Being an important parameter in order to plan
a test campaign, it is worth getting its closed, although approximated
expression, obtained extending the
condition ()
to
When we reduce the uncertainty about , keeping constant its expected value, the systematic contribution to the uncertainty is reduced and then, as we have already learned from Figs. , and , it becomes meaningful to analyze larger samples. We can then predict the fraction of individuals tagged as positive with improved accuracy, i.e. E decreases. This intuitive reasoning is confirmed by the plots of Fig , moving from the solid curves to the dashed ones. Instead, improving the specificity to 0.885 to 0.978, i.e. reducing E from 0.115 to 0.022, keeping the same uncertainty of 0.007, leads to surprising results at low values of , at least at a first sight (dashed curves dotted curves). In fact, one would expect that from this further improvement in the quality of the test (which definitively makes a difference when testing a single individual, as discussed in Sec. ) should follow a general improvement in the prediction of the fraction of positives.
The reason of this counter-intuitive outcome is due to the combination of two effects. The first is the dependence on E and E of the statistical contributions to the uncertainty, as we can see from Eqs. () and (). The second is that, decreasing E, the expected value of decreases too (less `false positives') and therefore the relative uncertainty on , i.e. E, increases. While the second effect is rather obvious and there is little to comment, we show the first one graphically, for at which the effects becomes sizable, in the three plots of Fig. :
the upper plot for our reference values of and , the middle one improving to 0.007, and the bottom one also reducing the expected value of to 0.022. But differently from Figs. , and , these plots show instead of E, so that we can focus only on the contributions to the uncertainty, not `distracted' by the variation of the expected value of . Moving from the top plot to the middle one, only the contribution due to is reduced, all the others remaining exactly the same. Then, when we increase the specificity, i.e. we reduce E from 0.115 to 0.022, keeping unaltered its uncertainty, its contribution to is unaffected, while the statistical contributions do change. In particular is strongly reduced, while increases a little bit. The combined effect is a decrease of the overall statistical contribution, thus lowering .Summing up, the combination of the two plots of Fig. gives at a glance, for an assumed proportion of infectees , an idea of the `optimal' relative uncertainty we can get on (bottom plot) and the sample size needed to achieve it (upper plot). We remind that the lowest relative uncertainty, equal to of the value shown in the plot, is reached when the sample size is about one order of magnitude larger than , i.e. when the random contribution to the uncertainty is absolutely negligible and any further increase of not justifiable. But, anyway - think about it - being , is it worth increasing so much ( times) the sample size in order to reduce by only 30%?