A New Explanation For the Plight of Winter Babies 276
Ant passes along a Wall Street Journal report on research that turned up a new explanation for the lifelong challenges experienced by winter babies. "Children born in the winter months already have a few strikes against them. Study after study has shown that they test poorly, don't get as far in school, earn less, are less healthy, and don't live as long as children born at other times of year. Researchers have spent years documenting the effect and trying to understand it... A key assumption of much of that research is that the backgrounds of children born in the winter are the same as the backgrounds of children born at other times of the year. ... [Economist] Mr. Hungerman was doing research on sibling behavior when he noticed that children in the same families tend to be born at the same time of year. Meanwhile, Ms. Buckles was examining the economic factors that lead to multiple births, and coming across what looked like a relationship between mothers' education levels and when children were born." Here's a chart in which the effect — small but significant — jumps out unmistakeably.
And Yet another (Score:2, Insightful)
Re:Jumps out? (Score:1, Insightful)
yeah, thank you.. this article is ridiculous. economists "playing around with the data" should not be labeled as science.
Re:Jumps out? (Score:3, Insightful)
Noise wouldn't be periodic.
School entrance age cutoffs, maybe? (Score:5, Insightful)
Re:Jumps out? (Score:3, Insightful)
It's the being overly dramatic part that I object to. The difference may be significant, but it is small enough that in practice it means little for individuals. It's this kind of thing that has parents doing idiotic things like trying to conceive their kids in September so that they do better.
Re:Jumps out? (Score:5, Insightful)
Re:3rd bump (Score:3, Insightful)
Re:Jumps out? (Score:5, Insightful)
From TFA:
The two economists examined birth-certificate data from the Centers for Disease Control and Prevention for 52 million children born between 1989 and 2001, which represents virtually all of the births in the U.S. during those years. The same pattern kept turning up: The percentage of children born to unwed mothers, teenage mothers and mothers who hadn't completed high school kept peaking in January every year. Over the 13-year period, for example, 13.2% of January births were to teen mothers, compared with 12% in May -- a small but statistically significant difference, they say.
--end-quote
So problem is more than adequately explained by being born to a teen mother, and winter birth need not be related at all.
Winter birth is probably attributable to spring break, and the re-emergence of summer fashions (read: skimpy) and horny young guys after a hard winter.
The real story is births to teen mothers burdens not only the mother, but also the baby. Winter has nothing to do with it.
Re:Jumps out? (Score:3, Insightful)
Yes, that is the real story. However, there has long been a mystery surrounding why winter babies do not do as well, and the fact that they tend, slightly, to be the children of teen mothers is an interesting explanation (hence the research and the article in the newspaper...).
Re:Jumps out? (Score:5, Insightful)
Much more important is the lack of error bars, they are what you can use to decide if the difference is greater than noise. However since they seem to be confident enough to include a secondary maximum and minimum, we are led to assume that the error bars are rather small. Since TFA says the study looked at 52 million children over 12 years, it sounds fairly reasonable to suggest that error bars are relatively small w.r.t atleast the primary max an min.
TFA also says that the 52 million children in the sample were all of them, making the sample 100% of the population. That should result in some pretty small error bars, indeed!
The two economists examined birth-certificate data from the Centers for Disease Control and Prevention for 52 million children born between 1989 and 2001, which represents virtually all of the births in the U.S. during those years.
Re:Jumps out? (Score:4, Insightful)
Of course the difference jumps out. The chart was deliberately designed to make the change jump out by not using 0 as the origin of the Y axis.
This is a very common technique for making a difference look a lot larger than it actually is.
Or it could just be that using 0 as the axis would make a very unreadable graph that wasted a lot of space and didn't show the interesting portion very well.
Clearly reducing the range has the unfortunate side effect of falsely increasing the perceived significance of the results. However, given that the graphs also very clearly print the mins and maxs I'm strongly drawn to believe that the researchers where actually trying to communicate the data accurately as opposed to tricking unwary readers.
Oh, and the differences here are a 2.3% decrease in the percentage of married mothers and 1.2% increase in the number of teen mothers. Considering the topic they're analysing the effect is a lot larger than I would have anticipated.
Re:Here's what I think is wrong. (Score:2, Insightful)
I don't think you quite understand. Data showed that there is already a correlation between the season a baby was born in and measurable performance statistics. They have shown that some, most or all of this correlation is due to a key assumption being false;
A key assumption of much of that research is that the backgrounds of children born in the winter are the same as the backgrounds of children born at other times of the year.
Ah fuck it, I can't be bothered to explain it in full. It's too obvious.
Re:Jumps out? (Score:5, Insightful)
With an n of 52 million, those charts do include error bars - They fall about +/- a thousandth of a pixel around each plotted point. The pixels themselves just cover the error bars.
As for the Y-offset... Yes, you can use that to dishonestly highlight minor difference. When you have such small differences in your dependent variable, however, as long as you make the Y axis entirely clear to the reader, it merely serves to save the viewer a trip to find a magnifying glass.
Basically, if you had a series that showed some degree of noisy periodicity and you zoomed/cropped in on one section that appears to prove your point, it counts as dishonest. When you have virtually no error and a trend that looks like cookie-cutter copies from year to year - I'd love to see the p values for this, but I'd bet it would require scientific notation to realistically print (ie, on the order of p <= 10^-12).
Re:Jumps out? (Score:3, Insightful)
So what you're saying, is that this article only applies to babies born north of the mason-dixie line? Babies south of there, particularly west of the Mississippi, are exposed to mild winters that on many days in Chicago and Detroit might be called "fine summer days". The day after christmas here in Dallas, a lot of people take a stroll around white rock lake in the park, because it's 70 degrees and sunny. Dallas is only 1 arc minute north of Cairo, Egypt. Similar weather can be found in populus cities like New Orleans, Houston, Phoenix, Albuquerque, Las Vegas, Reno, Los Angeles, San Diego and more. Something like 1/3rd of the US lives in this region and isn't affected by winter seasonal issues experienced in the great lakes area and new England area.