Application of logistic regression in the analysis of risk factor associated with arterial hypertension

• Autor(a) principal: Silveira, Maria Beatriz Galdino da
• Data de Publicação: 2021
• Outros Autores: Barbosa, Nyedja Fialho Morais, Peixoto, Ana Patrícia Bastos, Xavier, Érika Fialho Morais, Xavier Júnior, Sílvio Fernando Alves
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Research, Society and Development
• Texto Completo: https://rsdjournal.org/index.php/rsd/article/view/22964
• topic: Association; Risk Factors; Fitted model.; Associação; Fatores de risco; Modelo ajustado.; Asociación; Factores de riesgo; Modelo de ajuste.

Logistic regression is an important technique for data modeling when you want to analyze the relationship between a response variable and one or more independent variables. The technique allows one to estimate the chances related to the probability of occurrence of an event of interest. Logistic regression differs from linear regression due to the dichotomous nature of the dependent variable and has been used in several areas of knowledge, including studies in the health area. This study used the logistic regression technique to analyze the association between Hypertension and certain risk factors. The data used comes from the National Health Survey (PNS) for the year 2019, carried out by the Brazilian Institute of Geography and Statistics (IBGE) in the country. Two models were adjusted, the final model being composed of seven variables with a statistical significance of 5%. Diagnostic techniques indicated an adequate fit of the model, as well as its accuracy for predictions. The results show that factors such as increasing age, high body mass index (BMI) and a positive diagnosis for diabetes increase the chances of an individual being hypertensive.