In this paper, we consider a hypothesis testing problem of determining, among n random variables, k random variables which have different probability distributions from the rest (n-k) random variables. For this purpose, instead of using separate observations for each random variable, we propose to use mixed observations which are functions of multiple random variables. It is demonstrated that $O({\frac{k \log(n)}{\min_{P_i, P_j} C(P_i, P_j)}})$ observations are sufficient for correctly identifying the $k$ anomalous random variables with high probability, where $C(P_i, P_j)$ is the Chernoff information between two possible distributions $P_i$ and $P_j$ for the proposed mixed observations. This can potentially lead to significant savings of sensing resources in certain applications.