Hi we run item analysis on the whole cohort since our scanner pumps out discrimination, point bi-serial and p-value I don't see any problem with using only 10% of the group either jim On Fri, Nov 30, 2012 at 8:13 AM, Jenny Morris <[log in to unmask]>wrote: > Dear All**** > > ** ** > > As this is the first time we have been using TBL I plan to run an item > analysis on the questions we are using. We have around 300 students in the > group and I was considering basing this analysis on 10% of the group. I’d > welcome feedback from others who have undertaken similar work.**** > > ** ** > > Thanks and best wishes**** > > ** ** > > Jenny**** > > ** ** > > Dr Jenny Morris**** > > Associate Professor (Senior Lecturer) in Health Studies**** > > Faculty of Health, Education and Society**** > > University of Plymouth**** > > Knowledge Spa**** > > Treliske**** > > Truro TR1 3HD**** > > Cornwall**** > > ** ** > > Tel: 01872 256461**** > > Web: http://www.plymouth.ac.uk/faculties/health**** > > ** ** > > ‘High quality education for high quality care’**** > > ** ** > > ** ** > > ** ** > > ** ** > -- Jim Sibley [log in to unmask] NEW Home Phone 604-564-1043 Work 604-822-9241