Apartment rent prediction using spatial modeling

This paper provides a new model to explain local variation in apartment rents by introducing the notion of a spatial process. This model differs from those in the literature by explicitly specifying spatial association between pairs of locations as a function of distance between them. Data on apartment rents for the eight markets are used to illustrate the spatial model. Results indicate significant prediction improvement over traditional hedonic rent models that only include indicator variables to capture spatial effects.

Duke Scholars

Author Alan E. Gelfand Statistical Science