Oghoyafedo et al., 2017 379 Nigerian Journal of Environmental Sciences and Technology (NIJEST) www.nijest.com ISSN (Print): 2616-051X | ISSN (electronic): 2616-0501 Vol 1, No. 2 July 2017, pp 379 - 389 Accident Prediction Model at Unsignalized Intersection Using Multiple Linear Regression Method Oghoyafedo N. K. 1,* , Ehiorobo J. O. 1 , Nwankwo E. 1 1 Department of Civil Engineering, University of Benin, Benin City, Nigeria Corresponding Author: *nosakhare.oghoyafedo@uniben.edu ABSTRACT The issue of road accidents is an increasing problem in developing countries. This could be due to increasing road traffic/vehicle occupancy, geometric characteristics and road way condition. The factors influencing accidents occurrence are to be analysed for remedies. The purpose of this research is to develop an accident prediction model as a measure for future study, aid planning phase preceding the designed intervention, enhance the production of updated design standards to enable practitioners design unsignalized intersection for optimal safety, reduce the number of accidents at unsignalized intersections. Five intersections were selected randomly within Benin City and traffic count carried out at these intersections as well as geometric characteristics and roadway conditions. The prediction model was developed using multiple linear regression method and the standard error of estimate was computed to show how close the observed value is to the regression line. The model was validated using coefficient of multiple determination. The establishment of the relationship between accidents and traffic flow site characteristics on the other hand would enable improvement to be more realistically accessed. This study will also enhance the production of updated design standards to enable practitioners design unsignalized intersection for optimal safety, reduce the number of accidents at unsignalized intersections. Keywords: Unsignalized Intersection, Multiple Regression, Dependent Variable, Independent Variable, Accident Rate 1.0. Introduction Accident can be defined as anything which happens by chance, anything occurring unexpectedly undersigned (Odugbemi, 2010). Road accident do not simply happen, they are caused. Nigeria has a high road traffic accident rate as well as one of the largest numbers of death per 10,000 vehicles (Sheriff, 2009). Nigeria is ranked second-highest in the rate of road accidents among 193 countries of the world (Agbonkhese et al., 2013). (Oladepo and Brieger, 1986) had argued that three-quarters of all accidents on Nigerian roads involve fatalities. The incidence of fatal road accidents in Nigeria is phenomenal. Trend analysis of fatal road accidents between June 2006 and May 2014 using Nigeria Watch database record gives 15,090 lives lost to fatal road accidents in 3,075 events, highest fatality occurred in 2013 (2,061 deaths), a 2.8% increase from the 2012 record of 1,652 deaths (Ukoji, 2014). Road accidents can happen in many forms. Generally, road traffic accident can be categorized into four common type: where the driver collide with another vehicle or a roadside object, when the driver leaves the lane where they are in, accidents at junctions include rear-end collision and angle or side impacts, accidents that involving pedestrians and cyclists and accident that collide with animals (Nicholas et al., 2003). Accident at intersection gives high impact to the road users. In urban areas where the traffic volume are high, intersection provided must accommodate the high volume for turning movement that traverse to large areas. For this situation, the channelization is an effective means to make sure that the road intersection provides safety. Intersection channelization is used to separate turn lanes from through lane that consist of solid white liners or barrier which guide the traffic so that the vehicle can safely negotiate the complex intersection. (Nicholas et al., 2003)