Friday, 17 January 2014

More on birthday coincidences

My daughter's birthday was last week (12 January), so I had a personal interest in today's  Telegraph article about a family with 4 children all having the same birthday - 12 January

Family with 4 children - all born on 12 January
Anybody who has read our book or seen our Probability Puzzles page will be familiar with the problem of 'coincidences' being routinely exaggerated (by which I mean probabilities of apparently very unlikely events are not as low as people assume). There is the classic birthdays problem that fits into this category (in a class of 23 children the probability that at least two will share the same birthday is actually better than 50%); but of more concern is that national newspapers routinely print ludicrously exaggerated figures for 'incredible events'*. 

So when I saw the story in today's Telegraph I did what I always do in such cases - work out how wrong the stated odds are. Fortunately, in this case the Telegraph gets it spot on: for a family with 4 children, two of whom are twins, the probability that all 4 have the same birthday is approximately 1 in 133,225. Why? because it is simply the probability that the twins (who we can assume must be born on the same day) have the same birthday as the first child times the probability that the youngest child has the same birthday as the first child. That is 1/365 times 1/365 which is 1/133225. It is the same, of course, as the chance of a family of three children (none of whom are twins or triplets) each having the same birthday. The Telegraph also did not make the common mistake of stating/suggesting that the 1 in 133,225 figure was the probability of this happening in the whole of the UK. In fact, since there are about 800,000 families in the UK with 4 children and since about one in every 100 births are twins, we can assume there are about 8,000 families in the UK with 4 children including a pair of twins. The chances of at least one such family having all children with the same birthday are about 1 in 17.

*Our book gives many examples and also explains why the newspapers routinely make the same types of errors in their calculations. For example (Chapter 4) the Sun published a story in which a mother had just given birth to her 8th child -  all of whom were boys; it claimed the chance of this happening were 'less then 1 in a billion'.  In fact, in any family of 8 children there is a 1 in 256 probability that all 8 will be boys. So, assuming that approximately 1000 women in the UK every year give birth to their 8th child it follows that there is about a 98% chance that in any given year in the UK a mother would give birth to an 8th child all of whom were boys.

1 comment: