Modeling Time-Varying Conditional Betas. A Comparison of Methods with Application for REITs

Marcel Aloy (1) , Floris Laly (2) , Sébastien Laurent (1, 3) , Christelle Lecourt (1)

1 AMSE - Aix-Marseille Sciences Economiques
2 Louvain School of Management (LFIN‐LIDAM, UCLouvain)
3 Aix-Marseille Graduate School of Management

Beta coefficients are the cornerstone of asset pricing theory in the CAPM and multiple factor models. This chapter proposes a review of different time series models used to estimate static and time-varying betas, and a comparison on real data. The analysis is performed on the USA and developed Europe REIT markets over the period 2009–2019 via a two-factor model. We evaluate the performance of the different techniques in terms of in-sample estimates as well as through an out-of-sample tracking exercise. Results show that dynamic models clearly outperform static models and that both the state space and autoregressive conditional beta models outperform the other methods.

Keywords: real estate; REITs; multivariate GARCH; state space; dynamic conditional beta; autoregressive conditional beta

Domains: Humanities and Social Sciences; Economics and Finance

Marcel Aloy, Floris Laly, Sébastien Laurent, Christelle Lecourt. Modeling Time-Varying Conditional Betas. A Comparison of Methods with Application for REITs. Gilles Dufrénot; Takashi Matsuki. Recent Econometric Techniques for Macroeconomic and Financial Data, Springer International Publishing, pp.229-264, 2021, Dynamic Modeling and Econometrics in Economics and Finance, 978-3-030-54252-8. ⟨10.1007/978-3-030-54252-8_9⟩. ⟨hal-03103717⟩