Combining Value Estimates to Increase Accuracy

The estimates provided by discounted cash flow, the method of comparables, and market prices usually disagree. Combining two or more of these value estimates makes sense because every bona fide estimate provides information and because relying on one estimate ignores the information content of the others. How, then, should financial analysts combine different value estimates to form a more accurate estimate than that provided by any one method? Drawing from Bayesian decision theory, the Delaware Block Method, and forecasting research, this article suggests five rules of thumb for combining two or more value estimates into a superior value estimate. According to finance theory, value equals the sum of expected free cash flow suitably discounted. Yet, different valuation procedures, such as discounted cash flow (DCF) analysis and the “method of comparables,” usually yield discrepant value estimates. When no single estimate is clearly the most precise and accurate in a given situation, combining two or more of the available value estimates makes sense. Every bona fide estimate provides some incremental information, and relying on only one estimate ignores the information offered by the others.How should financial analysts combine discrepant value estimates to form a more accurate estimate? Drawing from the Delaware Block Method used by the courts in many bankruptcy cases, Bayesian decision theory, and forecasting research, this article proposes and elaborates on five rules of thumb:Estimate value as a linear weighted average of all bona fide available value estimates, including current market price if it is available.Take advantage of the benefits of diversification by incorporating as many bona fide value estimates as available.If you believe some of the estimates are more accurate and precise than others, assign greater weight to the more accurate and precise estimates.Take an equally weighted “simple” average of all available estimates. In practice, this approach usually works just as well as more sophisticated weighting procedures.Perhaps try statistical back testing to peer-group or historical data but be careful. Back testing may help determine the optimal weights, but it comes with its own set of caveats.The method of combining does have unresolved issues. Bayesian theory says that value estimates should be combined as a linear weighted average. Without a reliable peer group of efficiently priced comparable firms, however, determining what the weights should be is usually difficult. Moreover, there is no way to evaluate whether the weights, once chosen, are correct. If the optimal weights vary over time, estimating them by back testing to historical time series is inappropriate.Nevertheless, despite these problems, combining promises enough benefits to warrant much more attention from practitioners, as well as academic researchers, than it has attracted in the past.