Time trends in gender-specific incidence rates of road traffic injuries in Iran

Citation metadata

From: PLoS ONE(Vol. 14, Issue 5)
Publisher: Public Library of Science
Document Type: Report
Length: 6,084 words
Lexile Measure: 1400L

Document controls

Main content

Abstract :

Objectives Every day, an average of 3,400 deaths and tens of millions of injuries occur as a result of traffic accidents. This study aims to model and validate road traffic injury (RTI) times series, specifically considering gender. Study design Time trend studies of monthly road traffic injuries (RTI) in Iran from March 2005 to February 2016, as well as those of males and females from March 2009 to February 2016 were performed. Methods The seasonal auto-regressive integrated moving average method (SARIMA) was employed to predict RTI time series. The final model was selected from various SARIMA models based on the Akaike information criterion (AIC) and the Bayesian information criterion (BIC). To examine whether the residuals were white noise, the Ljung-Box (LB) test and residuals plots were used for un-correlation, and the zero mean and stationarity, respectively. Additionally, smoothing methods were utilized to validate the SARIMA models for fitting and out-of-range prediction of the time series models under study. The sample auto-correlation function (ACF) and the partial autocorrelation function (PACF) with 20 lags were employed to determine the order of models and to ascertain if the residuals of the model were uncorrelated. Results Based on the obtained results, SARIMA (2,1,0)(0,1,1).sub.12, SARIMA (0,1,1)(0,1,1).sub.12, SARIMA (1,1,1)(0,0,1).sub.12, and SARIMA (2,0,0)(1,0,0).sub.12 were chosen for the time series including incidence rates of total road traffic injuries (IRTI), IRTI of males, females, and males-to-females, respectively. The AIC values were -87.57, 413.38, -732.91, and -85.32, respectively. The LB test for the residuals of the time series models of (0.539) IRTI, (0.3) IRTI of males, (0.23) females, and (0.237) males-to-females indicated that residuals were uncorrelated. Furthermore, prediction values for the next 24 months (2016 to 2018) showed no decline in the incidence rate of male and female traffic injuries. Results of the predictions using exponential smoothing methods indicated out-of-range prediction validity of the SARIMA models. Conclusion This study exemplified the high efficiency of SARIMA models in predicting road traffic injuries (RTIs). Based on observations, the IRTI mean in Iran was 35.57 in 2016. The predicted values of the IRTI for 2016-2018 by the SARIMA model showed no decreasing trend. During the studied period, the observed values of IRTI for males were two to three times the female values. Thus, prediction of RTI can provide a useful tool for traffic safety policymaking by simulating interrupted time series when applying new traffic enforcement interventions and regulations in the future. Additionally, IRTI analysis of males and females showed that men had a non-increasing trend but higher incidence of traffic injuries, whereas the IRTI for women revealed an increasing trend from 2009 to 2012 with a lower incidence of injuries. This growth could be attributed to the impact of increased outdoor activities of women and the increased number of issued driving licenses in the period of 2009-2012.

Source Citation

Source Citation   

Gale Document Number: GALE|A584928733