Persistent Link:
http://hdl.handle.net/10150/105763
Title:
Classification and Powerlaws: The logarithmic transformation
Author:
Leydesdorff, Loet; Bensman, Stephen
Citation:
Classification and Powerlaws: The logarithmic transformation 2006,
Issue Date:
2006
Description:
Journal of the American Society for Information Science and Technology 57(11) (2006) 1470-1486
URI:
http://hdl.handle.net/10150/105763
Submitted date:
2006-09-21
Abstract:
Published in Journal of the American Society for Information Science and Technology 57(11) (2006) 1470-1486. Abstract: Logarithmic transformation of the data has been recommended by the literature in the case of highly skewed distributions such as those commonly found in information science. The purpose of the transformation is to make the data conform to the lognormal law of error for inferential purposes. How does this transformation affect the analysis? We factor analyze and visualize the citation environment of the Journal of the American Chemical Society (JACS) before and after a logarithmic transformation. The transformation strongly reduces the variance necessary for classificatory purposes and therefore is counterproductive to the purposes of the descriptive statistics. We recommend against the logarithmic transformation when sets cannot be defined unambiguously. The intellectual organization of the sciences is reflected in the curvilinear parts of the citation distributions, while negative powerlaws fit excellently to the tails of the distributions.
Type:
Preprint
Language:
en
Keywords:
Science Technology Studies
Local subject classification:
classification; citation; journal; logarithmic; transformation; powerlaw

Full metadata record

DC FieldValue Language
dc.contributor.authorLeydesdorff, Loeten_US
dc.contributor.authorBensman, Stephenen_US
dc.date.accessioned2006-09-21T00:00:01Z-
dc.date.available2010-06-18T23:34:00Z-
dc.date.issued2006en_US
dc.date.submitted2006-09-21en_US
dc.identifier.citationClassification and Powerlaws: The logarithmic transformation 2006,en_US
dc.identifier.urihttp://hdl.handle.net/10150/105763-
dc.descriptionJournal of the American Society for Information Science and Technology 57(11) (2006) 1470-1486en_US
dc.description.abstractPublished in Journal of the American Society for Information Science and Technology 57(11) (2006) 1470-1486. Abstract: Logarithmic transformation of the data has been recommended by the literature in the case of highly skewed distributions such as those commonly found in information science. The purpose of the transformation is to make the data conform to the lognormal law of error for inferential purposes. How does this transformation affect the analysis? We factor analyze and visualize the citation environment of the Journal of the American Chemical Society (JACS) before and after a logarithmic transformation. The transformation strongly reduces the variance necessary for classificatory purposes and therefore is counterproductive to the purposes of the descriptive statistics. We recommend against the logarithmic transformation when sets cannot be defined unambiguously. The intellectual organization of the sciences is reflected in the curvilinear parts of the citation distributions, while negative powerlaws fit excellently to the tails of the distributions.en_US
dc.format.mimetypehtmen_US
dc.language.isoenen_US
dc.subjectScience Technology Studiesen_US
dc.subject.otherclassificationen_US
dc.subject.othercitationen_US
dc.subject.otherjournalen_US
dc.subject.otherlogarithmicen_US
dc.subject.othertransformationen_US
dc.subject.otherpowerlawen_US
dc.titleClassification and Powerlaws: The logarithmic transformationen_US
dc.typePreprinten_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.