Co-authorship networks and scientific performance. Evidences from a case study by using different bibliographic archives

The present contribution aims at exploring the effects of collaborative behaviours on scholar scientific performance. Mainly thanks to the availability of international bibliographic archives, seminal studies in various fields have been focused on co-authorship networks as a proxy of scholars' collaborative skills. To this purpose, several data sources are available but they present some drawbacks, especially when a specific discipline or community is under analysis. For instance, international archives might not be able to cover all kinds of scientific production, especially for social sciences where papers can be published in books or in national-oriented journals. In this scenario, we gathered co-authorship data on the scientific community of Italian academic statisticians as recorded in the Italian Ministry of University and Research database at March 2010. We used three bibliographic archives covering top-international journals as well as thematic and nationally oriented publications: Web of Science (WoS), Current Index to Statistics (CIS), and bibliographic information related to nationally funded research projects (PRIN). Since each data source showed peculiar characteristics influencing both network properties and performance results, we also discussed the main issues and the practical implications on merging data sources (i.e., record linkage and author name disambiguation) improving the bibliographic data quality for reconstruct an unified co-authorship network. Both network and individual covariates are used to model individual h-index by Generalized Extreme Value (GEV) distribution. Our results provided evidence of our hypotheses on distinct collaboration patterns among statisticians, as well as distinct effects of scientist network positions on scientific performance, by both Statistics subfield and data source. References De Stefano, D., Zaccarin, S. (2016). Co-authorship networks and scientific performance: an empirical analysis using the generalized extreme value distribution. Journal of Applied Statistics 43: 262-279. De Stefano, D., Fuccella, V., Vitale, M. P., Zaccarin, S. (2013) The use of different data sources in the analysis of co-authorship networks and scientific performance. Social Networks 35: 370–381. Fuccella, V., De Stefano, D., Vitale, M. P., Zaccarin, S. Improving co-authorship network structures by combining multiple data sources: evidence from Italian academic statisticians. Scientometrics (to appear)