Firm-Level Determinants of Innovation in Ecuadorian Enterprises (ACTI Survey 2012–2014, SMOTE-Corrected Dataset)

This dataset contains firm-level microdata from 5,984 Ecuadorian enterprises across manufacturing, commerce, services, mining, and transport sectors. It was derived from the Encuesta Nacional de Actividades de Ciencia, Tecnología e Innovación (ACTI) conducted by the National Institute of Statistics and Census (INEC) in collaboration with SENESCYT for the period 2012–2014. The dataset was processed to address severe class imbalance in innovation outcomes using the Synthetic Minority Oversampling Technique (SMOTE) and cleaned to remove variables with over 10% missing values. It includes variables on firm characteristics, human capital composition, R&D investment, technological acquisition, innovation activities, and performance indicators. These data were used to estimate firm-level models of product, service, organizational, and marketing innovation, employing logistic regression and two-stage least squares (2SLS) estimation techniques. This dataset supports the publication by D’Espaux and Padilla León (2025), “ Dissecting Innovation: Evidence of Specialization and Trade-Offs in Ecuador's Firms”, providing a balanced and reproducible dataset for econometric replication and policy analysis.