Abstract

Over the past two decades the population of Madison County, Alabama grew more than 185%, while the number of households grew by 251%. The variables collected in transportation planning studies are of a socio-economic nature and, therefore are interrelated and random. These socio-economic variables are very often not considered when applying multiple linear regressions to such data. The purpose of this paper is two-fold: to examine the determinants of traffic volume on the road network that influence traffic congestion; and to develop a predictive model of traffic flow along Madison county road network. Data per tract for the year 2000 was used for the development of the model. It is hypothesized that the socio-economic characteristics positively increase trip generation in terms of traffic volume on the road network. The empirical findings based on ordinary least square (OLS) reveal that an increase in population, employment, median household income, and number of household in Madison County census tracts positively related to traffic generation rates (traffic flow). However, the increase in population also contributes to more housing in the area and leads to more automotive traffic cars on the road. The paired t-test with a p-value of 0.354 suggests that there is no difference between the observed and the predicted. The paper concludes that the lack of a public transportation system in the area would result in more home-based-work and other trips, which would ultimately increase the traffic flow in all the census tracts. The decisions taken about trip purpose for a particular urban area will depend on the transportation issues important to that area.