In sensor networks, we are interested in prolonging the lifetime of the network and thus the energy conservation is one of the most important aspects to be considered in the design. In this paper, we present regression techniques to model the sensor data. In this, framework, the nodes of the sensor network collaborate to fit a regression model to their local measurements. This model takes the form of a weighted sum of local basis functions. Instead of transmitting data to each other or outside the network, nodes communicate the model's parameters and thus the communication required is reduced . Usually, sensors are densely deployed. Therefore, to reduce further the energy cost, sensors in the same sensing area are used in turns.