At two-way stop controlled (TWSC) intersections drivers on minor stream are generally at risk because of the difficulty in judging safe gap between major stream vehicles. Any misjudgment by the driver while choosing gap may result in a collision with major stream vehicle. This paper provides important insights for determining and analyzing spatial critical gaps of drivers at high speed and medium speed TWSC intersections. The critical gap line (CGL) fitted for the accepted and rejected gaps using parametric (binary logit model-BLM) and non-parametric (support vector machines-SVM) techniques gives critical gap values at 15th, 50th and 85th percentile speeds. The evaluation of spatial critical gap with respect to major road vehicle (conflicting vehicle) speed makes it easier to understand the impact of variation in speed on spatial gaps accepted by the drivers on the minor road. The logit models developed revealed that the probability of accepting gap decreases with increase in the speed of the conflicting vehicle and it increases with increase in the distance of conflicting vehicle. The spatial critical gaps estimated using support vector machines were found in close approximation with those estimated using binary logit model. The study results showed that SVMs have very good potential to be an alternative tool for the estimation of driver's critical gap. The spatial critical gaps corresponding to 15th, 50th and 85th percentile speeds for medium speed intersections were 32 m, 38 m and 46 m respectively and for high speed intersections these values were 64 m, 76 m and 104 m respectively. The increase in the magnitude of gap value with respect to the percentile speed clearly states the effect of speed on spatial gaps. The insights from the study can be used to suggest various measures to improve the safety of crossing drivers at uncontrolled intersections. © 2019 The Authors