We employ the recent Jordà et al. (2016) and Knoll et al. (2017) datasets to investigate the long-run relationship between house prices and credit volume, allowing for interest rate, real exchange rate and real gross domestic product (GDP). We refine the analysis using more recent data at the quarterly-level to define relevant co-integrating relationships across a number of European economies. Housing, GDP and credit cross-sectional averages are included in the analysis to detect potential spill-over effects. Empirical results indicate cross-country heterogeneities and an uneven feedback mechanism between credit and housing – the full loop is established only for several countries in the dataset. Important results relate to the statistical properties of the housing time series. Grouping countries for panel-like econometric exercises may lead to spurious regression results, poor inference and misleading policy implications. Short-run dynamics, compared to the long-run may often lead to contradicting policy advice if the order of integration of the house price series is not properly accounted for. Accounting for spatial patterns of house prices which cannot be attributed to global output shocks may provide useful insights into policy making.
JEL Codes: C21, E51, O18, R31.
The views expressed are those of the author(s) and do not necessarily represent those of the Bank of Lithuania.