Hierarchical multiple regressions results.

This article discusses the dynamics of innovation in America and Europe, focusing on variables such as access to technology, education, and life expectancy. To do this, the article proposes an agent-based model called the Innovameter. The dependent variable is the Global Innovation Index. The paper focuses on data analysis through correlation analysis and multiple hierarchical regressions to determine the contribution of specific variables related to the pillars of the Global Innovation Index and indicators of the Human Development Index. After analyzing the data, an agent-based model was built to parameterize these main variables by defining two levels of abstraction: at the global level, there is the country, where birth rates, life expectancy, ICT use, and research and development are defined. At the local level, we define the individuals who have an age, years of schooling, and income. A series of experiments were conducted by selecting data from 30 countries. From the results of the experiments, a nonparametric correlation analysis was performed, and correlation indices were obtained indicating a relationship between the predicted outcomes and the outcomes in the global index. The proposed model aims to provide suggestions on how the different variables can become the norm in most of the countries studied.