1# RECORD 6ae7a44769e1c434ed0b69f49a62bca7496a80ac2# TITLE: Higher frequency hedonic property price indices: a state-space approach3# YEAR: 2020.0 VENUE: Empirical Economics DOI: 10.1007/s00181-020-01862-y4# AUTHORS: R. Hill; A. Rambaldi; Michael Scholz5# PAGES: 25 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: The hedonic imputation method allows characteristic shadow prices to evolve over time. These shadow prices are used to construct matched samples of predicted prices, which are inserted into standard price index formulas. We use a spatio-temporal model to improve the method’s effectiveness on housing data at higher frequencies. The problem is that at higher frequencies, there may not be enough observations per period to reliably estimate the characteristic shadow prices. In such cases, the reliability of the hedonic imputation method is improved by using a state-space formulation which yields estimates of the shadow prices that are weighted sums of previous periods’ information. In addition, the state-space representation of the model includes a geospatial spline surface which significantly reduces the number of parameters to be estimated when compared to the standard practice of including postcode dummies in the model. Empirically, using a novel criterion, we show that in higher frequency comparisons, our hedonic method outperforms competing alternatives.789===== PAGE 1 (score 6, numeric-paren 0, table-words 1, var-words 4) =====1011Empirical Economics (2021) 61:417–44112https://doi.org/10.1007/s00181-020-01862-y13Higher frequency hedonic property price indices:14a state-space approach15Robert J. Hill1 · Alicia N. Rambaldi2 · Michael Scholz116Received: 16 June 2019 / Accepted: 17 March 2020 / Published online: 11 April 202017© The Author(s) 202018Abstract19The hedonic imputation method allows characteristic shadow prices to evolve over20time. These shadow prices are used to construct matched samples of predicted prices,21which are inserted into standard price index formulas. We use a spatio-temporal model22to improve the method’s effectiveness on housing data at higher frequencies. The prob-23lem is that at higher frequencies, there may not be enough observations per period to24reliably estimate the characteristic shadow prices. In such cases, the reliability of25the hedonic imputation method is improved by using a state-space formulation which26yields estimates of the shadow prices that are weighted sums of previous periods’ infor-27mation. In addition, the state-space representation of the model includes a geospatial28spline surface which significantly reduces the number of parameters to be estimated29when compared to the standard practice of including postcode dummies in the model.30Empirically, using a novel criterion, we show that in higher frequency comparisons,31our hedonic method outperforms competing alternatives.32Keywords Housing market · Hedonic imputation · State-space model · Geospatial33data · Spline · Quality adjustment and matched sample34JEL C33 · C43 · R3135We acknowledge financial support for this project from the Austrian Research Promotion Agency (FFG),36Grant #10991131, and we thank Australian Property Monitors for supplying the data. We are very thankful37for the detailed and excellent comments provided by an anonymous referee and the handling editor.38B Michael Scholz39michael.scholz@uni-graz.at40Robert J. Hill41robert.hill@uni-graz.at42Alicia N. Rambaldi43a.rambaldi@uq.edu.au44145Department of Economics, University of Graz, Universitätsstr. 15/F4, 8010 Graz, Austria46247School of Economics, The University of Queensland, St. Lucia, QLD 4072, Australia4812349