A ‘power law’ based method to reduce size-related bias in indicators of knowledge performance: An application to university research assessment
作者：
Highlights：
• The method reduces size-related bias affecting knowledge performance indicators using the scale-free property of power laws.
• The paper analyses the issue of size-related bias introduced in evaluation exercise outputs by varying university size.
• A scaled performance indicator is introduced for the normalization of the evaluation average score distributions.
• The method has policy implications and gives a contribution for the future design of research assessment exercises.
摘要
•The method reduces size-related bias affecting knowledge performance indicators using the scale-free property of power laws.•The paper analyses the issue of size-related bias introduced in evaluation exercise outputs by varying university size.•A scaled performance indicator is introduced for the normalization of the evaluation average score distributions.•The method has policy implications and gives a contribution for the future design of research assessment exercises.
论文关键词：Knowledge performance,Research assessment,Research productivity indicators,Power laws,Dimensional bias,Scale-free property
论文评审过程：Received 29 September 2017, Revised 30 August 2018, Accepted 4 October 2018, Available online 26 October 2018, Version of Record 26 October 2018.
论文官网地址：https://doi.org/10.1016/j.joi.2018.10.005
