Accuracy and Robustness of House Price Index Methods

We evaluate the statistical properties of five different house price index methods with the objective of identifying one that is most accurate and robust when estimated at frequent time intervals and for distinctly local markets. We adopt a split-sample technique to establish a consistent basis for comparison of the different price index methods. Our results demonstrate that if suitable data is available for estimation of price indexes, the arbitrary aggregation of data across time and geography is not warranted. One model, the ‘hedonic imputation’, outperforms alternative models on all measures of accuracy and robustness. Differences in levels of accuracy between different models are found to be statistically significant.