1168 The Methods of Growth Econometrics
uncertainty, the Bayesian approach can consider many candidate explanatory
variables simultaneously, and the extent of their robustness to changes in spec-
ification. Researchers can then communicate the degree of support for a particular
hypothesis with more faith that the results do not depend on arbitrary modeling
choices. Perhaps the main open questions about these methods are those identi-
fied by Ciccone and Jarocinski (2007). From their analysis, it is clear that current
approaches to Bayesian model averaging may have significant limitations of their
own. The development of methods to overcome these should be a research priority.
Another reason for optimism is that the quality of available data is likely to
improve over time. The development of new and better data has clearly been one
of the main achievements of the empirical growth literature since the early 1990s,
and one that was not foreseen by critics of the field. Researchers have developed
increasingly sophisticated proxies for drivers of growth that previously appeared
resistant to statistical analysis. One approach, pioneered in the growth literature by
Knack and Keefer (1995) and Mauro (1995), has been the use of country-specific rat-
ings compiled by international agencies. Such data increasingly form the basis for
measures of corruption, government efficiency, and protection of property rights.
More recent work, such as that of Kaufmann, Kraay and Zoido-Lobaton (1999a,
1999b) and Kaufmann, Kraay and Mastruzzi (2003), has established unusually com-
prehensive measures of various aspects of institutional quality. Similarly, research
in political science, notably the POLITY project at the University of Maryland, has
developed a range of indicators of political institutions that have already played
an important role in empirical growth studies.
As more variables become available, the construction of proxies is likely to make
increasing use of latent variable methods. These aim to reduce a set of observed
variables to a smaller number of indicators that are seen as driving the majority
of the variation in the original data, and that could represent some underlying
variable of interest. For example, the extent of democracy is not directly observed,
but is often obtained by applying factor analysis or extracting principal compo-
nents from various dimensions of political freedom. There are obvious dangers
with this approach, but the results can be effective proxies for concepts that are
otherwise hard to measure.^29 Using latent variables makes especially good sense
under one view of the proper aims of growth research. It is possible to argue that
empirical growth studies will never give good answers to precise hypotheses, but
can be informative at a broader level. For example, a growth regression is unlikely
to tell us whether the growth effect of inflation is more important than the effect
of inflation uncertainty, because these two variables are usually highly correlated.
It may even be difficult to distinguish the effects of inflation from the effects of
sizeable budget deficits.^30 Instead, a growth regression might be used to address a
less precise hypothesis, such as the growth dividend of macroeconomic stability,
broadly conceived. In this context, it is natural to use latent variable approaches
to measure the broader concept.
Another valuable development is likely to be the creation of rich panel datasets
at the level of regions within countries. Regional data offer greater scope for