Análise da incidência de dengue em Sergipe : uma aplicação de modelos de séries temporais

• Autor(a) principal: Santos, Joas Silva dos
• Data de Publicação: 2018
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UFS
• Texto Completo: http://ri.ufs.br/jspui/handle/riufs/9724
• topic: Estatística; Ensino de estatística; Dengue; SARIMA; Séries temporais; Dengue fever; Time series; CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA::ESTATISTICA::ANALISE DE DADOS

The dengue fever is a reemerging arbovirose considered a serious public health problem in tropical and subtropical regions. Nowadays, about fifty to one hundred million infections occur annually in more than 100 endemic countries putting almost half of the population at risk. Many factors contributed to the disease resurgence. However, the main boosters were: the climate changes, urbanization, globalization and the intense population growth. Taken together, those factors provided ideal environmental conditions for the establishment of the main virus transmitter, the Aedes aegypti mosquito, a vector highly adapted to the domestic environment. Then the aim of this study was to develop a model through the Box-Jenkins methodology of time series to predict the dengue fever incidence in Sergipe based on notifications occurred from 2001 to 2012 taken from The Injury Information System of Notification. The model SARIMA (0,1,2)(2,1,1)12 showed a better adjustment to the data and also the minors AIC (278,510), BIC (295,986) and MAPE (0,550). The validation of the model was based on the comparison of the predictions and the real data observed from July to December of 2012. Therefore, the analysis of time series specifically the SARIMA model was useful in the monitoring and prediction of dengue fever cases, making possible the implementation of more adequate prevention programs