Impact Factors and the Central Limit Theorem: Why citation averages are scale dependent
作者：
Highlights：
• We apply the Central Limit Theorem to study how citation averages depend on scale.
• Scale (i.e., journal size) affects Impact Factors and distorts their rankings.
• For a journal of size n, the range of Impact Factor values scales as 1/n.
• Large journals cannot have very high Impact Factors.
• The Impact Factors of very large journals converge to a single value.
• The Impact Factors of small journals are highly volatile.
• We analyzed 20 years of Impact-Factor and journal-size data from Clarivate Analytics.
• We propose the Φ index, a rescaled Impact Factor that accounts for scale effects.
摘要
•We apply the Central Limit Theorem to study how citation averages depend on scale.•Scale (i.e., journal size) affects Impact Factors and distorts their rankings.•For a journal of size n, the range of Impact Factor values scales as 1/n.•Large journals cannot have very high Impact Factors.•The Impact Factors of very large journals converge to a single value.•The Impact Factors of small journals are highly volatile.•We analyzed 20 years of Impact-Factor and journal-size data from Clarivate Analytics.•We propose the Φ index, a rescaled Impact Factor that accounts for scale effects.
论文关键词：Science of Science,Scholarly Publishing,Impact Factors,Journal size,Central Limit Theorem
论文评审过程：Received 4 April 2018, Revised 25 August 2018, Accepted 25 August 2018, Available online 17 September 2018, Version of Record 17 September 2018.
论文官网地址：https://doi.org/10.1016/j.joi.2018.08.011
