Patent-based indicators at the country level are frequently used to assess countries' innovation performances or efforts. Yet they are often said to reflect the propensity to patent rather than actual research productivity. The authors of this article argue that patent-based indicators can rightfully be used to measure research productivity, as witnessed by the influence of several policy tools on the R&D-patent relationship. They also put forward a new counting methodology, less subject to "home" bias. © Springer-Verlag 2008.