Working Paper: CEPR ID: DP3265
Authors: Francesco Corielli; Massimiliano Marcellino
Abstract: Index tracking requires building a portfolio of stocks (a replica) whose behaviour is as close as possible to that of a given stock index. Typically, much fewer stocks should appear in the replica than in the index, and there should be no low frequency (persistent) components in the tracking error. Unfortunately, the latter property is not satisfied by many commonly used methods for index tracking. These are based on the in-sample minimization of a loss function, but do not take into account the dynamic properties of the index components. Instead, we represent the index components with a dynamic factor model, and develop a procedure that, in a first step, builds a replica that is driven by the same persistent factors as the index. In a second step, it is also possible to refine the replica so that it minimizes a loss function, as in the traditional approach. Both Monte Carlo simulations and an application to the EuroStoxx50 index provide substantial support for our approach.
Keywords: Factor Models; Index Tracking; Replica; Stock Index
JEL Codes: C43; C53; G10
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| persistent factors (C41) | tracking error (Y10) |
| portfolio construction (G11) | tracking error (Y10) |
| index tracking methods (C43) | tracking error (Y10) |