Healy M J
Department of Epidemiology and Population Sciences, London School of Hygiene and Tropical Medicine, U.K.
Stat Med. 1989 Aug;8(8):893-906. doi: 10.1002/sim.4780080802.
The assessment of errors of measurement and their effects needs to take into account the structure of the data in which the errors occur. This is illustrated and the appropriate analysis of variance specified for a variety of contexts. The notion of an acceptable level of measurement error is discussed in terms of decision theory and illustrated by a simplified example.