A spatial quantile regression hedonic model of agricultural land prices

Abstract

Land price studies typically employ hedonic analysis to identify the impact of land characteristics on price. Owing to the spatial fixity of land, however, the question of possible spatial dependence in agricultural land prices arises. The presence of spatial dependence in agricultural land prices can have serious consequences for the hedonic model analysis. Ignoring spatial autocorrelation can lead to biased estimates in land price hedonic models. We propose using a flexible quantile regression-based estimation of the spatial lag hedonic model allowing for varying effects of the characteristics and, more importantly, varying degrees of spatial autocorrelation. In applying this approach to a sample of agricultural land sales in Northern Ireland we find that the market effectively consists of two relatively separate segments. The larger of these two segments conforms to the conventional hedonic model with no spatial lag dependence, while the smaller, much thinner market segment exhibits considerable spatial lag dependence.