Hall (2005) - A Note On The Bias In Herfindahl Type Measures Based On Count Data

From edegan.com
Revision as of 17:33, 18 March 2013 by imported>Ed
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Reference

  • Hall, B.H. (2005), "A note on the bias in Herfindahl-type measures based on count data", Revue D' Economie Industrielle, Paris Editions, Techniques Et Economiques, Vol.110, pp.149
@article{hall2005note,
  title={A note on the bias in Herfindahl-type measures based on count data},
  author={Hall, B.H.},
  journal={Revue D' Economie Industrielle, Paris Editions, Techniques Et Economiques},
  volume={110},
  pages={149},
  year={2005},
  abstract={A Herfindahl index of constructed from shares based on count data where the number of counts is small will generally be biased downward because of the statistical properties of count data and Jensen’s inequality. This note suggests a simple correction for the bias and illustrates its applicability when using measures based on patent data and patent citation data.},
  discipline={Econ},
  research_type={Measures},
  industry={},
  thicket_stance={},
  thicket_stance_extract={},
  thicket_def={},
  thicket_def_extract={},  
  tags={},
  filename={Hall (2005) - A Note On The Bias In Herfindahl Type Measures Based On Count Data.pdf}
}

File(s)

Abstract

A Herfindahl index of constructed from shares based on count data where the number of counts is small will generally be biased downward because of the statistical properties of count data and Jensen’s inequality. This note suggests a simple correction for the bias and illustrates its applicability when using measures based on patent data and patent citation data.