Habitat fragmentation is considered one of the critical reasons for the biodiversity loss. Establishing a connected reserve network which accommodates the free movement of protected species in the reserve is an effective way to reduce habit fragmentation. One possible method to ensure a connected reserve is to convert a whole large area to a conservation reserve. However, the resources devoted to conservation effort have always been scarce, and it is important that these resources are allocated in an optimal way. The optimal design of a reserve network which is effective both ecologically and economically has become an important research topic in the reserve design literature. The problem of optimal selection of a subset from a larger group of potential habitat sites is often solved using either heuristic or formal optimization methods. The heuristic methods, although flexible and computationally fast, can not guarantee the solution is optimal therefore may lead to scarce resources being used in an ineffective way. The formal optimization methods, on the other hand, guarantees that the solution is optimal. But it has been argued that it would be difficult to model site selection process using optimization models, especially when spatial attributes of the reserve have to be taken into account. This paper presents a linear integer programming model for the design of a minimal connected reserve network. Dantzig cut approach is employed to prevent loops that may occur in the solution to ensure the selected sites assemble a connected tree, corresponding to a connected reserve. Computational performance of the model is tested using datasets randomly generated by the software GAMS. Results show that the model can solve a connected reserve design problem which includes 100 potential sites and 30 species in a reasonable period of time, and the model significantly outperforms the representative method in the literature in terms of computational efficiency. As the number of potential sites increases, the processing time needed to solve the problem is expected to grow up quickly. As an empirical study, the model is applied to the protection of endangered and threatened bird species in the Cache River basin area in Illinois, USA. 11 bird species and 56 potential sites are included in the empirical study. Two minimal connected reserve networks are designed. One is to protect each species at least once and the other twice where applicable. The model presented in this paper is deterministic in terms of the occurrence of species in potential sites, and static in terms of the time when selection decision is made. More studies are needed to combine uncertainty and dynamics into the optimization model. The successful application of any site selection model has to be based on complete and accurate data. However, the data itself may have some associated problems such as incompleteness, out-of-date, inaccurate, etc. Data issue is critical for a successful design of an effective reserve network and it should get more attention especially in China.