Measuring Risk Profile with a Multidimensional Rasch Analysis

Valeria CAVIEZEL
Lucio BERTOLI-BARSOTTI
Sergio Ortobelli LOZZA

Keywords

risk profile, predisposition to risk earn, Rasch model multidimensional IRT models marginal maximum likelihood

Abstract

In this paper we propose an evaluation of investors’ risk profiles such as to meet the minimal requirements that Italian financial institutions must satisfy by law (d. lgs. 164, 2007). Thus we investigate all aspects specific to so-called risk profiles: an investor’s knowledge and his financial experience (concerning financial instruments and their use); financial objectives, a personal predisposition to risk /earn and the temporal horizon. The methodology used in financial literature with regard to risk profiles is essentially based on simplistic statistical analyses that often fail to consider possible psychological aspects. In order to account for investor preferences and psychological attitudes, we suggest to use an item response theory model. We first assume a unidimensional model, belonging to the family of Rasch models and then, as an alternative approach, a Generalized Multidimensional Rasch model. In particular, the objective is to assess the value of a questionnaire whose items describe different characteristics of the main latent variable risk profile. Under the assumption of a multidimensional measurement model, given the multivariate position of each investor with respect to identified latent traits we can represent his position with respect to possible investments proposed by a bank and we can identify different situations that respect the investor’s risk profile and best characterize typical investor choices.