CMStatistics 2018: Start Registration
View Submission - CFE
Title: Mixed kernel estimation of counterfactual distributions for Munich rent survey Authors:  Joachim Schnurbus - University of Passau (Germany) [presenting]
Goeran Kauermann - LMU Munich (Germany)
Abstract: The tremendous increase in rent prices for apartments in larger cities is a problem in most countries. A general question in this respect is whether increments in the rent are merely a matter of rising demand that is exploited or whether an increasing quality of apartments also contributes to the increase in the apartment rent. To tackle this question we provide a counterfactual distribution-based decomposition of several current releases of rent surveys from Munich, Germany, that allows to disentangle the rent increase over time into two effects. First, the rent increase caused by an improvement of the flats and second, the increase due to inflation and demand. A novel nonparametric kernel estimator for mixed continuous and discrete covariates is proposed for estimating the counterfactual distribution. Application to the Munich rent market indicates that the majority of the rent increase seems not to be justified by improved flat characteristics.