Forecasting the prices and rents for flats in large German cities

Arbeitspapier

In this paper, we make multi-step forecasts of the monthly growth rates of the prices and rents for flats in 26 largest German cities. Given the small time dimension, the forecasts are done in a panel-data format. In addition, we use panel models that account for spatial dependence between the growth rates of housing prices and rents. Using a quasi out-of-sample forecasting exercise, we find that both pooling and accounting for spatial effects helps to substantially improve the forecast performance compared to the benchmark models estimated for each of the cities separately. In addition, a true out-of-sample forecasting of the growth rates of flats' prices and rents for the next six months is done. It shows that in most cities both prices and rents for flats are going to increase. In some cities, the average monthly growth rate even exceeds 1%, which is a very strong increase compared to the overall price level increase of about 2% per year.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: DIW Discussion Papers ; No. 1207

Classification and Topics

• Classification: Wirtschaft ; Single Equation Models; Single Variables: Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions ; Single Equation Models; Single Variables: Panel Data Models; Spatio-temporal Models ; Forecasting Models; Simulation Methods
• Subject: Housing prices ; housing rents ; forecasting ; dynamic panel model ; spatial autocorrelation ; German cities

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Kholodilin, Konstantin A. ; Mense, Andreas
• Event: Veröffentlichung
• (who): Deutsches Institut für Wirtschaftsforschung (DIW)
• (where): Berlin
• (when): 2012

Further information

• Handle: http://hdl.handle.net/10419/61406
• Last update: 10.03.2025, 11:44 AM CET