Controlling for unobserved heterogeneity is a fundamental challenge in empirical research, as failing to do so can introduce omitted variables biases and preclude causal inference. In this paper we develop an innovative method – the Iterative Geographically Weighted Regression (IGWR) method – to identify clusters of farms that follow a similar local production econometric model, taking explicitly unobserved spatial heterogeneity into account. The proposed method is the perfect combination of the GWR approach and the adaptive weights smoothing (AWS) procedure. This method is applied to regional samples of olive growing farms in Italy. The main finding is that the conditional global IGWR model fits the data best, proving that explicitly accounting for unobserved spatial heterogeneity is of crucial importance when modeling the production function of firms particularly for those operating in land based industries