Gas metal arc welding is a very important and useful technology in the fabrication of railroad cars and commercial vehicle structures. However, since the fatigue strength of the joints welded by gas metal arc welding is considerably lower than that of the parent material due to stress concentration and metallurgical changes at the weld, the fatigue-strength assessment of welded joints is very important for the reliability and durability of railroad cars and the establishment of a criterion for long-life fatigue design. In this paper, in order to save time and cost for the fatigue design, an accelerated life-prediction method that is based on the theory of statistical reliability was investigated. Its usefulness was verified by comparing the $({Delta}{sigma}_a)_R-N_f$ relationship that was obtained from actual fatigue test results with the $({Delta}{sigma}_a)_R-(N_f)_{ALP}$ relationship that was derived from accelerated life testing. And the reliability of the predicted life was evaluated. The reliability of the accelerated life-prediction on the base of actual test data was analyzed to be 80% for the plug-type gas-welded joints and 95% for the ring-type gas-welded joints.