Factor based index tracking

Corielli, Francesco; Marcellino, Massimiliano

doi:10.1016/j.jbankfin.2005.07.012

“…. , n} = S (t) 2 S (t) 1 and S (t) 2 S (t) 1 = ∅ (see (28), (29)), we obtain the result which was set out to prove.…”

Section: Propertiesmentioning

confidence: 61%

“…For instance, the price to pay for the full replication of the Russell 2000 index is estimated at 1.3% and 1.84% annually. These well-documented issues [5,12,18,28,29,31] hamper the use of a full replication approach and explain the success of partial replication approaches. Partial replication means that the fund manager is allowed to invest in a limited number of securities to track the benchmark [5,8,28,38,66,69,80].…”

mentioning

confidence: 99%

Construction of Risk-Averse Enhanced Index Funds

Lejeune

¹

,

Samatlı-Paç

²

2013

INFORMS Journal on Computing

View full text Add to dashboard Cite

We propose a partial replication strategy to construct risk-averse enhanced index funds. Our model takes into account the parameter estimation risk by defining the asset returns and the return covariance terms as random variables. The variance of the index fund return is forced to be below a low-risk threshold with a large probability, thereby limiting the market risk exposure of the investors and the moral hazard associated with the wage structure of fund managers. The resulting stochastic integer problem is reformulated through the derivation of a deterministic equivalent for the risk constraint and the use of a block decomposition technique. We develop an exact outer approximation method based on the relaxation of some binary restrictions and the reformulation of the cardinality constraint. The method provides a hierarchical organization of the computations with expanding sets of integer-restricted variables and outperforms the Bonmin and the Cplex 12.1 solvers. The method can solve very large (up to 1000 securities) instances, converges fast, scales well, and is general enough to be applicable to problems with buy-in threshold constraints. Cross-validation tests show that the constructed funds track closely and are consistently less risky than the benchmark on the out-of-sample period.

show abstract

“…The idea is that a portfolio that yielded in the past performance levels close to those of the benchmark will continue to do so in the future. The (total or average) squared deviation is one of the most popular tracking measures [5,28,38,76]. Other tracking metrics minimize the tracking error variance, the mean absolute deviation, the root squared mean error, and a power function of deviation (see [38] for a detailed discussion of the most popular tracking measures).…”

Section: Stochastic Index Tracking Modelmentioning

confidence: 99%

“…These well-documented issues [5,12,18,28,29,31] hamper the use of a full replication approach and explain the success of partial replication approaches. Partial replication means that the fund manager is allowed to invest in a limited number of securities to track the benchmark [5,8,28,38,66,69,80]. The requirement is enforced through the use of binary decision variables and the introduction of a cardinality constraint.…”

mentioning

confidence: 99%

Construction of Risk-Averse Enhanced Index Funds

Lejeune

¹

,

Samatlı-Paç

²

2010

View full text Add to dashboard Cite

We propose a partial replication strategy to construct risk-averse enhanced index funds. Our model takes into account the parameter estimation risk by defining the asset returns and the return covariance terms as random variables. The variance of the index fund return is forced to be below a low-risk threshold with a large probability, thereby limiting the market risk exposure of the investors and the moral hazard associated with the wage structure of fund managers. The resulting stochastic integer problem is reformulated through the derivation of a deterministic equivalent for the risk constraint and the use of a block decomposition technique. We develop an exact outer approximation method based on the relaxation of some binary restrictions and the reformulation of the cardinality constraint. The method provides a hierarchical organization of the computations with expanding sets of integer-restricted variables and outperforms the Bonmin and the Cplex 12.1 solvers. The method can solve very large (up to 1000 securities) instances, converges fast, scales well, and is general enough to be applicable to problems with buy-in threshold constraints. Cross-validation tests show that the constructed funds track closely and are consistently less risky than the benchmark on the out-of-sample period.

show abstract

“…Corielli and Marcellino (2006) propose the use of factor analysis so that stocks are grouped around various factors depending on their past returns, and the tracking portfolio contains those stocks that best explain the variability of these factors. In their results, several stocks are used as representatives of each factor, so the tracking portfolio can include stocks that explain the same parts of the variability in the performance of the index.…”

mentioning

confidence: 99%

A MULTIOBJECTIVE MODEL FOR PASSIVE PORTFOLIO MANAGEMENT: AN APPLICATION ON THE S&P 100 INDEX

García

¹

,

Guijarro

²

,

Clemente

³

2013

Journal of Business Economics and Management

View full text Add to dashboard Cite

Index tracking seeks to minimize the unsystematic risk component by imitating the movements of a reference index. Partial index tracking only considers a subset of the stocks in the index, enabling a substantial cost reduction in comparison with full tracking. Nevertheless, when heterogeneous investment profiles are to be satisfied, traditional index tracking techniques may need different stocks to build the different portfolios. The aim of this paper is to propose a methodology that enables a fund's manager to satisfy different clients’ investment profiles but using in all cases the same subset of stocks, and considering not only one particular criterion but a compromise between several criteria. For this purpose we use a mathematical programming model that considers the tracking error variance, the excess return and the variance of the portfolio plus the curvature of the tracking frontier. The curvature is not defined for a particular portfolio, but for all the portfolios in the tracking frontier. This way funds’ managers can offer their clients a wide range of risk-return combinations just picking the appropriate portfolio in the frontier, all of these portfolios sharing the same shares but with different weights. An example of our proposal is applied on the S&P 100.

show abstract

Factor based index tracking

Cited by 73 publications

References 18 publications

Construction of Risk-Averse Enhanced Index Funds

Construction of Risk-Averse Enhanced Index Funds

Construction of Risk-Averse Enhanced Index Funds

A MULTIOBJECTIVE MODEL FOR PASSIVE PORTFOLIO MANAGEMENT: AN APPLICATION ON THE S&P 100 INDEX

Contact Info

Product

Resources

About