Philip Bouchier wrote:
>I have a set of measurements (e.g. number of errors, faults, etc) over a
>period of time (e.g. 9 Months) and measurements are taken weekly. These
>measurements are graphed on a spreadsheet. I need to select a small number
>of measurements and graphs then display the measurements and the graphs to
>my audience.
Nine months of weekly measurements comprise only 39 data;
surely that's not too great a number to display at once.
>My question is, Is there a statistical way of selecting the set of
>measurement that show movement up or down other than just
>eye balling the graphs??
If by "movement up or down" you mean "trend", then there are
a great many methods of detecting and displaying trend, none
of which require a selection of any subset of only 39 data.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
