Dear all,
I have been asked to consider performing pairwise post hoc tests
comparing multiple treatment groups which do not, overall, differ
significantly according to ANOVA, since this approach has previously
been used in published studies in the same field. I cannot find any
evidence from the statistical literature to support this method of
analysis. I would be grateful if someone could point me in the direction
of published references either justifying or disputing this approach so
that I can discuss it further with my colleagues.
Thanks in advance
Liz Hensor
Dr Elizabeth M A Hensor PhD BSc (Hons)
Data Analyst
Academic Unit of Musculoskeletal and Rehabilitation Medicine
36 Clarendon Road
Leeds
West Yorkshire
LS2 9NZ
Tel: +44 (0) 113 3434944
Fax: +44 (0) 113 2430366
[log in to unmask]
|