Aggregating governance indicators

TL;DR: In this article, a simple variant of an unobserved component model is used to combine the information from different sources of governance data and country-specific aggregate governance indicators, and the authors illustrate the methodology by constructing aggregate indicators of bureaucratic quality, rule of law, and graft.

Abstract: In recent years the growing interest of academics and policymakers in governance has been reflected in the proliferation of cross-country indices measuring various aspects of governance. The authors explain how a simple variant of an unobserved components model can be used to combine the information from these different sources into aggregate governance indicators. The main advantage of this method us that it allows quantification of the precision of both individual sources of governance data and country-specific aggregate governance indicators. The authors illustrate the methodology by constructing aggregate indicators of bureaucratic quality, rule of law, and graft for a sample of 160 countries. Although these aggregate governance indicators are more informative about the level of governance than any single indicator, the standard errors associated with estimates of governance are still large relative to the units in which governance is measured. In light of these margins of error, it is misleading to offer very precise rankings of countries according to their level of governance: small differences in country rankings are unlikely to be statistically - let alone practically - significant. Nevertheless, these aggregate governance indicators are useful because they allow countries to be sorted into broad groupings according to levels of governance, and they can be used to study the causes and consequences of governance in a much larger sample of countries than previously used (see for example the companion paper by the authors,"Governance matters", Policy Research Working Paper no. 2196).