In this paper, we consider a constant-stress accelerated life test with competing risks for failure from exponential distribution under progressive type-II hybrid censoring. We derive the maximum likelihood estimator and Bayes estimator of the parameter and prove their equivalence under certain circumstances. Further study of the estimators indicates that missing of failure modes would result in overestimation of the mean lifetime. Finally, a Monte-Carlo simulation is performed to demonstrate the accuracy and effectiveness of the estimators.