Perturbation analysis is an efficient method for performance analysis of discrete event dynamic systems. It yields gradient information from single sample path observation. Over last two decades, various perturbation analysis techniques have been developed to handle a large class of problems. Coupling is a method aiming at efficiently generating multiple samples of random variables. It has a wide range of applications in applied probability. This paper is concerned with perturbation analysis via coupling. This approach offers a great versatility of the form of gradient estimators. It is also potentially helpful for variance reduction in perturbation analysis. It is demonstrated in this paper that several known perturbation analysis techniques can be reviewed as special ways of coupling.