Hedonic House Price ModelingBased on Multilevel Structured Additive Regression - Computational Approaches for Urban Environments - page 93

Chapter 5
Hedonic House Price Modeling
Based on Multilevel Structured Additive
Regression
Alexander Razen, Wolfgang Brunauer, Nadja Klein, Stefan Lang, and
Nikolaus Umlauf
Abstract This chapter reviews recent developments in hedonic modeling of house
prices based on structured additive regression (STAR) models. In STAR models,
continuous covariates are modeled as P(enalized)-splines. Furthermore, random
effects for spatial indexes, smooth functions of two-dimensional surfaces, and
(spatially) varying coefficient terms may also be estimated using this methodology.
Based on hierarchical STAR models, we discuss a number of useful extensions.
With respect to value-at-risk concepts, financial institutions are often not only
interested in the expected value but also in different quantiles of the distribution
of real estate prices. To meet these requirements, we apply multilevel STAR models
for location scale and shape (GAMLSS type regression) and a Bayesian version of
quantile regression. As another extension, we sketch multiplicative region-specific
scaling factors for nonlinear covariates in order to permit spatial variation in the
nonlinear price gradients.
Keywords Bayesian hierarchical models ￿ Hedonic pricing models ￿ GAMLSS ￿
Bayesian quantile regression ￿ MCMC
Opinions expressed by the authors do not necessarily reflect the official viewpoint
of UniCredit Bank Austria AG.