This study focuses on optimising traffic flow in Rwanda through econometric analysis of time-series data. A theoretical approach was employed, including an assumption that traffic flow can be modelled by a linear regression equation with time as the independent variable. The model's parameters were estimated using maximum likelihood estimation, ensuring identifiability through statistical tests. The asymptotic analysis revealed that the traffic data converges to a stable solution over long periods, indicating reliable predictions of future flow patterns. The study successfully identified and quantified the effects of various factors influencing traffic flow in Rwanda using econometric techniques. These findings suggest implementing dynamic traffic management systems based on real-time data analysis for optimal traffic flow control. Model selection is formalised as =argmin_\L () +\, () \ with consistency under mild identifiability assumptions.
Muhizi et al. (Wed,) studied this question.