Modelling count response variables in informetric studies: Comparison among count, linear, and lognormal regression models
作者：
Highlights：
• The negative binomial often seems to be more appropriate than other count models for informetric data.
• Linear regression model predicted negative values for a few of the response variables modelled.
• Linear regression model performed worse than both the negative binomial and lognormal models.
• Overall, the negative binomial model performed slightly better than the lognormal model.
摘要
•The negative binomial often seems to be more appropriate than other count models for informetric data.•Linear regression model predicted negative values for a few of the response variables modelled.•Linear regression model performed worse than both the negative binomial and lognormal models.•Overall, the negative binomial model performed slightly better than the lognormal model.
论文关键词：Count response variable,Linear regression model,Count regression models,Negative binomial regression model,Lognormal regression model,Informetric studies
论文评审过程：Received 7 January 2015, Revised 10 May 2015, Accepted 11 May 2015, Available online 28 May 2015, Version of Record 28 May 2015.
论文官网地址：https://doi.org/10.1016/j.joi.2015.05.001
