Dear all,
Thanks to everyone who replied to my enquiry (appended at the bottom of this
email). Below is a summary of all the replies which I received.
Best wishes
Jenny
**********************
hiya,
may be you want to look into multiple regression (with stepwise), clustering and
discrimenant analysis. the latter 2 basically give you a over view seeing who
and who is alike, may be it is affected by age, family background, gender or
what have you.
multiple regression provide alternative approach but stepwise let you to see
which independent (age family background etc) is most infulencial in this
case.
If you need any help just let me know. I have a small website / company going
on..
WWW.Dazuni.co.uk
best of luck.
JL
*********************************
Hi Jenny,
Interesting questions.
I currently head up the research methods course for the undergraduate
medical course which started here in UEA two years ago. This involves
statistics in years 1 and 2 and involved a lot of study design and
statistical concepts rather than just techniques.
I don't have any objective information or info but I can give you my
impression of our first two cohorts :
1) Males and females appear to do equally well based upon the last 3
assignments. However, it's almost solely females that seek further help when
they've not done well. I'm not sure why but it could indicate a difference
in attitude.
2) Those students without 'A'-level mathematics think they are at a
disadvantage but my impression is that they are not. I've not noted any
difference but I've not looked at this in detail. It's possible something I
could do at some point.
Best wishes and good luck,
Lee
Dr Lee Shepstone,
Senior Lecturer in Medical Statistics,
School of Medicine, Health Policy and Practice,
University of East Anglia
*************************************************
Dear Jenny,
I did a very small study as part of my PGCE in university teaching on some
environmental health/science students & found that girls performed (&
attended) better than boys. Also, background in maths was associated with
performance in exam based assessment, but not performance in practical
assessments (which were much more strongly associated with attendance). Not
sure how general all this is though.
Nicky
Dr. Nicky Welton
MRC Health Services Research Collaboration
Department of Social Medicine
University of Bristol
Canynge Hall
Whiteladies Road
Bristol BS8 2PR
Tel: +44 (0)117-331-3902
Fax: +44 (0)117-928-7365
Email: [log in to unmask]
***************************************
Jenny
I'm personally not aware why there would be any strongly influential gender
issues, though attitudes to maths likely to be relevant also. If you are
collecting data, you might want to collect it for both the students and the
lecturers as there could be issues of empathy/interactions between lecturers
and students [anecdotally I'd expect male lecturers on statistics to be more
likely to explain statistics using examples from, say, football, which might
turn the female students off?]. There could also be other generic gender
issues in how people learn and other factors worth controlling for [age,
socio-economic background etc etc]
I suggest you contact the Royal Statistical Society Centre for statistical
education http://science.ntu.ac.uk/rsscse/
as well as looking at journal of statistical education
http://www.amstat.org/publications/jse/ and contacting its editor
hope this helps
regards
David
Matz David <[log in to unmask]>
*****************************************
Dear Jenny,
Re (3), see Onwuegbuzie AJ, Academic Procrastination and Statistics Anxiety,
Assessment & Evaluation in Higher Education, 2004, 29, 1, 3-19.
Re (2), it has always been my impression that females outperformed males. We
used to award a prize each year to the 3rd year medic who did best in
Statistics, and it practically always went to a female. My impression is that
a
large part of the explanation is simply greater legibility! I have never
looked
at the issue for our MPH students who submit scripts for their SPSS modules
word-processed - maybe the sample size is a little small for this.
Hope this helps.
Robert G. Newcombe PhD CStat Hon MFPH
Reader in Medical Statistics
University of Wales College of Medicine
Heath Park
Cardiff CF14 4XN
Phone 029 2074 2329
Fax 029 2074 2898
http://www.uwcm.ac.uk/study/medicine/epidemiology_statistics/research/statistics/newcombe.htm
*****************************************
I don't have answers to any of your questions, but in planning this proposal
I would hope there might be a recognition of a problem that became something
of a bee in my bonnet: a propensity in medics even stronger than that in
other half-educated (in statistics) groups to emphasize Michelin stars at
the expense of other aspects of results. Journals have far too many reports
of Mann-Whitney tests with accompanying p-values and lacking any descriptive
PRE measure. The interocular trauma test gets far too little attention.
Mike Procter <[log in to unmask]>
*****************************************
Dear Jenny
Very many years ago I attended a lecture by Richard Cormack. As I recall he had
analysed first year exam results of Statistics students at St Andrews. The only
important factors were age at entry and having studied statistics at school.
Those who had entered at age 17 directly after the Scottish Highers fared worse
than those who had done an extra year, and those who had studied statistics did
worse than those who had not!
Very old data now, but of anecdotal interest.
Robin Prescott
Professor R.J.Prescott
Director
Medical Statistics Unit
University of Edinburgh Medical School
Teviot Place
Edinburgh
EH8 9AG
tel: 0131 650 3229
fax: 0131 650 6909
e-mail [log in to unmask]
*****************************************
> Dear all,
> I am involved in a bid to update the way that statistics is taught to the
> medical undergraduates here in Sheffield. As part of the background to the
> bid we were wondering if anyone had any information on the following:
> (1) Are there any possible gender issues in the attitudes/performance of
> students
> (2) Is there any evidence to suggest that gender and attitudes/performance
> in stats are linked?
> (3) Are attitudes/performance linked to entry qualifications/background
> in maths for undergraduates?
> I'd be grateful for any thoughts you may have or pointers as to where to
> look for answers to the above questions. I will of course post all replies to
> allstat
|