Dear all
I am examining a study that perhaps should have used non-parametric tests on
the data. Instead a parametric test was used. I realise that certain
assumptions govern when a parametric and non-parametric test should be used,
but pragmatically, if a parametric test was used, how much of an impact will
that have on the outcome e.g. will it grossly over-estimate significance or
make ltlle difference?
Andrew Jull
Clinical Nurse Consultant
Auckland Hospital
NEW ZEALAND
NB my email address has changed to [log in to unmask] Please update your
address book.
|