A Simple Hybrid Model for Estimating Real Estate Price Indexes

Abstract The accurate measurement of housing and real estate prices is of real theoretical importance and is crucial to understanding the operation of the housing market. Two basic techniques - hedonic and repeat sales methods - for measuring and analyzing the structure of housing prices have been developed. This paper presents an explicit model for combining samples of single sales and multipule sales for the analysis of housing prices and the computation of more efficient price indices. The procedure is based upon an explicit error structure, incorporating a random walk in housing prices. It is also based upon robust generalized least-squares methods to improve the efficiency of estimation. The technique is illustrated using a unique sample of condominium sales during a 12-year period in downtown Los Angeles.