Integrating Microdata on Higher Education Institutions (HEIS) with Bibliometric and Contextual Variables: A Data Quality Approach

An introduction on data quality Data quality has been addressed in different research areas, mainly including statistics, management and computer science. The statistics researchers were the first to investigate some of the problems related to data quality by proposing a mathematical theory for considering duplicates in statistical data sets, in the late 60s. The management research began at the beginning of the 80s; the focus was on how to control data manufacturing systems in order to detect and eliminate data quality problems. Only at the beginning of the 90s, computer science researchers began considering the data quality problem, specifically how to define measure and improve the quality of electronic data, stored in databases, data warehouses and legacy systems. Data quality has been defined as “fitness for use”, with a specific emphasis on its subjective nature. Another definition for data quality is “the distance between the data views presented by an information system and the same data in the real world”; such a definition can be seen as an operational definition, although evaluating data quality on the basis of comparison with the real world is a very difficult task. Data quality is well-recognized as a multidimensional concept including several distinct dimensions (Batini & Scannapieco, 2006) proposed in various contexts (Catarci & Scannapieco, 2002). A crucial dimension of data quality is data accuracy: it measures the closeness between a value v and a value v’, considered as the correct representation of the real-life phenomenon that v is intended to represent. However, quality is more than simply data accuracy. Other significant dimensions play a role in the definition of the Data Quality concept, including completeness, consistency, and timeliness (i.e. degree of up-todateness), just to cite some significant ones.