Conceptual difficulties in the use of statistical inference in citation analysis
arXiv:1612.03285 · doi:10.1016/j.joi.2016.09.012
Abstract
In this comment, I discuss the use of statistical inference in citation analysis. In a recent paper, Williams and Bornmann argue in favor of the use of statistical inference in citation analysis. I present a critical analysis of their arguments and of similar arguments provided elsewhere in the literature. My conclusion is that the use of statistical inference in citation analysis involves major conceptual difficulties and, consequently, that the usefulness of statistical inference in citation analysis is highly questionable.
References in corpus (4)
- Caveats for using statistical significance tests in research assessments
- The precision of the arithmetic mean, geometric mean and percentiles for citation data: An experimental simulation modelling approach
- From rankings to funnel plots: the question of accounting for uncertainty when measuring university research performance
- Funnel plots for visualizing uncertainty in the research performance of institutions
Cited by in corpus (4)
- The Accuracy of Confidence Intervals for Field Normalised Indicators
- On The Peer Review Reports: Does Size Matter?
- The Research Production of Nations and Departments: A Statistical Model for the Share of Publications
- Confidence intervals for normalised citation counts: Can they delimit underlying research capability?