Journal of Real Estate Finance and Economics, 29:2, 147±148, 2004
# 2004 Kluwer Academic Publishers. Manufactured in The Netherlands.
Spatial Statistics and Real Estate
R. KELLEY PACE*
LREC Endowed Chair of Real Estate, Department of Finance, E.J. Ourso College of Business Administration,
Louisiana State University, Baton Rouge, LA 70803-6308, U.S.A.
JAMES P. LESAGE
University of Toledo, Department of Economics, Toledo, OH 43606, U.S.A.
The ®rst special issue of the Journal of Real Estate Finance and Economics on ``Spatial
Statistics and Real Estate,'' published in 1998, helped spur development of this topic. As
evidence of that, the papers in that issue were cited an average of 9.7 times (as of October
1, 2003). In comparison, the August 1998 issue of the Journal of Political Economy
contained papers that were cited an average of 8.3 times.
The current special issue contains a number of papers that could have a similar or
greater impact on statistical methodology in real estate research. The ®rst paper, ``The
Dynamics of Location in Home Price'' by Alan Gelfand, Mark Ecker, John Knight, and
C. F. Sirmans, provides a general spatiotemporal model that subsumes repeat sales, panel
data, and spatial hedonic models. They illustrate these models using real estate data from
The second paper, ``Modeling Spatial and Temporal House Price Patterns: A
Comparison of Four Models'' by Bradford Case, John Clapp, Robin Dubin, and
Mauricio Rodriguez, presents results from a competition among multiple approaches to
the spatiotemporal prediction problem. Each participant had the courage to predict out-of-
sample without knowledge of the actual observations. A referee, Mauricio Rodriguez, then
computed the actual performance across each model. The participants subsequently
revised their models and tried again without knowing the out-of-sample observations. The
combination of these ®rst and second papers gives some interesting insights into the
theoretical and applied aspects of spatiotemporal modeling.
The third paper, ``Alternative Models for Describing Spatial Dependence among
Dwelling Selling Prices'' by Ana Militino, Lola Ugarte, and L. Garcia
compares various spatial econometric and geostatistical models and adds individual
effect models using housing data from Pamplona, Spain. This paper represents one
*The ®rst author was funded by National Science Foundation grant BCS-0136193, and the second author by
National Science Foundation grant BCS-0136229.