The standard mathematical treatment of the build-up and decay of airbo
rne radionuclides on a filter paper uses the solutions of the so-calle
d Bateman equations adapted to the sampling process. These equations c
an be interpreted as differential equations for the expectation of an
underlying stochastic process, which describes the random fluctuations
in the accumulation and decay of the sampled radioactive atoms. The p
robability distribution for the number of Po-218, Pb-214 and Bi-214 at
oms, accumulated after sampling time t, is the product of three Poisso
n distributions. It is shown that the distribution of the number of co
unts, registered by a detector with efficiency epsilon during a counti
ng period T after the end of sampling, is also the product of three Po
isson distributions. Its mean is dependent on epsilon, t, T, how rate,
and N-A(0), N-B(0) and N-C(0) the number of Po-218, Pb-214 and (214)G
i atoms per unit volume. This joint Poisson distribution was used to c
onstruct the likelihood given the observed number of counts. Using Bay
es' Theorem posterior densities were obtained for N-A(0), N-B(0) and N
-C(0). These densities characterise the remaining uncertainty about th
e unknown airborne concentrations of Po-218, Pb-214 and Bi-214 atoms.