Contrary to an accepted wisdom, this paper shows that cross-country variations in the number of patents per researcher do not only reflect differences in the propensity to patent but also signals differences in research productivity. We put forward and test an empirical model that formally accounts for the productivity and the propensity component of the R&D-patent relationship. The two components play an important role, as witnessed by the impact of several policies, including education, intellectual property and science and technology policies. Indicators based on domestic priority filings reflect research efforts and are primarily affected by varying propensities to patent. In contrast, international filings, especially triadic patents, rather capture variations in research productivity. © 2008 Elsevier B.V. All rights reserved.