Percentile Ranks and the Integrated Impact Indicator (I3)

In a brief communication to this journal, entitled “Basic Properties of Both Percentile Rank Scores and the I3 Indicator,” Rousseau (in press) proposed to define percentile classes in the case of the Integrated Impact Indicator (I3) right-open so that the largest number in a set always belongs to the highest percentile. He argued that “this completely solves the issue raised by Leydesdorff & Bornmann (2011) that in the case of small numbers (e.g., reviews), papers would for arithmetic reasons have lower percentile values.”