"In this study, we show how use of the hedonic imputation method complicates the price index problem. In addition to the usual choice between formulas such as Fisher and Törnqvist, the fact that index compilers have some discretion over which prices are imputed implies that it is necessary to choose as well between different varieties of each formula. The functional form of the hedonic model must also be taken into account. We illustrate the importance of these issues in a housing context using house price data for three regions in Sydney over a 3-yr period. "("JEL "C43, E31, O47, R31) Copyright (c) 2008 Western Economic Association International.

The Sydney housing market peaked in 2003. The period 2001-2006 is, therefore, of particular interest since it captures a boom and bust in the housing market. We compute hedonic, repeat-sales and median price indexes for five regions in Sydney over this period. While the three approaches are in broad agreement regarding the timing of the turning point in the housing market, some important differences also emerge. In particular, we find evidence of sample selection bias in our hedonic and repeat-sales data sets, which in turn seems to generate bias (although in opposite directions) in our hedonic and repeat-sales indexes. The median indexes also may be biased as a result of an apparent decline in the average quality of houses sold in the latter part of the sample. Although in this case the repeat-sales indexes seem to generate the most reliable results, we nevertheless in general favor the hedonic approach. We also find evidence of convergence in prices across regions during the boom and divergence in the subsequent bust.

Owners' estimates of the value of their