Stock and bond return predictability: the discrimination power of model selection criteria

Authors:
Rosario Dell'Aquila;Elvezio Ronchetti
Affiliations:
Investment Research, Zürcher Kantonalbank, Postfach, CH-8010 Zürich, Switzerland and University of Lugano (Universití della Svizzera italiana), Lugano, Switzerland;Department of Econometrics, University of Geneva, Blv. Pont d'Arve 40, CH-1211 Geneva, Switzerland and University of Lugano (Universití della Svizzera italiana), Lugano, Switzerland
Venue:
Computational Statistics & Data Analysis
Year:
2006

Citing 1
Cited 3

Bagging predictors

Machine Learning

On properties of predictors derived with a two-step bootstrap model averaging approach-A simulation study in the linear regression model

Computational Statistics & Data Analysis
Simple VARs cannot approximate Markov switching asset allocation decisions: An out-of-sample assessment

Computational Statistics & Data Analysis
Correcting and combining time series forecasters

Neural Networks

Quantified Score

Hi-index	0.03

Visualization

Abstract

The discrimination power of well-known model selection criteria is analyzed when the R-squared is low as in typical asset return predictability studies. It turns out that the discrimination power is low in this situation and this may explain, already in a simple i.i.d. setup, why often in-sample predictability, but no out-of-sample predictability is found. In particular it is possible to give another interpretation to the results of the well-cited Bossaerts and Hillion (Rev. Financial Stud. 12 (1999) 405-428) study. As a consequence, model selection criteria are put in a testing framework and a bootstrap-based procedure is proposed as a diagnostic tool to construct the class of models which are statistically indistinguishable from the best model chosen by a model selection criterion. In an empirical illustration the Pesaran and Timmerman (J. Finance 50 (1995) 1201-1228) results are reanalyzed and it turns out that in this case this class of models can be large. Finally it is shown that similar problems arise in a more hidden way in the context of recent model uncertainty studies using Bayesian model selection criteria.