To enhance coverage and improve service continuity, satellite-terrestrial integrated radio access network (STIRAN) has been seen as an essential trend in the development of 6G. However, there is still a lack of theoretical analysis on its coverage performance. To fill this gap, we first establish a system model to characterize a typical scenario where low-earth-orbit (LEO) satellites and terrestrial base stations are both deployed. Then, stochastic geometry is utilized to analyze the downlink coverage probability under the setting of shared frequency and distinct frequencies. Specifically, we derive mathematical expressions for the distances distribution from the serving station to the typical user and the associated probability based on the maximum bias power selection strategy (Max-BPR). Taking into account real-world satellite antenna beamforming patterns in two system scenarios, we derive the downlink coverage probabilities in terms of parameters such as base station density and orbital inclination. Finally, the correctness of the theoretical derivations is verified through experimental simulations, and the influence of network design parameters on the downlink coverage probability is analyzed.