[R] Help with Normal Range Estimation for repated measures

[Crabb, David]

I would be grateful if members of the list could point me in the
direction of any code (preferably in R) that will allow me to estimate
95th percentiles from a set of repeated measurements. For example, we
are interested in a clinical measurement where we have 3 measures for 14
subjects and 2 measurements on 24 subjects and single measurement on 36
subjects. We want to combine these to form a Normal range by using
something that takes account that some of the measures are repeats.
Something non-parametric would be ideal like a weighted empirical
distribution function. In other words we don't simply want to use 84
single values from the 84 subjects but use all the data (but we are
aware this needs to be corrected for).

Any help, however small, with this problem will be gratefully received.


-----------------------------------------------
Dr. David Crabb
School of Science,
The Nottingham Trent University,
Clifton Campus, Nottingham. NG11 8NS
Tel: 0115 848 3275   Fax: 0115 848 6690