Quadrotors lack redundancy in their actuators making actuator faults risky. One way to cope with actuator failures on quadrotors is to sacrifice yaw control and use the remaining rotors to land directly or maintain forward flight. In order to apply an appropriate control strategy, these active fault tolerant control (AFTC) methods require a quick loss of effectiveness (LOE) detection. This research presents a novel method for fast and robust detection of actuator failures on quadrotors. The proposed algorithm has very little model dependency. A Kalman estimator estimates a stochastic effectiveness factor for every actuator, using only onboard RPM, gyro and accelerometer measurements. Then, a hypothesis test identifies the failed actuator. This algorithm is validated online in real-time, also as part of an AFTC-system. LOE is induced by ejecting the propellers from the motors. The robustness of this algorithm is further investigated offline over a range of parameter settings by replaying real flight data containing 26 propeller ejections. The detection delays are found to be in the 30-130 ms range, without missed detections or false alarms ocurring.