[jerf]

This is a good example of how in the real world, everything is correlated with everything. Understanding this principle, I would expect uneven birth times and birth dates. I may not be able to guess what will cause it to be uneven (though in this particular case I would have gotten pretty close), or by how much it will deviate from uniformly random (I would have gotten this wrong to the low side), but it's sure to be something.

To put it another way intuitively, in a complicated world with so many things impacting so many other things, to have a totally uniformly random birth times or dates would essentially require some active force to smooth the times and dates out, because it is beyond implausible that absolutely nothing would have an impact. From diurnal hormone cycles, traffic cycles, preferences about surgery times, and probably another dozen things you could think of that could impact the times, it is implausible to expect that they would all be completely wrong or that they would all precisely cancel.

Uniform randomness is a very convenient mathematical fiction for making Statistics 101 problems easy enough for students to do. This is a necessary thing and it's hard to imagine how to avoid it. But in reality almost nothing is ever truly uniformly random. There's always something out there that's going to correlate it with something. It is a sad side effect of this need to simplify problems enough to be tractable by students that we end up teaching that uniform randomness is somehow the "default" distribution and the others are exceptions or something.

[hinkley]

If the medical staff influence the delivery time, they in turn are influenced by everything else, like vendors and traffic accidents. While obstetricians are not fungible with trauma surgeons, and nurses are only slightly more fungible (because they tend to work in a particular ward), they all have to deal with the pharmacy and anesthesiology, etc. I don’t know if they share surgical theaters, but you can’t reuse a surgery until it is clean and functioning, I think those crews would definitely be floating.

I don’t know much of anything about the other people in the OR, if the assistants stick to a particular group of surgeons or float. The people handling tools and gauze pads (which sounds like a dumb job but someone has to be sure that 12 pads and a clamp went into your abdomen and exactly that number came back out at the end), clamps, retraction, suction, IV and gas monitoring, etc etc. Those are somewhat specialized to the task but I don’t know if they are specialized to a surgical unit or if the same people who help with a appendectomy also assist with a finger reattachment or spinal surgery. If they do a surgery could get bumped for scheduling conflicts, or shift changes.

[vlovich123]

There’s a difference between lots of different factors having an impact and one giant one forcing everything to be at the same time.

With the former you’d expect a normal distribution (not uniform) due to the central limit theorem - the sum of a large number of variables with some error distribution will result in a sum with a normal distribution. This isn’t math 101 but an incontrovertible fundamental finding of Calculus (and 100% applies to the real world).

The article explains the latter phenomenon though. Births are being scheduled due to C-sections. This isn’t a confluence of some interesting factors into a surprising result but the presence of one factor that overrides all others and one that has grown in popularity due to the efficacy of modern techniques.

[jerf]

"With the former you’d expect a normal distribution (not uniform) due to the central limit theorem"

You'd expect it, but in the real world you'd be extremely frequently wrong. Correlations in the real world very frequently end up defeating the central limit theorem in practice.

The central limit theorem, being a mathematical thing, is correct; it can't be "wrong". However, while adding together a lot of distributions will absolutely trend towards a normal distribution, it does not make very many promises about how "quickly" that will happen. In practice the real world is filled with the sort of pathologies that result in it being "very slow". Scare quoting some words here because they are rather vague in math terms and I feel bad about that, but putting real mathematical meat behind them would be beyond the scope of an HN post. Many, many, many things are not normal that "should" be, and you can make some grave mistakes in the real world if you overestimate the normality of real world distribution. I recommend Taleb's works here, if you need more details.

[quickthrower2]

Mu guess was going to be the body is less likely to want to go into labour at night so “holds off” until the morning to some extent but not always!

[jerf]

Yup, that's what I meant by "diurnal hormones". Personally I'd still guess there's an effect there, it's just so swamped by the c-section surgery nothing else is visible.