Colin,
Your university seems to be a bit slow with this.
I have been on a working party at Sheffield University for a year
now, advising on statistical aspects of the transparency review.
You can tell your university that it is NOT necessary to use
retrospective questionnaires, and it is NOT necessary for every
member of staff to participate. Our approach uses sampling. Those
sampled keep a careful diary of their work for one week. The
sampling exercise is being conducted by our Statistical Services
Unit, the department's consulting wing. Our approach has been
approved by JM Consulting. I am amazed that they are still
propagating the idea that retrospective assessment of time usage is
acceptable. We came down very firmly against it from the start.
You can also tell your colleagues that this IS worth doing, at least
in my opinion, but only if it is done well, so that the results are
convincing. Your university seems set on getting such poor quality
data that I can sympathise with people not wanting to bother with the
questionnaire.
I would be very interested to hear how many other universities have
actually consulted their own statisticians on this. Perhaps COPS
should follow this up.
Tony
----
Professor A O'Hagan Email: [log in to unmask]
Department of Probability and Statistics
University of Sheffield Phone: +44 114 222 3773
Hicks Building
Sheffield S3 7RH, UK Fax: +44 114 222 3759
----------- http://www.shef.ac.uk/~st1ao/ ------------
|