Suppose I told you about something that’s totally preventable and is associated with an average excess death rate of 6.7%. It’s worse for youths: the excess death rate for those aged 20-29, because of this totally preventable problem, is 25.4%.
And there would be one simple fix to end those excess deaths entirely.
Ladies and Gentlemen, it’s time to ban birthdays. The simple policy fix: stop recording date of birth on birth certificates, and ban kids from having birthday parties so they never grow up knowing their birthday.
Here’s the original study by Pablo Peña.
Now hear me out. We might think it a bit silly to ban birthdays, but the excess death finding seems pretty robust. And we know that anything that saves even one life is worthwhile. I’m sure that the fine folks in the New Zealand Government will use the price elasticity of demand for kid birthday parties to argue that the forgone benefits would add up to not much more than maybe $400 a day over the whole country. And nobody will bother fisking the number or even giving it a basic plausibility check before the National Party goes and implements the ban to avoid being outflanked on the “showing you care” margin by the newly competent Labour Party.
Now for a more worrying econometric point: a pile of regression discontinuity design regressions use birthday cutoffs where policy legalises something at an age as the source of the discontinuity, attributing all changes then to the policy and nothing to birthday effects. So RDD methods find increased mortality when kids hit the legal alcohol purchase age. But that’s confounded with this birthday effect, as Stillman and Boes demonstrated. Be careful using RDDs around birthdays. Most studies will dummy out the birthday, but it’s worth checking whether birthday effects extend a week either side: a fair few will save the birthday party for the adjacent weekend.