Measurability of $p$

It is now time to put together all the items discussed so far and to move to the question of how well we can measure the proportion $p$ of infectees in a population of $N$ individuals, out of which $n_s$ have been sampled at random and tested, resulting in a total of $n_P$ positives. Again we proceed by steps. In this section we tackle the question of how the expected number of positives and its uncertainty depend on the proportion $p$ of infectees in the population. The real inferential problem, consisting in stating which values of $p$ are more or less believable, will be analyzed in Secs.  and .