Cost of Capital: Applications and Examples, + Website, 5th Edition

APPENDIX 11A

Examples of Computing OLS Beta, Sum Beta, and Full-information Beta Estimates

Niel Patel

Introduction

Computing OLS and Sum Beta Estimates Example

Computing Realized Return Data

Computing OLS Beta Estimate

Computing Sum Beta Estimate

Computing Full-information Beta Estimate Example

INTRODUCTION

Two commonly used methods of calculating beta estimates for a subject company are: (1) regressing returns for the public guideline companies against the returns of benchmark market index over the same periods (also known as ordinary least squares regression of OLS beta estimates) and (2) regressing returns for the public guideline companies against the returns of benchmark market index over the same period (t) and lagged returns of benchmark market index (t – 1) (also known as sum beta estimates).

An alternative method for estimating a beta for a subject company is called “full-information beta,” which involves selecting and analyzing guideline public companies that report segment data for businesses that are comparable to all or part of the subject company's business operations. This technique may be of particular interest in cases in which the valuation subject has many different types of operations and/or the most directly comparable, observable operations to the subject operations are contained within discrete business segments of larger, more diversified public companies.

COMPUTING OLS AND SUM BETA ESTIMATES EXAMPLE

Estimating OLS and sum beta for a public company (subject ...