| Abstract: | ABSTRACT The index proposed by Ellison and Glaeser (1997) is now well established as the preferred method for measuring the localization of economic activity. In this paper we develop an alternative localization measure that is consistent with the theoretical framework originally proposed by Ellison and Glaeser. Our measure follows directly from the Random Utility (Profit) Maximization (RUM) location decision model. Because the distributional assumptions in our model are fully compatible with RUM, we are able to offer a more efficient measure of industry clustering. |
