[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Statistical ranking problem.
This is a purely statistical issue but I am expecting someone can make
suggestions. Our fieldworkers are rewarded with a bonus. So far we have
5 variables that go from the number of forms filled to the number of
errors reported. Then we take the individual weighted average of these
variables and anyone above the overall average is considered for a
bonus. This turns out to be unfair because so many people can be lying
just below the set cutoff line (=overall average) due to external
factors for instance.
I am thinking to consider the coefficient of variation as well but would
like to know if there is a better way to account for the distribution
Stata SE updated version 9.2
Postdoctoral Research Fellow
African Population and Health Research Center (APHRC),
Shelter Afrique Center, 2nd Flr, Longonot Road, Upper Hill,
P.O. Box 10787 00100, GPO,
Tel. +254 20 2720400/1/2
Fax. +254 20 2720380
"Promoting the well-being of Africans through policy-relevant research
on population and health"
* For searches and help try: