Simulation-based analysis methods make few restrictions on the system design and scale to very large and complex systems, therefore they are widely used in timing analysis of complex industrial embedded systems. This paper presents a statistical approach to validation of temporal simulation models extracted from complex embedded systems, by introducing existing mature statistical methods to the context. The proposed approach firstly collects sampling distributions of response time and execution time data of tasks in both the modeled system and the model, based on simple random samples (SRS). The second step of the approach is to compare the sampling distributions, regarding interesting timing properties, by using the non-parametric two-sample Kolmogorov-Smirnov test. The evaluation using a fictive system model inspired by a real robotic control system with a set of change scenarios, shows a promising result. The proposed algorithm can identify temporal differences between the target system and its extracted model, i.e., the algorithm can assess whether the extracted model is a sufficiently accurate approximation of the target system.