Covariance estimation: do new methods outperform old ones?
Tóm tắt
This paper compares three new methods of estimating the asset returns covariance and evaluates their performances with the conventional covariance estimation methods. We find that taking a simple average of the historical sample covariance matrix and the covariance matrix estimated from the single-index model provides the best overall performance among all competing methods. In addition, we find that commonly used assessment criteria provide systematically different rankings, which explains the preferences to different types of estimation methods in the existing literature. We believe the difference between our results and those of previous studies may be partly due to the differences in the ratio of the time series observations to the number of stocks in the samples that have been used in different studies.
Tài liệu tham khảo
Blume ME (1971) On the assessment of risk. J Financ 26:1–10
Chan LKC, Karceski J, Lakonishok J (1999) On portfolio optimization: forecasting covariance and choosing the risk model. Rev Financ Stud 12:937–974
Cohen KJ, Pogue JA (1967) An empirical evaluation of alternative portfolio selection models. J Bus 40:166–193
DeMiguel V, Garlappi L, Uppal R (2009) Optimal versus naïve diversification: how inefficient is the 1/N portfolio strategy. Rev Financ Stud 22:1915–1953
Disatnik DJ, Benninga S (2007) Shrinking the covariance matrix. J Portf Manage 33:55–63
Elton EJ, Gruber MJ (1973) Estimating the dependence structure of share prices—implications for portfolio selection. J Financ 28:1203–1232
Elton EJ, Gruber MJ, Spitzer J (2006) Improved estimates of correlation coefficients and their impact on the optimum portfolios. Eur Financ Manag 12:303–318
Elton EJ, Martin MJ, Brown SJ, Goetzmann WN (2007) Modern portfolio theory and investment analysis. Wiley, New York
Eun CS, Resnick BG (1992) Forecasting the correlation structure of share prices: a test of new models. J Bank Financ 16:643–656
Jagannathan R, Ma T (2003) Risk reduction in large portfolios: why imposing the wrong constrains helps. J Financ 58:1651–1683
King B (1966) Market and industry factors in stock price behavior. J Bus 39:139–190
Laloux L, Cizeau P, Bouchaud J, Potters M (1999) Noise dressing of financial correlation matrices. Phys Rev Lett 83:1467–1470
Laloux L, Cizeau P, Potters M (2000) Random matrix theory and financial correlations. Int J Theor Appl Financ 3:391–397
Ledoit O, Wolf M (2003) Improved estimation of the covariance matrix of stock returns with an application to portfolio selection. J Empir Finance 10:603–621
Pafka S, Kondor I (2003) Noisy covariance matrices and portfolio optimization II. Phys A: Stat Mech Appl 319:487–494
Pafka S, Kondor I (2004) Estimated correlation matrices and portfolio optimization. Phys A: Stat Mech Appl 343:623–634
Roll R, Ross S (1980) An empirical investigation of the arbitrage pricing theory. J Financ 35:1073–1103
Rosenberg B (1974) Extra-market components of covariance in security returns. J Financ Quant Anal 9:263–274
Sharpe W (1963) A simplified model for portfolio analysis. Manag Sci 9:277–293
Vasicek OA (1973) A note on using cross-section information in Bayesian estimation of security betas. J Financ 28:1233–1239