We present the design and implementation of POS, an in-network service that computes accurate order statistics energy-efficiently. POS returns a stream of periodic samples from any order statistic. It initially computes the value of the order statistic and then periodically runs a validation protocol to determine whether the value is still valid. If not, it uses an optimized binary search to determine the new value and then resumes periodic validation. POS uses in-network aggregation and transmission suppression to reduce communication complexity. Results from both experiments on a mote testbed and simulations show that POS can compute order statistics accurately while consuming less energy than the best techniques to compute averages in common cases.