How to consider fractional counting and field normalization in the statistical modeling of bibliometric data: A multilevel Poisson regression approach

作者：

Highlights：

• Fractional counting and field normalization are indispensable in bibliometrics.

• Multilevel Poisson regression provides statistical models for the two procedures.

• Fractional counting I simulates the usual numerical procedures statistically.

• In addition fractional counting II avoids publication duplicates in the data.

• Fractional counting II does not depend anymore on the type of fractional counting.

摘要

•Fractional counting and field normalization are indispensable in bibliometrics.•Multilevel Poisson regression provides statistical models for the two procedures.•Fractional counting I simulates the usual numerical procedures statistically.•In addition fractional counting II avoids publication duplicates in the data.•Fractional counting II does not depend anymore on the type of fractional counting.

论文关键词：Fractional counting,Field normalization,Multilevel model,Poisson regression,Multilevel multiple membership model

论文评审过程：Received 23 July 2018, Revised 12 March 2019, Accepted 12 March 2019, Available online 3 April 2019, Version of Record 3 April 2019.

论文官网地址：https://doi.org/10.1016/j.joi.2019.03.007