PM 2.5 Concentration Measurement Analysis by Using Non-Parametric Statistical Inference

Abstract

Rapid population growth, urbanization and motorization have brought about secondary effects that have gradually damaged the atmosphere, whose importance is vital for both the survival of all living beings and the climate balance. In this sense, air pollution is a problem that affects current society and is much more critical in developing countries. In this context, in the present paper non-parametric statistical inference techniques are used to carry out the analysis of measurements of health concerning fine particulate matter concentration, PM 2.5, in an urban park of Quito, Ecuador. In short, the data collected during the measurements were stored in random variables and the Kruskal-Wallis test was used to test if these random variables come from populations with identical distributions. Also, the Wilcoxon signed rank test was used to test if the numerical values collected in the samples of the random variables of interest represent a level of contamination that could be dangerous for human beings. The experimental results show that urban parks and, specifically, trees are a natural filter between the pollution generated in the road and the center of the park. Therefore, the role of trees in the face of vehicular pollution will depend on two variables: the amount and compactness of the vegetation, and the emission levels recorded in the border roads.