Investigation of the performance of rail freight: a regression model with panel data

• Autor(a) principal: Valle, Wallace Giovanni Rodrigues do
• Data de Publicação: 2019
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Research, Society and Development
• Texto Completo: https://rsdjournal.org/index.php/rsd/article/view/1435
• topic: Carga ferroviária; Análisis de regresión; Datos del panel.; Rail freight; Regression analysis; Panel data.; Transporte ferroviário de carga; Análise de regressão; Dados em painel.

The objective of this paper is to investigate the factors that affect the performance of rail freight and to ascertain the magnitude of the resulting effects. A multiple linear regression model was developed with panel data analysis, considering the fixed effects over time. The data collected correspond to the period from 2011 to 2018 and come from the National Land Transportation Agency (ANTT). The explanatory variables used are: speed, maintenance, accidents and cargo volume (production). After formulating and executing the model, the obtained indices were tested for statistical significance. We attempted to attenuate heteroscedastic errors by calculating robust standard errors and performed a model specification test. It was detected that the volume of cargo transported and speed of the train have a statistically relevant impact on performance. The model developed showed no evidence of poor specification and can assist in the planning of the activities of the observed companies.