Although the existing time synchronization protocols in wireless sensor networks (WSNs) are efficient for short periods, many applications require long-term synchronization among the nodes, for example, coordinated sleep and wakeup modes, and synchronized sampling. In such applications, experiments have shown that even clock skew correction cannot maintain long-term clock synchronization and a quadratic model of clock variations can better capture the dynamics of the actual clock model involved, hence increasing the resynchronization period and conserving significant energy. This paper derives the maximum likelihood (ML) estimator for all the clock parameters in a two-way timing exchange model with exponential delays. The same estimation procedure can be applied to one-way timing exchange models with little modification.