Driver behaviour modelling is essential for reducing driver workload and enhancing vehicle safety systems. To create more personalized and intelligent vehicles, efficient driver behaviour models must be integrated into vehicle dynamic systems. This paper focuses on understanding driver responses to unexpected events, with a particular emphasis on acceleration profiles due to their sensitivity to driving anomalies. Notable abnormal driving manoeuvres, such as hard braking, sharp U-turns, and sudden lane changes, often necessitate stopping the vehicle. The study employs KDE of histograms, KL divergence, ANOVA, and F-test analyses to identify and validate these findings. Additionally, time-frequency plots are utilized to predict various driving anomalies and their causes. A Kalman filter-based jerk estimation algorithm is proposed to estimate changes in jerk behaviour, aiding in the prediction of driving anomalies. The applications of this research include developing advanced driving safety systems by evaluating driving behaviour changes before and after anomalies occur.