Análise da demanda por transporte de táxi com modelos de regressão linear múltipla - um estudo de caso em Natal, RN

• Autor(a) principal: BOSCHETTI, Giovane
• Data de Publicação: 2018
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UFRN
• Texto Completo: https://repositorio.ufrn.br/handle/123456789/40733
• topic: taxi; modelos; regressão linear; demanda

The first step of the traditional model in transportation planning is based on quantifying and estimating the trip demand among various traffic zones existing in a determined region. In the context of urban transport, taxis have received little attention in Brazilian literature, even though the comprehension of its demand can contribute to an integrated transport planning with other transport modes, bringing benefits to the whole society. The present paper deals with identifying one or more variables that influence the production of taxi trips in the city of Natal/RN, Brazil, through a multiple regression analysis. To do so, it has been collected and analyzed data on taxi trip conducted in the city for one year, and sought to relate them to socioeconomic, demographic and land use data. Associated with the regression analysis, Stepwise and “Best Subset” variables selection techniques were employed to contribute to the definition of the best model for the problem. As a result, it was verified that the number of households with per capita incomes greater than 10 minimum salaries, and the rate of population with age over 80 years old significantly and positively influence the number of taxi trips produced in each neighborhood of Natal/RN, building a model with an explanation rate 2=80%.