I have been asked to pass on the following to the group in hopes that
someone may be able to help.
Sincerely
Lorna Hamilton
****************************************************************************
******************
We had 2 people walk up and down a set of stairs 50 times each, under a
number of conditions (2 sizes of stair, 20 different stair coverings) and
noted what happened. We also noted what happened with no covering on the
stair, and we did this early on in the runs, and also later on. There are 88
runs (2*2*22) each consisting of 100 bits of data, 50 going up and 50 going
down.
There is a learning process over time, the later the run occurred the less
likely anything unusual happened. The notes that are recorded lie in 4
categories, nothing unusual, caught a heel, loss of balance and a stumble.
What we want to do is say if there is a difference between the number of
times something unusual happened when there is a covering on the stair, and
when there isn't. It would also be good if we could say covering A caused
less incidents that covering B, despite the fact that people had fewer
incidents as the runs progressed.
We do not want to compare incidents going up with those coming down, and we
know the people had different walking habits, so are happy to look at their
data independently. We are also happy to look at the 2 stair sizes
independently, if that is useful. As an idea of the data one person started
off with 22 heel catches, 6 losses of balance, 1 slip and 21 times where
nothing unusual happened. By run number 86 this was down to 10 heel catches,
1 loss of balance, no slips and so 39 times where they went down the stairs
and nothing unusual happened (different coverings on the stairs).
Repeated measures or multivariate analysis? Is there anything useful we can
do with the fact that the control case (no covering on the stair) was done
twice, albeit not exactly at the beginning and end?
Privileged and confidential information and/or copyright material may be
contained in this e-mail. The information and material is intended for the
use of the intended addressee only. If you are not the intended addressee
you may not copy or deliver it to anyone else or use it in any unauthorised
manner. To do so is prohibited and may be unlawful. If you receive this
e-mail by mistake, please advise the sender immediately by return e-mail and
destroy all copies. Thank you.
|