Central City Revitalization: A Predictive Model

The object of this paper is to increase the understanding of the gentrification process by developing a set of representative indices that could be used to assess the likelihood of gentrification occurring in a central city neighborhood. Using Boston, Massachusetts as a representative city, economic, housing, social and amenity variables were collected from the 1970 U.S. Census. A sample of blocks that did and did not revitalize after 1970 was chosen. As the gentrification outcome was known with certainty, a logistic regression model was estimated. The estimated model quite accurately classified the neighborhoods into their respective grouping, resulting in a block-level statistical model of housing revitalization.