A common task in microbiology involves determining the composition of a mix
ed population of individuals by drawing a sample from the population and us
ing some procedure to identify the individuals in the sample. There may be
a significant probability that the identification procedure misidentifies s
ome members of the sample (for example, because the available data are insu
fficient unambiguously to identify an individual) which makes finding the p
roportions in the underlying population non-trivial. A further complication
arises where individuals are present in the population that do not belong
to any of the subpopulations recognised by use of the identification proced
ure. A simple algorithm is presented to address these problems and construc
t a maximum likelihood estimate of the proportions, together with confidenc
e limits. The technique is illustrated using an example drawn from flow cyt
ometry in which phytoplankton cells are identified from flow cytometry data
by an RBF neural network, and the limitations of the approach are discusse
d. (C) 2000 Elsevier Science BN; All rights reserved.