Dragon baby boom in NZ?
Back in January, Rachel Cunliffe looked at birth statistics for China as a whole and for Hong Kong, and saw a small ‘dragon baby’ boom for the Year of the Dragon in Hong Kong, but nothing for the whole PRC.
Today, the Herald is seeing a Year of the Dragon boom in Auckland
A support organisation for migrant parents in Auckland is experiencing a baby boom because of a surge in the number of dragon babies born to Chinese parents.
They go on to say
Membership at the Chinese Parents Support Service Trust for new Chinese migrant mothers has reached 200 – and one in four mothers had a dragon baby born this year.
It’s hardly surprising that new Chinese migrant mothers are likely to have a baby born this year — that’s what makes them new mothers. So what we really have is growth in the number of mothers using the service, and the fact that one in four of these mothers has a child under 9 months, a ‘dragon baby’.
Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »
This seems like a good place to bring up the baby selection problem. I wonder if there are any real-life misconceptions that occur in the media based on this:
Suppose every family in the country keeps having babies until they get a boy then they stop. What is the expected proportion of boys for the country and for each family.
The country is easy because the god of baby choice keeps handing out equal proportions of girls and boys. So the expected proportion is 50%.
For each family the expected proportion is 69% (see below if you need the explanation).
The apparent paradox is that every family in the country has an expected proportion of 69% but the overall country expected proportion is 50%.
(1) How do you explain this paradox in 25 words or less to a non-stats person?
(2) Are there any real life examples where the media confuses the 69 and the 50?
Appendix
The first baby is a boy with prob 0.5 and the proportion is 100%
The second baby is a boy with prob 0.25 and the proportion is 50%
The third baby is a boy with prob 0.125 and the proportion is 33%
…
Sum them all up to infinity to get expected proportion 69%
12 years ago
I haven’t seen this particular example show up in real life. There are related issues that do: for example, the average number of attempts at quitting smoking is larger if you average over people rather than over attempts.
If sex of babies were 50:50, I think you’ll find the within-family proportion is 2/3 rather than 69%. In fact about 52-53% of babies are male and there is a very slight tendency for correlation within family, so things are a little more complicated.
12 years ago