Measuring the DUI mode of innovation efficiently: A short-scale approach
Leonie Reher et al.
Abstract
This paper advances the empirical measurement of the doing–using–interacting (DUI) mode of innovation, based on the conceptual framework of Alhusen et al. Res Policy 50(4):104214 (2021) and its survey-based operationalization of Reher et al. ifh Working Paper 45 (2024b). Using data from German SMEs, we examine whether the three-dimensional structure of DUI learning theorized in the literature can be mirrored empirically. Exploratory factor analysis (EFA) confirms this latent structure by identifying three main learning processes: (1) DUI internal (learning-by-doing and internal interaction), (2) DUI user-driven (learning-by-using), and (3) DUI external (learning-by-external-interaction). However, some factor loadings are problematic, suggesting that not all of the original indicators are suitable for measuring the DUI mode of innovation. Secondly, building on the latent structure identified through EFA, short scales of various lengths are developed using ant colony optimization (ACO) to address practical constraints in innovation surveys. This provides a starting point for the further development of DUI innovation indicators that are particularly suited to less R&D-intensive innovation contexts, such as small firms, low-tech sectors, and lagging regions, as well as corresponding short scales.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.