Selection bias in innovation studies: A simple test

• Counting patents at one patent office may result in selection bias.
• The selection bias affects econometric estimates of ‘patent production functions’.
• We propose a test to evaluate the likely presence of selection bias.
• We recommend using a ‘global’ count of patents when relevant.

The study of the innovative output of organizations often relies on a count of patents filed at one single office of reference such as the European Patent Office (EPO). Yet, not all organizations file their patents at the EPO, raising the specter of a selection bias. Using novel datasets of the whole population of patents by Belgian firms and German universities, we show that the single-office count results in a selection bias that affects econometric estimates of invention production functions. We propose an easy-to-implement methodology to evaluate whether estimates that rely on the single-office count are affected by a selection bias.