Abstract
In this study we empirically examine the persistence across input and output indicators of innovation using a panel of Spanish manufacturing firms during the period 1990–2013. We use R&D as innovation input and technological innovation, product innovation and process innovation as output measures. We analyse the transition matrices and design an econometric strategy consisting of the estimation of various specifications using random effects dynamic probit models that account for state dependence, unobserved heterogeneity and endogenous initial conditions. Findings indicate the presence of true persistence in all our innovation indicators. They also show the existence of different degrees of persistence depending on the innovation measure used. Persistence in R&D increases around 20% the probability of conducting R&D. The highest persistence is associated with technological innovation. The probability of introducing a technological or process innovation is 28% higher for firms that have innovated in the previous year. When technological innovation is broken down into product and process innovation, the degree of persistence is higher for process innovation than for product innovation. This result is not unexpected considering the Spanish productive structure, which is made up mainly of low and middle-low technological sectors which are based on process innovations rather than on product innovations.
Notes
1. Transitions probabilities matrix has also been calculated for the unbalanced panel. Results are quite similar and are available from the corresponding author upon request.
2. We have run the specifications lagging all controls for one period. Results only change slightly, and our conclusions do not alter. We have opted by introducing controls without lags following Reed’s (Citation2013) suggestion.
3. Tavassoli and Karlsson (Citation2015) use similar robustness checks.
4. Results of the robustness checks are available upon request.