The problem of determining the optimal maintenance strategy for a machine given its lifetime distribution has been studied extensively. Solutions to this problem are outlined in the academic literature, prescribed in professional handbooks, implemented in reliability engineering software systems and widely used in practice. These solutions typically assume that the lifetime distribution and its parameter values are known with certainty, although this is usually not the case in practice. In this paper we study the effect of parameter uncertainty on the optimum age-based maintenance strategy. The effect of uncertainty is evaluated by considering both a theoretical uniform lifetime distribution and a more realistic Weibull lifetime distribution. The results show that admitting to the uncertainty does inﬂuence the optimal maintenance age and also provides a quantiﬁable cost beneﬁt. The results can help maintenance managers in making maintenance decisions under uncertainty, and also in deciding when it is worthwhile to invest in advanced data improvement procedures.