This paper aims at introducing a new statistical technique to describe sequences: Optimal Matching Analysis (OMA). Borrowed from biology, this technique is based on rather simple principles that can be adapted to suit the theoretical requirements of many analyses. Since OMA is not based on any causal assumption, this method is particularly of interest to sociologists to retemporalize action by analyzing it as a process. Two applications of Optimal Matching to time-use data are proposed in order to demonstrate its flexibility but also its sociological interest.Cet article vise à présenter les fondements d'une nouvelle technique statistique qui permet de décrire les séquences : les Méthodes d'Appariement Optimal (M.A.O.). Empruntée à la biolo...