This text looks at calibration and validation as a means to understand traffic flow models better. It concentrates on the car-following part of it and demonstrates that the calibration of stochastic models under certain circumstances can become very difficult. Three types of stochasticity are distinguished for microscopic traffic flow models: the one coming from noisy data, the one coming from the distribution of the parameters describing the driver's behavior and the one coming from the model itself, when a noise component is added to a deterministic differential equation governing the vehicle's movements. By using four sub models comprising four different noise terms and an identical deterministic part this text shows that a calibration with synthetic - and therefore reproducible - data can lead to awry results. Parameters fitted by the calibration procedure are significantly different for deterministic and stochastic models. The text makes the conclusion that the stochasticity is the reason why the parameter estimation of stochastic models fails sometimes. Up to now, the authors were, unfortunately, not able to propose a solution to cope with this intrinsic pitfall of genuine stochastic models.