The rejection of non-meaningful activities is an important issue in human activity recognition (HAR) systems. This rejection is often operated as a hypothesis test based on a model representing all non-meaningful patterns. Such a ?non-meaningful? model is often difficult to obtain in reality. This paper presents a new test, the pairwise likelihood ratio test (PLRT), to reject nonmeaningful activities. The model for non-meaningful activities is not required in this test. Moreover, instead of using a fixed likelihood-ratio threshold, the distribution of the likelihood ratios is used as a measurement to improve the rejection accuracy. Two approaches to combine multiple PLRTs into a stronger classifier are also presented.