Correlation versus Interchangeability: The Limited Robustness of Empirical Findings on Democracy using Highly Correlated Datasets

Abstract: This article shows that highly correlated measures can produce different
results. We identify a democratization model from the literature and test it
in over 120 countries from 1951-1992. Then, we check whether the
results are robust regarding measures of democracy, time periods, and
levels of development. The findings show that measures do matter: while
some of the findings are robust, most of them are not. This explains, in
part, why the debates on democracy have continued rather than been
resolved. More importantly, it underscores the need for more careful use
of measures and further testing to increase confidence in the findings.
Scholars in comparative politics increasingly are drawn to large-N
statistical analyses, often using datasets collected by others. As in any
field, we show how they must be careful in choosing the most appropriate
measures for their study, without assuming that any correlated measure
will do.

Correlation versus Interchangeability: The Limited Robustness of Empirical Findings on Democracy using Highly Correlated Datasets

Leave a Reply

Your email address will not be published.