Susan Smith posted a question about the Science Citation Index  impact
factors...

Susan: Impact factors are an attempt to refine the raw citation counts ISI
gathers to rank the journals it tracks. The idea is that some journals are
going to be cited a great deal simply because each issue is so large and
carries so many articles. Others may be thinner, and so will appear not to be
cited as much -- even though the _proportion_ of citable items in them that
were actually cited may be higher than the proportion of citable items that
were cited in the larger journals. The impact factor, then, calculates how
many of the citable items were actually cited for each journal, rather than
just giving a raw count. More specifically, it's "the average number of
citations given in a specific year to documents published in that journal in
the two preceding years, divided by the number of 'citable' documents
published in that journal in those two years." This quote comes from an
article by Moed and Van Leeuwen in the Journal of the Journal of the American
Society for Information Science, 46(6): 461-467 [July, 1995]. I just happened
to run across that article and your posting at just about the same time, so
I'm passing it along. Moed and Van Leeuwen write at some length about how the
IF is derived and question whether ISI is properly thinking about what should
go into the "citable document" bucket. Very interesting stuff...

--Paul Crandall
Serials Product Specialist, UMI
[<Crandall01@AOL.COM>]