2012/05/11 by Ping Zhou, Zhou Ping, Zhou, Ping +2 · 1 citation
Computer Science · Decision Sciences · Physics and Astronomy · Social Sciences · #Digital Libraries (cs.DL) #FOS: Computer and information sciences #FOS: Physical sciences #Higher Education Governance and Development #Physics and Society (physics.soc-ph) #cs.DL #physics.soc-ph #scientometrics and bibliometrics research
paper · pdf · doi:10.48550/arxiv.1205.2424
arxiv created 2012/05/11 · openalex publication_date 2012/05/11 · arxiv updated 2012/05/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Metrics based on percentile ranks (PRs) for measuring scholarly impact involves complex treatment because of various defects such as overvaluing or devaluing an object caused by percentile ranking schemes, ignoring precise citation variation among those ranked next to each other, and inconsistency caused by additional papers or citations. These defects are especially obvious in a small-sized dataset. To avoid the complicated treatment of PRs based metrics, we propose two new indicators - the citation-based indicator (CBI) and the combined impact indicator (CII). Document types of publications are taken into account. With the two indicators, one would no more be bothered by complex issues encountered by PRs based indicators. For a small-sized dataset with less than 100 papers, special calculation is no more needed. The CBI is based solely on citation counts and the CII measures the integrate contributions of publications and citations. Both virtual and empirical data are used so as to compare the effect of related indicators. The CII and the PRs based indicator I3 are highly correlated but the former reflects citation impact more and the latter relates more to publications.