In this study the design of a reinforced concrete beam under bridge-type loading is investigated. Variability of the parameters affecting the resistance of the structure is taken into account in terms of statistical distributions developed using Monte-Carlo methods. The results have explicitly shown the significance of these parameters in the variation of moments of resistance. A simulation model has been developed to predict the random variation of moments due to highway loading. Extreme value distributions have been fitted to the smallest values of the moment of resistance and the greatest values of the moment of loading. This method gives a more accurate safety factor and probability of failure than the previously proposed and existing design procedures. The effect of service load on the fatigue life of the structure is also examined by extending the model, based on the concept of cumulative damage. In the model a realistic representation of truck loading has been produced and compared with the existing design procedures. This study results in a new method of prediction of fatigue life which has advantages over the previously proposed methods. A comprehensive and original investigation has been done on the effects of randomness of the loads and the structural properties on the prediction of fatigue life on reinforced concrete beams using Miner's law. The investigation methods adopted in this study based on the probabilistic approach offer distinct advantages over the experimental approach, which requires extensive laboratory tests. On the other hand, the growing interest in the relevance of probability and statistics in engineering design underlines the importance of this kind of study.