Measuring innovation using firm-level surveys: Evidence from developing countries✰

Understanding innovation in developing countries has been substantially constrained by the lack of comparable and reliable data. Collecting data on firm-level innovation is challenging because of the difficulties to operationalize the definition of innovation, the subjective judgement calls that respondents are required to make because of this, and because what constitutes innovation may be considered differently across different country contexts. These challenges may lead to serious issues in innovation measurement. This paper contributes to the literature on measurement of innovation by uncovering significant differences in self-reporting innovation rates likely to result in mismeasurement. The first finding is that measures of innovation varies across survey instruments. Second, key elements explaining these differences are related to both framing issues and cognitive issues. Minimizing differences and potentially mismeasurement issues, therefore, requires ensuring good quality interviews but also facilitating good and consistent understanding of what is an innovation. Adding questions that collect more details describing innovation is critical to identifying inconsistencies in responses. While, the focus is on developing countries; the results of the study are also relevant to other countries and the overall literature on innovation survey design.