Avaliação da Distribuição Estatística dos Acidentes de Trajeto no Brasil

• Autor(a) principal: Manta, Rafael Costa
• Data de Publicação: 2024
• Outros Autores: Teti, Bruno de Sousa, Soares, Willames de Albuquerque, Lima, Nathan Bezerra de, Lima, Nathalia Bezerra de, Gorga Lago, Eliane Maria, da Cruz, Felipe Mendes, Vas, Bianca M.
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Revista de Engenharia e Pesquisa Aplicada
• Texto Completo: http://revistas.poli.br/index.php/repa/article/view/2796

 Commute accident is one that occurs from home to the workplace or vice versa, and according to Brazilian legislation, it is considered a workplace accident. The number of accidents during the home-work-home commute increased by 41.2% between 2007 and 2013, as reported in the survey by the National Confederation of Industry. The objective of this study is to analyze the data on commute accidents recorded between 2005 and 2015 in Brazil by the Ministry of Labor and Social Security through statistical analysis. Five probability distributions were considered, aiming to identify the one that best fits the historical series and gain a better understanding of the occurrence of such events. The data studied in this work were obtained through the Dataprev Open Data Portal. Using Excel and PAST software, tests were conducted for discrete random variables and the following probability distributions: Normal, Log-Normal, Beta, Gamma, and Weibull. For each distribution, three adherence tests were performed: Kolmogorov-Smirnov, Chi-square, and Anderson Darling, with a significance level of 5%. It was found that the Beta distribution was the best fit for the accident data, while the Log-Normal distribution performed the least effectively.