While this may seem funny, and it is, there is a real problem deciding what is signal and what is noise and making assumptions as to what is real data and what is garbage.
Assuming the extraneous and non-conforming data is noise and focusing on the intended signal may neglect that fact there is another and perhaps more important signal.
I am concerned about treatment of outliers and unexpected intrusions into the expected data stream and smoothing for neatness.
Nowhere is this more apparent than in bee studies which by their nature are necessary messy and difficult. Practicality results in missed data points, and student observers have incentive to report what is expected and assume outliers are 'mistakes'.
***********************************************
The BEE-L mailing list is powered by L-Soft's renowned
LISTSERV(R) list management software. For more information, go to:
http://www.lsoft.com/LISTSERV-powered.html