CMStatistics 2017: Start Registration
View Submission - CFE
A1194
Title: Nonlinear spatial hedonic quantile regression: Housing prices, relevant characteristics, and their shadow prices Authors:  Markus Fritsch - University of Passau (Germany) [presenting]
Harry Haupt - University of Passau (Germany)
Joachim Schnurbus - University of Passau (Germany)
Abstract: In many applications of statistical real estate appraisal methods the following challenges arise simultaneously: [1] relevant characteristics of a property need to be identified, [2] shadow prices (marginal market valuation) of characteristics and [3] prices of bundles (of characteristics) not observed need to be estimated. State of the art hedonic housing price analysis comprises [i] modeling price functions nonlinearly, [ii] accounting for complex spatial association structures (horizontal market segmentation), and [iii] allowing for varying functional relationships across the conditional price distribution (vertical market segmentation). We discuss two general classes of nonlinear quantile regression models which meet these criteria but pursue different avenues to simultaneously address the challenges [1]-[3]. Due to the underlying assumptions, the inference obtained from both model classes differs analytically and -- more importantly -- leads to different economic interpretations. The methods are illustrated by applying them to data generating processes with various degrees of functional and spatial complexity in a Monte Carlo study and to geo-referenced urban house price data.