Your presentation of the statistics does not
take into account the possible bias
introduced by the the methods use to select
the sample size.
Your sample can not be said to represent the
entire Infoworld print subscriber base with
out research into how well the non-hardware
vendor, non-software vendor universe
coincides with the over-all subsriber
universe.
Not that I am saying that the poll does NOT
represent the entire print subscriber
universe, my point is that we have no way of
knowing whether it does or not, because we
do not know if any bias was introduced
because of the sample selection.
regards,
Lee
XLConnect Solutions, Inc.
Opions expressed are mine and should not
be taken to represent my employers.
For questions or comments, email the Forums Editor