Economies of Scope in Data Aggregation: Evidence from Health Data
Bruno Carballa-Smichowski (Joint Research Committee); Nestor Duch Brown (Joint Research Committee); Seyit Höcük (Centerdata); Pradeep Kumar (Centerdata); Bertin Martens (Joint Research Committee); Joris Mulder (Centerdata); Patricia Prüfer (Centerdata, Tilburg University)
Abstract
Economies of scope in data aggregation (ESDA) are attracting the attention of policymakers and researchers. However, the concept remains blurry and lacks empirical backing. After defining and formalizing ESDA, we estimate them by progressively adding explanatory variables to a dataset of health(-related) data that we use to predict health outcomes. We show that a 1% increase in the number of predictors improves prediction accuracy by 0.087% to 0.132%. We observe a positive non-linear relation between variable complementarity and ESDA. We find that ESDA show increasing returns up to the third quartile of variables, and diminishing returns thereafter.