Conventional methods address data modeling in WSNs by converting a learning problem into an optimization task. These methods are mainly based on Gradient Descent and Nelder-Mead Simplex optimization techniques. They are energy efficient, but with drawbacks: the accuracy of the induced models is usually lower than that of the centralized technique; and the latency is proportional to the network size. In this paper, we propose a novel distributed method for parametric regression in a clustered WSN using particle swarm optimization. Two main contributions of this paper are as follows: First, we re-formulate the distributed regression in WSNs as a multiobjective optimization (MO) problem in which an objective is dedicated to each cluster. Second, we propose a distributed algorithm based on the Vector Evaluated Particle Swarm Optimization method to address the MO problem in two phases. The proposed algorithm obtains a set of candidate network regressors and computes the final model using a weighted averaging rule. We compare the prediction accuracy, latency, and energy consumption of our algorithm against its popular distributed counterparts and the centralized technique using a real-world and an artificial data set. The experimental results show that our algorithm outperforms the existing approaches in prediction accuracy while its energy consumption and latency are acceptable. We also evaluate the effect of the number of particles, swarm topologies, and clustering granularity on the performance of the proposed method.