ABSTRACT The main goal of this research was to identify personal and professional factors of train drivers which imply in the occurrence of accidents (denoted in this study as situations to non-compliance with procedures of the train driver consisting of unsafe acts that could cause major accidents) of a Brazilian logistics company related to accidentes in the period from 2014 to 2016. The research involved 348 drivers and some independent variables associated with each worker such as distances of removal (railway sections), driver’s age, working time (time working in the company), marital status, number of trips (number of train trips as a driver); months of work (months of work in the company) and total hours driving trains. Responses of interest are accident rates per work month and accident counts. Under a Bayesian approach, Beta and Poisson regression models were assumed in the presence of excess zeros. For the accident rate/months of work response, the covariates number of trips, posting distances and age showed some evidence of significant effects. For the response accident count, the covariate hours driving trains shows some evidence that it is a significant covariate. These results may be of great interest to rail logistics company managers to improve rail safety using some Bayesian modeling approaches in the presence of excess zeros. denoted noncompliance non compliance 201 2016 34 railway sections, sections , sections) s company, status driver) counts approach zeros ratemonths rate effects count 20 3 2

Resumo Introdução A retinopatia da prematuridade (ROP) é uma doença vasoproliferativa, que afeta a retina das crianças que nascem prematuramente; assim, este estudo propôs identificar fatores associados e predizer a retinopatia na prematuridade. Método Realizou-se um estudo transversal, com recém-nascidos prematuros, dividindo-os em dois grupos: com e sem retinopatia. As variáveis foram categorizadas por meio do teste da razão de verossimilhança e as variáveis que obtiveram p-valores menores que 0,2 foram analisadas por um modelo logístico múltiplo. A capacidade de predição do modelo foi realizada por meio da construção da curva ROC. Resultados Dos 296 recém-nascidos, 32 (10,81%) apresentaram retinopatia. No modelo logístico, as variáveis que apresentaram fator de risco foram idade gestacional ≤ 30 semanas (p-valor=0,0214), peso ao nascer ≤ 1.250 gramas (p-valor=0,0013) e escore Apgar no primeiro minuto < 7 (p-valor=0,0352). A curva ROC com sensibilidade 0,771 e especificidade 0,774 evidenciou o modelo com precisão de 0,8448 e ponto de probabilidade de 0,79. Conclusões Este modelo pode ser usado para predição de retinopatia em recém-nascidos prematuros com um fator de risco de 0,79, destacando que estes necessitam de maior atenção.

Abstract Introduction Retinopathy of prematurity (ROP) is a vasoproliferative disease that affects the retina of prematurely born children. Therefore, this study proposed to identify associated factors and to predict retinopathy in prematurity. Method A cross-sectional study including preterm newborns divided into two groups: with and without retinopathy. The variables were categorized using the likelihood ratio test, and the variables with p-values less than 0.2 were analyzed by a multiple logistic model. The model used the construction of a Receiver Operating Characteristic (ROC) curve as predicting tool. Results Of the 296 newborns, 32 (10.81%) had retinopathy. The following variables represented a risk factor according to the logistic model: gestational age ≤ 30 weeks (p-value = 0.0214), birth weight ≤ 1250 grams (p-value = 0.0013) and Apgar score at 1 minute <7 (p-value = 0.0352). The ROC curve with sensitivity of 0.771 and specificity of 0.774 was a precise model, showing accuracy of 0.8448 and a probability point of 0.79. Conclusions This model can be used to predict retinopathy in premature newborns with a risk factor of 0.79, emphasizing that the need for additional attention.