Indices and Clustering

Repeat Sales House Price Index Methodology
(with Lawrence Brown and Chaitra Nagaraja)
Journal of Real Estate Literature, Vol. 22 Issue 1, January 2014, 23-56.

Real Estate Prices in Beijing 1644 to 1840 (with Dan Raff and Se Yan)   Abstract  
Explorations in Economic History, Vol. 50, No. 3, July 2013, 335-462.

This paper provides the first estimates of housing price movements for Beijing in late pre-modern China. We hand-collect from archival sources transaction prices and other house attribute information from the 498 surviving house sale contracts for Beijing during the first two centuries of the Qing Dynasty (1644-1840), a long period without major wars, political turmoil, or significant institutional change in the Chinese capital. We use hedonic methods to construct a real estate price index for Beijing for the period. The regression analysis explains a major proportion of the variance of housing prices. We find that house prices grew steadily for the first half-century of the Qing Dynasty and declined afterwards in both nominal and real terms through the late eighteenth century. Nominal prices grew starting in the late eighteenth century and declined from the early nineteenth century through 1840. But these price changes occurred with contemporaneous price changes in basic measures of the cost of living: there was little change in real terms to the end of our period.

Anisotropic Autocorrelation in House Prices (with Kevin Gillen and Thomas Thibodeau)   Abstract  
Journal of Real Estate Finance and Economics, Vol. 23, Issue 1, 2001

This paper examines anisotropic spatial autocorrelation in single-family house prices and in hedonic house price equation residuals using a spherical semivariogram and transactions data for one county in the Philadelphia, Pennsylvania MSA. Isotropic semivariograms model spatial relationships as a function of the distance separating properties in space. Anisotropic semivariograms model spatial relationships as a function of both the distance and the direction separating observations in space. The goals of this paper are: (1) to determine whether there is spatial autocorrelation in hedonic house price equation residuals; and (2) to empirically examine the validity of the isotropy assumption. We estimate the parameters of spherical semivariograms for house prices and for hedonic house price equation residuals for 21 housing submarkets within Montgomery County, Pennsylvania. These housing submarkets are constructed by dividing the county into 21 groupings of economically similar adjacent census tracts. Census tracts are grouped according to 1990 census tract median house prices and according to characteristics of the housing stock. We fit the residuals of each submarket hedonic house price equation to both isotropic and anisotropic sepherical semivariograms. We find evidence of spatial autocorrelation in the hedonic residuals in spite of a very elaborate hedonic specification. Additionally, we have determined that, in some submarkets, the spatial autocorrelation in the hedonic residuals is anisotropic rather than isotropic. The empirical results suggest that the spatial autocorrelation in Montgomery County single-family house price equation residuals is anisotropic in submarkets where residents typically commmute to a regional or local Central Businss District (CBD).

Frequency of Transaction and House Price Modeling (with Henry O. Pollakowski and Bradford Case)   Abstract  
Journal of Real Estate Finance and Economics Vol. 14.1/2, 1997, 173-188

This article examines the characteristics and price behavior of repeatedly transacted properties. Using data from four U.S. counties, we estimate hedonic price models of properties grouped by transaction frequency, and compare estimated standard deviations and estimated appreciation rates by group. For each of four counties studied, we find that estimated house price appreciation is systematically higher among properties that transact more frequently. One possible explanation for this result is that purchasers make property improvements that are not adequately reflected in the available data We also find that estimated standard deviations of the disturbance term show a marked decrease as the frequency of transaction increases. Since frequently transacting properties are not found to be systematically more homogeneous than seldomly transacting properties, we do not attribute this to any increase in homogeneity for frequently transacting properties, but rather to the length of time elapsed between transactions of properties. The findings of this article suggest that repeat-sales price models may need to be adjusted to account for cross-sectional variation in transaction probabilities—that is, the selectivity of the subsample of properties that transacted (or transacted repeatedly) during any finite study period.

Homogeneous Groupings of Metropolitan Housing Markets (with Jesse M. Abraham, William N. Goetzmann)   Abstract  
Journal of Housing Economics, Vol 3.Issue 3, 1994, 186-206

In this paper, we use clustering techniques to identify structural relationships among U.S. housing markets and develop a bootstrapping procedure to test whether associations between cities are significant. The method allows the creation of meaningful “groups” of cities. These groups are useful for purposes of diversification, and for identifying appropriate hedging proxies for city-specific futures instruments. A clustering algorithm, K-means, is applied to the 1977-1992 returns to housing price indices in 30 metropolitan U.S. housing markets. It demonstrates strong regional differences in housing price fluctuations. When three groups are specified, we find a West Coast group, an East Coast group, and a central U.S. group. When more groups are specified, the West Coast divides into two clusters that are not north and south, and Texas cities separate from the central U.S. group. Using bootstrap methods, we reject the hypothesis that these groupings are a result of random associations.

On Choosing Among House Price Index Methodologies (with Bradford Case, Henry O. Pollakowski)   Abstract  

This paper compares housing price indices estimated using three models with several sets of property transaction data. The commonly used hedonic price model suffers from potential specification bias and inefficiency, while the weighted repeat-sales model presents potentially more serious bias and inefficiency problems. A hybrid model combining hedonic and repeat-sales equations avoids most of these sources of bias and inefficiency. This paper evaluates the performance of each type of model using a particularly rich local housing market database. The results, though ambiguous, appear to confirm the problems with the repeat sales model but suggest that systematic differences between repeat-transacting and single-transacting properties lead to bias in the hedonic and hybrid models as well.