hi
a study has been carried out where
women were asked about an ''a service that might be provided'
each woman was seen by a midwife (therefore some midwives saw up to six
women) and the midwives were asked 'if a service was provided'
what we are trying to ascertain is the level of agreement between the woman
and midwives responses and if the agreement was significant or not
the kappa statistic has been used but i would like to know if anyone has
any other suggestions about how concordance /discordance can be measured
does the fact each midwife (there were approxiamately 25 of them) is
counted more than once , there were approxiamately 120 women - the numbers
of women that each midwife saw varied
any suggestions would be much appreciated
regards
ann
------------
Ann e Fitzmaurice
Medical Statistician
Dugald Baird Centre for Research on Women's Health
University of Aberdeen
Aberdeen Maternity Hospital
Aberdeen, Scotland
Email [log in to unmask]
Tel 01224 553876
Fax 01224 553708
[log in to unmask]
|