We have developed a statistical computer program based on a Bayesian a
pproach to estimate bacterial density from tube dilution data. The pro
gram calculates an expectation, a mode (equivalent to the traditional
most probable number (MPN)) and a median as point estimates of the bac
terial density. The Bayesian analysis provides a probability density f
unction which reflects the knowledge accumulated about the bacterial d
ensity by observing the data. Its expectation is a summary value that
incorporates the shape and skewness of the distribution. On the other
hand, the MPN (mode) only uses the single most likely value and ignore
s other values that are consistent with the data. As a result the MPN
consistently underestimates the bacterial density and is likely to pro
duce large errors. Thus we recommend the use of the expectation as an
estimator for most problems. The theoretical basis of the Bayesian app
roach and ifs application to Salmonella data is discussed. Tables of r
esults for different combinations of tube dilutions are also presented
. (C) 1996 Academic Press Limited