Beta Forecasting at Long Horizons

36 Pages Posted: 15 Jul 2016 Last revised: 18 Aug 2016

Tolga Cenesizoglu

HEC Montreal - Department of Finance

Fabio de Oliveira Ferrazoli Ribeiro

UNSW Business School, University of New South Wales

Jonathan J. Reeves

UNSW Business School, University of New South Wales; Financial Research Network (FIRN)

Date Written: July 12, 2016

Abstract

Systematic (CAPM beta) risk forecasting for long horizons, such as one year, play an important role in financial management. This paper evaluates a variety of beta forecasting procedures for long forecast horizons. The widely utilized Fama-MacBeth approach based on five years of monthly returns is found to be unreliable in terms of mean absolute (and squared) forecast error and statistical bias. The most accurate forecasts are found to be generated from an autoregressive model of realized beta. In addition to analyzing the statistical properties of these forecasts, the economic significance between the different approaches is demonstrated through evaluating investment projects.

Keywords: NPV Analysis, Realized Beta, Systematic Risk

JEL Classification: G17

Suggested Citation

Cenesizoglu, Tolga and de Oliveira Ferrazoli Ribeiro, Fabio and Reeves, Jonathan J., Beta Forecasting at Long Horizons (July 12, 2016). UNSW Business School Research Paper No. 2016 BFIN 01. Available at SSRN: https://ssrn.com/abstract=2808969 or http://dx.doi.org/10.2139/ssrn.2808969

Tolga Cenesizoglu

HEC Montreal - Department of Finance ( email )

3000 Chemin de la Cote-Sainte-Catherine
Montreal, Quebec H3T 2A7
Canada

HOME PAGE: http://www.hec.ca/en/profs/tolga.cenesizoglu.html

Fabio De Oliveira Ferrazoli Ribeiro

UNSW Business School, University of New South Wales ( email )

Sydney, NSW 2052
Australia

Jonathan J. Reeves (Contact Author)

UNSW Business School, University of New South Wales ( email )

Sydney, NSW 2052
Australia

Financial Research Network (FIRN) ( email )

C/- University of Queensland Business School
St Lucia, 4071 Brisbane
Queensland
Australia

Paper statistics

Downloads
119
Rank
188,850
Abstract Views
683