A BAYESIAN FORECAST OF ROAD TRAFFIC FATALITIES IN NIGERIA

U. A IBEKWE; L. A. AJIJOLA; G. C. MESIKE

U. A IBEKWE Department of Actuarial Science & Insurance Faculty of Management Sciences University of Lagos, Akoka, Lagos, Nigeria.
L. A. AJIJOLA Department of Actuarial Science & Insurance Faculty of Management Sciences University of Lagos, Akoka, Lagos, Nigeria.
G. C. MESIKE Department of Actuarial Science & Insurance Faculty of Management Sciences University of Lagos, Akoka, Lagos, Nigeria.

Keywords: Road traffic accident, Empirical bayes, credibility theory

Abstract

Road accidents account for a significant proportion of the high mortality rates in Nigeria. Reducing road traffic accidents calls for knowledge of the causative factors and measures for remedial actions. This study, therefore, attempts to determine whether the targets announced for the U.N. Decade of Action for Road Safety are realizable in order to stabilize and reduce the level of road traffic accidents by about 50 percent by the year 2020. Projected road traffic fatalities in Nigeria are modeled using an Empirical Bayes approach. The model applied credibility theory to Reported Road accident Cases and Casualties data for the period 2001 to 2016 inclusive to forecast road accidents in subsequent years. Forecast accuracy is assessed within an Exponentially Weighted Moving Average (EWMA) model using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Mean Absolute Percentage Error (MAPE). It was discovered that the U.N. targets, though apparently largely achieved by the target year, may not be sustainable into the future in Nigeria if the target date were to be extended by another decade to 2030 unless drastic policy changes based on sound and quantifiable forecasts are introduced and implemented.