Hubbard, D. W. (2007). How to measure anything: Finding the value of 'intangibles' in business

 Although the author of this book worked as a management consultant for Coopers and Lybrand, he confronted the problem faced by managers in the public and private sectors, valuing anything that appears to elude measurement, "such as the value of quality, employee morale, or the economic impact of cleaner water" (p. xi). The consequences of this inability affect the occurrence of errors, appropriation of resources, and the effectiveness of decisions.

To define his terms, Hubbard explained measurement as "'error reduction', . . . a central theme of this book" (p. 17). Hubbard further defined measurement as "a set of observations that reduce uncertainty where the result is expressed as a quantity" (p. 21). Claude Shannon, an American electrical engineer, promulgated "a mathematical definition of information as the amount of uncertainty reduction in a signal, which he discussed in terms of the 'entropy' removed by a signal" (p. 22). Therefore, the measurement process entails the reduction of uncertainty by the degrees of refinement of a quantified range of amounts. According to Hubbard, Stanley Smith Stevens described the qualitative nature of measurement by clarifying the differences between nominal and ordinal measurements.

The chapter titles in the section, "Before you measure", map the first phase of reducing uncertainty and the measurement process, "Clarifying the measurement problem; Calibrated estimates, how much do you know now; Measuring risk: Introduction to the Monte Carlo Simulation; Measuring the value of information. Section III, "Measurement Methods", specifies the objective, empirical approaches to engage in measurement. Hubbard begins by describing the decomposition of components of a problem or question into their elemental parts, a task familiar to all scientific and academic researchers. Secondary sources supply additional information of previous investigations and methods of analysis of the same or similar problems.
When engaging in measurement, Hubbard stressed the importance of matching measurement cost with information value, "we need to know the Expected Value of Information not the Expected Value of Perfect Information" (p. 93). Throughout the book he advocated "the Rule of Five" . . . There is a 93% chance that the median of a population is between the smallest and largest values in any random sample of five from that population" (pp. 23-24). Furthermore, Hubbard viewed measurement as an iterative process, testing multiple types of observation, sampling sizes, experiments, and instruments.

Hubbard illustrated his argument with numerous examples from the public and private sector, for which he consulted.


Hubbard, D. W. (2007). How to measure anything: Finding the value of "intangibles" in business. New York: John Wiley & Sons, Inc.