 2(3):21-41.
[8] Goldfarb D, Iyengar G. Robust portfolio selection problems [J]. Mathematics of Operations Research, 2003, 28:1-38.
[9] El Ghaoui, Oks M, Oustry F. Worst-case value-at-risk and robust portfolio optimization: a conic programming approach [J]. Operations Research, 2003, 51:543-556.
[10] Zymler S, Kuhn D, Rustem B. 2009. Worst-case value-at-risk of non-linear portfolios [J]. Management Science, 2013, 59(1):172-188.
[11] Pinar M C, Pac A B. Mean semi-deviation from a target and robust portfolio choice under distribution and mean return ambiguity[J]. Journal of Computational and Applied Mathematics, 2013, 259:394-405.
[12] Breiman L. Classication and regression trees [M]. New York: Chapman and Hall, 1993.
[13] Tibshirani R. Regression shrinkage and selection via the lasso [J]. Journal of the Royal Statistics Society, 1996, 58:267-288.
[14] Efron B, Hastie T, Johnstone I, et al. Least angle regression [J]. Annals of Statist, 2004, 32:407-451.
[15] Fan J, Zhang J, Yu K. Vast portfolio selection with gross-exposure constraints [J]. Journal of American Statistical Association, 2012, 107:592-60.
[16] Jagannathan R, Ma T. Risk reduction in large portfolios: why imposing the wrong constraints helps [J]. Journal of Finance, 2003, 58:1 651-1 683.
[17] Chen L, He S, Zhang S H. Tight bounds for some risk measures, with applications to robust portfolio selection [J]. Operations Research, 2011, 59(4):847-865.
[18] 张忠桢. 二次规划-非线性规划与投资组合的算法线性规划 [M]. 武汉:武汉大学出版社, 2006: 152-154.
[19] Morgan J P. Risk Metrics[M]. 2nd ed. J P Morgan, 1994.
