It is so easy to jump to the wrong conclusions with probability. Even so-called experts (I mean, some who have given evidence as 'official' experts) have got it horribly wrong at trial in the past (cot death syndrome, for example). One thing which is often overlooked by casual observers (I only know enough to know that I know nothing) is that when you monitor large numbers of people looking for an unlikely occurrence, there actually can be a good chance of the anomaly occurring purely by chance to someone within that population. If I explain it like this: if you monitor the UK population for a lottery winner, and you find one, you would think, well, the chance of that individual winning the lottery is tiny (1 in 13,000,000). Yes, this is true for that one winner. But, when you multiply that possibility by all the people playing, the chances of finding a winner (or loser, as in the case of at least one nurse already exampled in this thread) is actually very good. And this is just one of the ways in which people (and even some of those who have set themselves up as experts) can be caught out.