Statistical inference on the h-index with an application to top-scientist performance

Abstract

Despite the huge literature on h-index, few papers have been devoted to the statistical analysis of -index when a probabilistic distribution is assumed for citation counts.2 WÐBÑ oe T Ð\  BÑ WÐBÑ . Therefore, constitutes the probability that a paper of the scholar receives more than citation. The random variable is usually required to be "heavy-tailed" B \ in the scientometric applications (see e.g. Glänzel, 2006Glänzel, , 2010, even if the results given in this section hold in general. Hence, if the scholar has published papers, the random 8 variables represent the citation counts for his/her papers. In order to develop \ ß á ß \ 8 " 8

Are the authors of highly cited articles also the most productive ones?

“…The literature on research excellence is particularly rich and can be segmented in at least three groups of contributions. The first area in fact concerns the bibliometric indicators proposed for the evaluation of performance in general, and in consequence for the identification of top scientists (Abramo et al, 2013a;Baccini et al, 2012;Bornmann et al, 2007;van Raan, 2006;Egghe, 2006;Hirsch, 2005). A second group of works concerns the study of the determinants of performance, particularly the personal and contextual variables that can make a researcher a top scientist (Costas et al, 2012;Abramo et al, 2011b;Abramo et al, 2009b).…”