In this paper, the problem of training federated learning (FL) algorithms over a wireless network with mobile users is studied. In the considered model, several mobile users and a network base station (BS) cooperatively perform an FL algorithm. In particular, the wireless mobile users train their local FL models and send the trained local FL model parameters to the BS. The BS will then integrate the received local FL models to generate a global FL model and send it back to all users. Due to the limited training time at each iteration, the number of users that can transmit their local FL models to the BS will be affected by changes in the users' locations and wireless channels. In this paper, this joint learning, user selection, and wireless resource allocation problem is formulated as an optimization problem whose goal is to minimize the FL loss function, which captures the FL performance, while meeting the transmission delay requirement. To solve this problem, a closed-form expression for the expected convergence rate of the FL algorithm is first derived to quantify the impact of the users' mobility and wireless factors on FL. Then, based on the expected FL convergence rate, the user selection and uplink resource allocation is optimized at each FL iteration so as to minimize the FL loss function while satisfying the FL parameter transmission delay requirement. Simulation results show that the proposed approach can reduce the FL loss function value by up to 20% compared to a standard FL algorithm.