Análisis de los procesos electorales en Ecuador : análisis exploratorio de estructuras, tendencias y relaciones estadísticas de variables sociales, económicas y electorales en Ecuador.

Abstract

The present work started with an exploratory data analysis using the Kaggle environment, through the hypothetical-deductive method. The data used comes from the CNE on the 2021 general elections in Ecuador, and the INEC employment, unemployment, and underemployment survey. Observations were made, two hypotheses were raised, their consequences were deduced and then an attempt was made to refute the hypotheses. The first hypothesis stated that the difference observed between registered votes and the total sum of votes is due to common errors made in the meetings. This hypothesis could not be refuted with the observed data, so it is tentatively true according to the carried-out analysis. The second hypothesis proposed that voters would have a certain preference for a candidate, depending on the socioeconomic stratum to which they belong. It was partially refuted since, according to the analysis, there was a preference for a candidate on the part of low-stratum voters, but not in the case of high-stratum voters. Additionally, a general computational analysis, and a discussion about the advantages and disadvantages of the Kaggle environment, were performed. Finally, a specific computational analysis was performed for the behavior of the Kaggle environment during the previous exploratory analysis. This analysis was carried out using the hypothetical-deductive method, with a hypothesis that anticipated the sections that would occupy more computational resources. This hypothesis could not be refuted by the analyzed data, but additional code sections with high consumption of computational resources were found.