Logo image
Time-Series Processes of Utility Betas: Implications for Forecasting Systematic Risk
Journal article   Peer reviewed

Time-Series Processes of Utility Betas: Implications for Forecasting Systematic Risk

Michael Gombola and Douglas Kahl
Financial management, v 19(3)
01 Oct 1990

Abstract

Bayesian analysis Beta Capital assets CAPM Estimating techniques Mathematical models Risk assessment Studies Utility
A Kalman filtering model is used to estimate the time-series process followed by utility betas. The model is estimated using monthly stock return data from the COMPUSTAT PDE file for 109 utility firms - 61 electric and 48 electric and gas - for the period 1967-1981. The beta for the majority of utility companies in the sample follows either an autoregressive or a constant coefficient process. Very few appear to follow a random walk process, which would produce betas that were not only unstable, but very difficult to forecast. With an autoregressive process, a patient forecaster using relatively simple diagnostic procedures should be able to obtain a reasonable long-run estimate of systematic risk. A reasonable forecast of beta then admits application of the capital asset pricing model for utilities, even if beta is time-varying. The strong evidence of autoregressive tendencies in utility betas lends support to the use of Bayesian-type adjustment processes.

Metrics

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#8 Decent Work and Economic Growth

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
Web of Science research areas
Business, Finance
Logo image