A New Explanation For the Plight of Winter Babies

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.

Comments

Jumps out?

[ucblockhead]

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.

Re:Jumps out?

[wjh31]

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.

Re:Jumps out?

[Anonymous Coward]

yeah, thank you.. this article is ridiculous. economists "playing around with the data" should not be labeled as science.

Re:Jumps out?

[ucblockhead]

Yeah, I have little doubt that there is a real effect here, but I hate when things like this are sensationalized. There may well be an effect, but it is a small one.

Re:Jumps out?

[Anonymous Coward]

Noise wouldn't be periodic.

Re:Jumps out?

[Bwian_of_Nazareth]

No... the effect can be statistically significant without being large. Of course the charts look more dramatic if you "zoom in", but the fact that the difference is only 0,5 % does not make it insignificant. And with the sample size of 52 million children, the results are probably very significant (too bad the article seems to omit the p-value for the tests).

Re:Jumps out?

[wjh31]

no, but if the amplitude of the oscillation you are trying to measure is comparable to the amplitude of noise, you would be foolish to try and draw many conclusions about that oscillation, certainly without any error bars. Also, there are plenty of sources of periodic noise, mains noise at 50/60hz is the prime example, but being periodic, its easy to account for.

Re:Jumps out?

[Bwian_of_Nazareth]

Why not? What is wrong with the numbers? A statistically significant result (and I guess this one from a 52-million sample is significant) can be of any size... even if the difference was only 0,0001 %, it could be a valid result. And of course they would choose such a scale for the charts that makes the trends visible.

Re:Jumps out?

[antifoidulus]

Maybe the person that made it had a January birthday?(or June for our friends south of the equator)

Re:Jumps out?

[ucblockhead]

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?

[AliasMarlowe]

Did they use only data for Northern hemisphere women (north of the tropics)?, Or is it a mix with tropical and Southern hemisphere as well?

Re:Jumps out?

[Anonymous Coward]

I'm not sure why you were modded flamebait. I think your question is valid, considering the southern hemisphere has the opposite seasonal cycle that the northern hemisphere has.

Re:Jumps out?

[ucblockhead]

That's a good question, and I have no clue why some boneheaded moderator thought it was flamebait. Please mod up.

Re:Jumps out?

[ceoyoyo]

Never trust a graph without error bars. But the pattern does look remarkably robust from year to year, which suggests that the noise is actually too small to be seen.

Re:Jumps out?

[selven]

It's well known that children born in Jan/Feb/Mar are much more likely to get ahead because age cutoffs tend to be January 1, so kids born on Jan 1 compete with kids born on Dec 29 in the same year despite having 11 months more experience. Because of this, more attention is given to these "stars", and they perform higher. You should look at the birth months of some professional football teams.

Re:Jumps out?

[Anonymous Coward]

I'd imagine that with 50+ million datapoints that the error bars would be pretty damn small.

Re:Jumps out?

[icebike]

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?

[TimSSG]

I would guess that it is for the USA and the results is as one might expect based on the traditional school year in the USA. Me and my siblings were born during Oct(10) through Jan(01) because we were from a farming family. The down time for farmers is after harvest and before planting. Late Oct(10) to March(03). A School Teacher Family would try to target Late May(05) to early Sept(9) as the time to have Kids. Tim S.

Re:Jumps out?

[maxume]

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?

[ppanon]

Same thing with hockey, where size is also a big advantage.

Re:Jumps out?

[Rob the Bold]

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?

[Anonymous Coward]

"playing around with data" and actual rigorous statistical analysis are not bad or wrong or useless. but they, alone, are not science. statistical correlations are statements of observations about sets of data which, definitely in the case of census type data and quite often in general, are obtained far from the rigor of scientific experimentation. there are no scientific conclusions in statistical analysis of data, simply observations. the most that can be concluded rationally are statements about the measured attributes of entities in the specific space and time period that generated the data set. it is very unscientific to draw conclusions from even massive data that yield strong correlates without further experimentation. science employs observations and experimentation and most importantly a rational approach to the nature of conclusions themselves. if a theory can be disproved it is not true. therefore all theories that are scientifically acceptable are based on conclusive reproducible experimental evidence and the absence of contrary experimental evidence. since a theory may be disproved someday based on new evidence, it can sadly never be assumed to be completely true despite our tendency to wish it so. conclusions in the field of statistics can not be scientific if they go beyond the mere statement of observed correlations.

Re:Jumps out?

[T Murphy]

So they need to look at teen births only to look for patterns. It would also be a good idea to look at only winter births just to confirm whether the teen births are the ones sticking out like this (probably true but they have the data so no reason to assume anything).

Re:Jumps out?

[Anonymous Coward]

This depends on locale.

I was born in Feb, and I grew up in Texas where the cutoff for school admission was based on the school year rather than the calendar year. Result: I was always one of the youngest in my classes.

Re:Jumps out?

[quantaman]

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:Jumps out?

[Runaway1956]

"horny young guys after a hard winter."

Just curious - are you old enough to remember a hard winter? I'm 53, and I only remember a couple of them.

As for the "horny young guys" - I never noticed that to be a seasonal phenomenon. Receptive, fertile females might be seasonal, but horny guys certainly are not.

Re:Jumps out?

[Lesrahpem]

The difference really jumps out with me. No allergies, walked at 9 months, IQ 168. Yeah, Winter really screwed me. Morons.

Re:Jumps out?

[net28573]

I concur!

Re:Jumps out?

[pla]

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.

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?

[Anonymous Coward]

The fact that you can see consistent effects from year to year is enough to tell you that they've got the noise level down. In fact, you can see a little secondary peak each year, too. In the first graph, for instance, it looks like they've got the month-to-month noise level down to 0.1-0.2%, while their signal has an amplitude of about 2.5%.

Re:Jumps out?

[Odinlake]

it sounds fairly reasonable to suggest that error bars are relatively small

Also the smoothness of the curves suggested by the green and blue dots respectively seem to suggest the error bars are relatively small.

Re:Jumps out?

[throbber]

Further to this, what about babies born in the dry season .... or the wet season.

The tropics don't have summer or winter.

Re:Jumps out?

[davidphogan74]

The moderator was probably born in January, and thus unable to get the question.

Re:Jumps out?

[flewp]

The article does say:

"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."

So it seems they used data from babies born in the US. On the other hand, the article also says: "Other researchers have suggested other reasons for season-of-birth differences. Maybe vitamin D was playing a role, for example, because children born in the winter were getting less sunshine in early life" - which if this were true, would apply to babies born in winter for both hemispheres.

Re:Jumps out?

[Anonymous Coward]

You are a sad and pathetic little wretch who apparently hasn't accomplished anything of note since learning to walk and attempts to compensate by for this lacking by posting his IQ on Slashdot.

Yeah, I'd say winter birth fsck'd you up pretty good.

Re:Jumps out?

[mini me]

How do you define a hard winter?

On the 43rd parallel, which isn't even very far north as far as winter is concerned:

- In the winter of 2000 it started snowing in mid-November and it did not stop until February.
- In the winter of 2004, daytimes highs hovered at no more than 30 below zero for several weeks.
- In the winter of 2007, the snowbanks could easily touch the powerlines.
- Fifteen feet of snow was the official recorded accumulation amount for the winter of 2008.

I mean, as an avid fan of winter, those just sound like ideal conditions to me. I can see how some would consider them to be hard winters though. My father says that modern winters are not unlike those of the past, we just have better snow removal equipment.

Re:Jumps out?

[kingturkey]

I haven't read into the Winter Babies phenomenon, however a number of the possible causes of differences listed in the article are not strictly seasonal changes but societal differences related to the season, for example the school attendance laws, which are likely to vary greatly in countries other than the US, especially ones in the Southern Hemisphere.

Re:Jumps out?

[Anonymous Coward]

What a silly question. Everybody knows that it's the /men/ who give birth in the Southern hemisphere.

Re:Jumps out?

[Hadlock]

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.

Re:Jumps out?

[demonlapin]

They used CDC data - that's the USA's Centers for Disease Control and Prevention. They're all Americans.

Re:Jumps out?

[demonlapin]

Different in different places. School year cutoff was Sept 1 where I grew up.

Re:Jumps out?

[Hadlock]

On the flip side, the southern US experiences "snow" perhaps 22-30 hours a year. Does this study account for "hard winters" here in Dallas where we saw 48 hours of snow, before it got back up into the mid 60's?

Re:Jumps out?

[nametaken]

I found it more interesting that teenage pregnancy appears to be steadily declining and years of education steadily increasing. ...unless I read that wrong?

Re:Jumps out?

[nametaken]

Outliers by Malcolm Gladwell deals with this in some detail.

http://www.amazon.com/s/ref=nb_ss?url=search-alias%3Daps&field-keywords=outliers&x=0&y=0

Re:Jumps out?

[Hognoxious]

My IQ is somewhat lower than yours. I'll take some comfort from the fact that I know what anecdotal evidence is.

Re:Jumps out?

[Lesrahpem]

and you have what evidence that I've accomplished nothing or amounted to nothing? I didn't post this to brag exactly, only as anecdotal evidence to the contrary of what the article is saying. My intelligence is more of a curse than anything, and I'm not proud of it.

Re:Jumps out?

[Runaway1956]

"Hard winter" in local areas is a totally different thing from a hard winter that affects a continent. Since 1999, there have only been a few isolated instances of roads being impassible in more than local areas. I can't remember the date - I think it was 2001, I left the Yakima valley in Washington, headed to Florida. A huge storm front came in over Washington, and another came in over California, and met each other over Colorado. Everything was a mess - but roads were maintained. I was on ice all the way from Washington until I was almost to Atlanta, but the roads were open, and usable.

You can look at the trucking industry for an indicator of how mild recent winters have been. The majority of American truck drivers will readily tell you that they WILL NOT DRIVE on ice. They are accustomed to mild winters, and they are accustomed to states having the resources to keep up with snowfall and ice accumulation. The VAST majority of truck drivers will readily tell you that if driving conditions require chains, they will not drive. Phhht. Buncha sissies, if you ask me. I remember my grandfather carrying his chains year round, because you could never be sure what you would find at higher elevations, even as far south as northern California.

Today, the fact that we rely on "Just in Time" trucking proves that we haven't experienced a harsh winter recently. When the Ozarks have a hard freeze for Thanksgiving, and don't thaw until March, then we will remember what a hard winter really is. And, a lot of that "Just in Time" nonsense will be discarded.

Re:Jumps out?

[Anonymous Coward]

parent assumes the cut off is Jan 1. In most US school districts the cut off is more likely to be in September or October and thus the FALL births are the oldest, followed by winter births.

Re:Jumps out?

[rohan972]

Perhaps it was a "hard" winter because of the seasonal unavailability of receptive fertile women.

Re:Jumps out?

[jabuzz]

However it is heavily USA biased, so does not necessarily tell us anything. For example if you looked at Premiership footballers born in England you would find that they are heavily biases to people born between the months of September and December.

The explanation being that school years start in September and the oldest tend to be the biggest and strongest, so are better at physical activity that those that could be almost a year younger, and while they eventually catch up it is too late.

Talk to any early years teacher an they will tell you that the oldest in the year tend to do better than those that again could be almost a year younger. Do they ever catch up, can they ever catch up?

When does thee USA school year intake start?

Re:Jumps out?

[Prof.Phreak]

How To Lie With Statistics (by Darrell Huff and Irving Geis) indeed.

Re:Jumps out?

[Prof.Phreak]

a high school senior has fun during the spring break in april, and 9 months later you have a baby from a couple who probably didn't start college (or started and dropped out---and will probably never go back).

Re:Jumps out?

[Anonymous Coward]

It's well known that children born in Jan/Feb/Mar are much more likely to get ahead because age cutoffs tend to be January 1, so kids born on Jan 1 compete with kids born on Dec 29 in the same year despite having 11 months more experience. Because of this, more attention is given to these "stars", and they perform higher. You should look at the birth months of some professional football teams.

Did you come up with this by yourself or did you read "Outliers"?

Re:Jumps out?

[boaworm]

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."

So, if you want to knock up a teen and/or unwed girl/woman, April is be the month to go?

What do you do in the US in April?

Re:Jumps out?

[Idiomatick]

I believe that graphs online should get their own file type. Having a graph as a static image ALWAYS sucks in one way or another. We are forced to suck it up irl. But online there is no reason we can't stick the raw data in a file and have an interactive graph generated for us. Here's hoping for html 6.0 upgrades?

Re:Jumps out?

[j-beda]

"When does thee USA school year intake start?"

I think it depends on the district, or at least the state. Some go by a calendar year, starting in January, some by a school year, starting in September. By the calendar year cutoff, January births should be oldest, thus most advantaged. By a school-year cutoff, January births are about the middle of the age-range for the class. Neither of these cutoffs would seem to disadvantage greatly those with January birthdays.

Re:Jumps out?

[cenc]

Yea, this is a serious question. What about countries in the tropics? Hell, what about any other country in the World? Do they have this problem in countries with good social security?

In South America, most people have the exact opposite reproduction schedule.

All the factors mentioned in those articles are U.S. culturally dependent issues. In fact, rather grossly bias towards Americans. It is not even the winter effect, it is the "American's born in the winter effect". At least that is the causes they seem to be looking at, and nothing else. It would seem to be the first thing to check in such a problem. Does anyone else have that problem?

Re:Jumps out?

[ajs]

Yeah, I have little doubt that there is a real effect here, but I hate when things like this are sensationalized. There may well be an effect, but it is a small one.

I think you're missing the point. We've known for a long time that there is a small effect, here. The discovery of the small disadvantage that winter babies have is not news. What's news is that we've found a correlating cause, not the existence of the phenomenon.

Re:Jumps out?

[ajs]

Much more important is the lack of error bars

I'm getting kind of sick of this kind of response on Slashdot. If you RTFA, you'll see that this is a WSJ article that's distilling a scientific paper for the general public. You're essentially constructing a strawman in that you're claiming a lack of scientific rigor in the non-scientific article about a scientific paper.

Essentially, this boils down you not seeking out the source material (granted, WSJ isn't doing you any favors in that department). In case Google failed you, this appears to be the paper in question:

http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1320799

It'll cost you $5 from that site, which was the only one Google Scholar came up with, but feel free to find another source.

Re:Jumps out?

[ikedasquid]

One other thing jumps out, according to the graphs teen pregnancy is slightly down, and education levels of mothers is slightly up! Both good things, even if it is an incredibly small margin...

Re:Jumps out?

[Anonymous Coward]

The the sample is the whole population, the sample mean IS the population mean. Since this is census data, they are not estimating anything. Those are the actual numbers. No error bars necessary.

Re:Jumps out?

[metlin]

Noise wouldn't be periodic.

Says who? Anyone who's done any kind of signal processing can tell you that there are any number of noise functions that can be periodic in nature.

Re:Jumps out?

[Rob the Bold]

However it is heavily USA biased

Heavily USA biased? The study was about the USA and only the USA. It's not biased, it's exclusive.

Talk to any early years teacher an they will tell you that the oldest in the year tend to do better than those that again could be almost a year younger. Do they ever catch up, can they ever catch up?

When does thee USA school year intake start?

That's where you're off base (or some cricket analogy) -- remember that this is a US study (or US biased if you will). US school years vary by state and community, but they start around mid-August to Early September. Children start school at the grade level determined by their age as of that point. So if a child is 5 on August 20 where school starts on August 21, then he goes to Kindergarten (and I've grossly oversimplified since every jurisdiction has its own rules). These January babies are neither the youngest or oldest in their class, but rather in the middle. They should be neither the largest and oldest or youngest and smallest.

Even in the US, we've heard the studies about birth month and success at football (sic)*. But this study isn't just about athletic achievement but all-around success in school, health and wealth.

*Sorry about that, but I've been a jackass ever since I read "US Department of Labor (sic)" in the Economist years ago. It's a freakin' proper noun! You don't adjust the spelling by region. I probably should get over that, but probably won't.

Re:Jumps out?

[niw]

Spring Break?

Re:Jumps out?

[Anonymous Coward]

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.

Uh...no. He said "northern hemisphere" and "southern hemisphere". If you take a moment to Google those two terms you'll probably get the point. Don't worry, we'll wait...

Still lost? OK, what he was getting at is that in the Southern Hemisphere the seasons are reversed from the Northern Hemisphere. So up north, January is in the winter, but south of the equator January is in the summer. So the question was, is there something about those months in particular, or something about that season in particular. Does it hold true that in the southern hemisphere that "Winter Babies" face the same issues as in the northern hemisphere, or is it "Summer Babies" for them that have issues?

Re:Jumps out?

[stubob]

April Fool's Day?

Re:Jumps out?

[SleazyRidr]

How is it a curse? Granted my IQ doesn't quite reach your level, but I'm smart enough to get over my problems.

Re:Jumps out?

[Coren22]

How would AC have an effect on babies?

this isn't a new explanation

[Trepidity]

People have been debating this explanation for decades, and studies are all over the map. It'd be more accurate to say that there is yet another new study on the subject of the relationship between season-of-birth correlates and socioeconomic factors, this one claiming that the relationship is in fact significant. There's a bunch more studies if you'd like.

Re:this isn't a new explanation

[Anonymous Coward]

I think all journal articles involving statistical analysis should be required to show, in big bold print, the ratio of the size of the data set used in the study versus the size of the data set they had before they decided what period and variables to add.

Also, all statistical analysis software should support a physical odometer that counts the number of regression equations they've run on the data. This number should also be in the article in big bold print. Tampering with the odometer should be met with the same punishment as is used for used car salesmen who alter car odometers.

That means...

[Anonymous Coward]

There's a tendency for promiscuous, uneducated teenagers to have unprotected sex during springtime and early summer. It's always easy to say this, but, duh...

Re:That means...

[Wanado]

This is exactly how I see it. It isn't the month of birth that is causing the "life with less means". It is the teenage mother-to-be with less means that is getting laid at prom. Do the math. Class dismissed.

Re:That means...

[digitig]

So the poor f2k in spring and the rich f2k in the autumn? Damn, what social group do I have to be in to get it all year round?

Re:That means...

[JLF65]

It's not the prom (which is in June), it's Spring Break (which is in March). High schools need to be banned from taking a Spring Break. It's the CLEAR solution. ;)

Re:That means...

[selven]

Judging by the presence of your comment on this forum, you're about diametrically opposite right now.

Re:That means...

[digitig]

Really? Well, damn again. I'm not joining Digg, even if it would mean getting laid more often.

Re:That means...

[Anonymous Coward]

I'm not joining Digg, even if it would mean getting laid more often.

It wouldn't.

Re:That means...

[Anonymous Coward]

Troll. Promiscuity has nothing to do with it. Frequency of sex does.

Re:That means...

[Anubis IV]

Bingo. I was about to say the same thing, but if we look at Spring Break and prom times, it seems pretty apparent that high school or early college kids could account for this little fact all by themselves. I'd be more curious about the numbers if they broke it down by age group.

Re:That means...

[Anonymous Coward]

In the part of the US where I live, prom season is in May. Perhaps the public school schedule is not uniform throughout the country.

Re:That means...

[Rakshasa Taisab]

'duh...'?

You're on slashdot, we've never even gotten close to those 'promiscuous, uneducated teenagers', except in our fantasies.

Re:That means...

[demonlapin]

My prom was late April, and I graduated before the end of May. School schedules vary.

Don't forget: it's not the getting laid that distinguishes dumb and smart women, it's the getting pregnant and having a baby.

Measured data includes uncertainty

[craklyn]

Any measurement made requires two peices of information: the measurement and the uncertainty associated with that measurement. To present data as though its known with 100% certainty is misleading and incorrect. It seems pendantic to worry about uncertainty, but when you're dealing with small effects on the order of less than one percent, if the error bars are +/-2.5%, then it's absolutely incorrect to refer to the result as "jumping out".

Re:Measured data includes uncertainty

[Rakshasa Taisab]

You mean, error bars to measure how bad the counters were at counting?...

1... 2... 3... 5... 6... oh... wait... shit

Re:Measured data includes uncertainty

[craklyn]

When a measurement is made, everything is expected to be done correctly operationally. It's not a measurement if someone misreads a yard stick, etc. What I mean is this: if you're sampling a small portion of a population, you can't assume that you selected a perfectly uniform, representative sample.

A good example of this is trying to find out the probability of a "perfect coin" to land heads. By perfect, we mean it is exactly 50% heads and 50% tails when thrown. If you throw it 20 times, you may very well not get 10 heads/10 tails. You counted everything perfectly, but since you had a limited sample, there was uncertainty in your measurement. Increasing the measurements decreases the size of the error bars.

Re:Measured data includes uncertainty

[Anonymous Coward]

Your previous post talked about "measurement uncertainty" and now you're switching to "sampling error". Make up your mind, those are two very different things.

If I have 4 nails in a box and I want to know the average size of a nail from that box, I measure two of them to within 1 mm and I get 38 mm and 62 mm. I get an estimate of 50 mm. Each measurement uncertainty is 1 mm but the sampling uncertainty is 12 mm (standard deviation).

Now if I measure all 4 nails, the sampling uncertainty becomes 0 mm, only the measurement uncertainty remains.

In the winter babies case, they didn't take a sample, they measured the whole set, so sampling uncertainty is 0. You said you expected each measurement was done correctly, so measurement uncertainty is 0. What are you complaining about?

Makes sense

[Anonymous Coward]

The difference is extremely small, but one would expect that people getting pregnant because of a one-night-stand or a whim is both higher among the uneducated, unmarried, and also higher during spring when many people's hormones tend to go into higher gear. People who are more in control of their emotions and actions tend to be more educated and are (at least somewhat) less likely to sleep with half the town during spring break.

Of course, the correlations I mention above don't necessarily have to be very large, but probably large enough to affect the statistics by a tenth of a percent.

Re:Makes sense

[Tablizer]

People who are more in control of their emotions and actions tend to be more educated and are (at least somewhat) less likely to sleep with half the town during spring break.

It's not quite that simple. People often have a lot of self-control in one area but not another.
       

And Yet another

[TheBilgeRat]

doctoral thesis claims their "significant" find is "significant". sigh.

Re:And Yet another

[qw0ntum]

Pray tell, what else do you expect them to say? "Our research doesn't really show any results to speak of... but here's a paper anyway!". Also, statistical significance is, well, significant. So they are accurate in saying it is a significant finding.

Re:And Yet another

[Anonymous Coward]

Oh, every once in a while it would be nice. "I spent four years researching a totally useless factoid and I found nothing. I am an idiot." Whether they are accurate or not is piffle. A dumb question gets a dumb answer. So, the solution to this statistical conundrum? No babies in winter? Great. The next study title would be "Babies have higher birth complications in summer (due to overcrowding and swamping of the hospitals)."

The solution is give up your grant and go analyse purchasing trends or flip burgers.

Re:And Yet another

[Huntr]

Printing a pub on the basis of spurious statistical relationships is poor science.

Born in December

[Harry_Mohan]

I was born in December and pursuing double masters with GPA of 3.4 is it really bad?

Re:Born in December

[retech]

You could do better... if you were born in June.

Re:Born in December

[celibate for life]

I don't think it means you will present all the aforementioned characteristics. So you could still die young!

Re:Born in December

[Anonymous Coward]

Yep. I was born in July, already have 3 college degrees (GPA 3.8 or better), and make about $100K a year. That's way better than "pursuing double masters." It must suck to be a winter baby.

Re:Born in December

[CubicleView]

Your grammar?

Re:Born in December

[Anonymous Coward]

I was born in October (29th to be exact) and quit school to work so I could pay off bills before continuing with my education. I started back at age 28 and am still there at age 29... I'm closer to the summer months, yet you've beat what I've done.

I've also noticed a pattern!

May seems like a "better month" but let's think about this. May birth: July/August date of conception. January birth: March/April date of conception. Now what's different here? One is a rainy, not real hot or cool period of the year (at least for the NE). July/August.. those are the dog days, when it's soo damn hot and humid (at least in the NE again). I'm thinking it just so happened there's more married births in May because those married couples were too hot in July/August, slept nude.. and well one thing led to another!

Re:Born in December

[Thomas M Hughes]

I was born in December and pursuing double masters with GPA of 3.4 is it really bad?

I was born in June, and received a Ph.D by the time I was 27, with a 3.95 GPA. Luckily for me, part of that Ph.D training involved learning that the word data is not the plural of anecdote.

Re:Born in December

[Anonymous Coward]

http://en.wikipedia.org/wiki/Muphry's_law

Re:Born in December

[jonadab]

I was born in late December and stopped once I got my Bachelor's (but with a GPA significantly higher than 3.4) to pay off my student loans. I paid off the last of the loans within four years after graduation and have been continuously employed since. But these are just individual data points, and the slashdot readership is by no means a random sample of the population in any case.

Re:Born in December

[SilverHatHacker]

I know the feeling. Born in January, running a 94% average for my entire school career.
Don't it feel good to be a misfit? (And to all the grammer Nazi's, that was intentional.)

Re:Born in December

[entropy_uc]

Dumb chicks put out in spring when they are horny.

Smart chicks put out when the crops are mature and it's clear there will be enough resources to feed another mouth.

It's amazing how much human behavior is hard wired into us.

Re:Born in December

[sumdumass]

Yea, it just evolved that way and despite a century of grocery stores and not getting your food from the farm directly, it has not evolved back away from it. Go figure.

Re:Born in December

[ucblockhead]

It's a pity...if only you'd been born in May, you'd have been getting a 96% average!

Re:Born in December

[Anonymous Coward]

But was "grammer Nazi's"?

CAPTCHA: majestic. The level of irony if it wasn't.

Re:Born in December

[Anonymous Coward]

I was born in December and pursuing double masters with GPA of 3.4 is it really bad?

I was born in June, and received a Ph.D by the time I was 27, with a 3.95 GPA. Luckily for me, part of that Ph.D training involved learning that the word data is not the plural of anecdote.

It's a good thing, too, because your comment might otherwise serve as the first brick in the foundation of my claim that summer babies are caustic and monumental shitheads that seem to spend their free time in pissing matches.

Re:Born in December

[Anonymous Coward]

It must suck to have paid for 3 college degrees in order to make $100K/year.

I was born the end of November, only had to get 1 college degree, and I make $150K/year. Of course, a single exception doesn't rule out a general effect.

Re:Born in December

[drizek]

I was born in August of 1995 and I am pursuing a PhD in Rocket Science and another in Brain Surgery. My GPA is a 4.22.

Re:Born in December

[markov_chain]

yeah srsly, citing a Ph.D GPA? u r doing it wrong

Re:Born in December

[SilverHatHacker]

grammer Nazi's:
'gra-mer nat-sees, n.
The kind of people who's goal in life are to point out you're mistakes.

Re:Born in December

[ceoyoyo]

I was born in June and finished my PhD while maintaining a GPA of 4.0 throughout grad school.

We've got two anecdotes... does that mean we have data now? ;)

Re:Born in December

[Imrik]

I have a different take, July/August school is out, March/April Prom and spring break. In other words, I think teenage pregnancies are hiding any thing else interesting in this kind of data.

Re:Born in December

[value_added]

I was born in June, and received a Ph.D by the time I was 27, with a 3.95 GPA. Luckily for me, part of that Ph.D training involved learning that the word data is not the plural of anecdote.

Bah.

Everyone knows Geminis are a smart lot (I'm one, too) so your accomplishments, while impressive, shouldn't be considered surprising. As for the OP, Sagittarius is a fire sign, so if he's anything like the Sagittarians I've known, he's probably dumb as a brick, but has the capacity to work harder than everyone else.

Whether the above is science, myth, anecdote or a case of "it's on the internet so it must be true", you be the judge. ;-)

Re:Born in December

[Eternauta3k]

ahhaha
I've been reading the discussion and getting it completely backwards. Damn people not specifying their hemisphere (I was born in June, but I'm a "winter baby").

Re:Born in December

[ucblockhead]

Just to give an idea how silly individual data points are, here's what the data says in English:

People who are born in January will get, on average, one month less education.

Babies who are born in January are 10% more likely to have a teenager for a parent. (Note teenager means under 20)

Babies who are born in January are 3% more likely to be born to an unwed mother.

Interesting statistics, but the differences too small to really matter when comparing individuals. The fact that all of these measures aren't showing direct correlation with success but only correlations with other factors that correlate with success, any concern about when individuals are born is pointless. This study says little or nothing about what advantages a rich kid with married parents who is born in May might have over a rich kid with married parents who is born in January.

Re:Born in December

[Anonymous Coward]

It must suck to have paid for 3 college degrees in order to make $100K/year.

People with GPA's of 3.8 don't typically pay for their college degrees. I had a ~3.8 and got enough scholarships to cover my B.S. (plus living expenses + books + food + some extra spending cash which I used to buy a laptop). Graduate assistanships paid for my graduate education.

Re:Born in December

[Anonymous Coward]

Wow, a PhD!!!!!

I suppose you have to be at the university gym in 26 minutes as well?

Re:Born in December

[Harry_Mohan]

Forgot to mention I got 80% scholarship.

Re:Born in December

[Anonymous Coward]

Troll

Re:Born in December

[bennomatic]

It's a pity...if only you'd been born in May, you'd have been getting a 96% average!

And that significant difference would be significant!

Re:Born in December

[Racing_Turtles]

Dumb chicks put out in spring when they are horny.

Smart chicks put out when the crops are mature and it's clear there will be enough resources to feed another mouth.

It's amazing how much human behavior is hard wired into us.

Charming use of "put out" and "chicks". You're a regular Casanova, I'm sure.

Re:Born in December

[Anonymous Coward]

Luckily for me, part of that Ph.D training involved learning that the word data is not the plural of anecdote.

It's a good thing, too, because your comment might otherwise serve as the first brick in the foundation of my claim that summer babies are caustic and monumental shitheads that seem to spend their free time in pissing matches.

I was born in January and have no idea what you're talking about

Re:Born in December

[Anubis IV]

3.7 and born in November, here. See what a difference just a month makes? Imagine how different things would be had we been born in summer.

I can just see it a few decades from now. Children sue their parents for giving birth to them during winter months because it disadvantages them with regards to their education.

Re:Born in December

[Anonymous Coward]

Luckily for me, part of that Ph.D training involved learning that the word data is not the plural of anecdote.

Ah, English majors....

Best of luck; it's a tough market packed with highly qualified people you're facing.

Re:Born in December

[RazorJ_2000]

Hahaha!! Now that one deserves to be modded up!!!

Re:Born in December

[IdolizingStewie]

He paid for it with the extra years spent earning living expenses instead of a real salary to get the second 2 degrees. And for the record, my husband graduated with a 3.8 for his BSME with little to no scholarship money awarded him. Then again, maybe it's because he was born in February.

Re:Born in December

[poopdeville]

Seriously.

Who cares about some schmuck's grades? What has he published?

Re:Born in December

[demonlapin]

Loser. I was born last Sunday and had a 5.45 GPA while getting my Ph.D.Phil. in Rocket Surgery.

Re:Born in December

[Raffaello]

Pathetic. I won't be born for another 5 millenia and I already have Ph.D.s in every major scientific, technical, and mathematical discipline. It's been nice talking to you, but I have to go back in time now and ghost write Philosophiae Naturalis Principia Mathematica for some dopey January baby. Thanks to what I'm about to do you'll certainly have heard of him - Isaac Newton. The funny part is that even after I've explained mechanics and calculus to him, he keeps insisting that he can find the Philosopher's Stone and alchemically transmogrify base metals into gold, the limey fsck-tard.

Re:Born in December

[Anonymous Coward]

Nah, too much selection bias! :p

Re:Born in December

[Anne Thwacks]

My GPA is a 4.22.

I was born in Europe, and I am still here. WTF is a GPA?

Re:Born in December

[drizek]

Grade ooint average.

A is 4.0, A+ is 4.33, B- is 2.67, etc.

GPA is the average of all the numerical values of your letter/percent grades.

Re:Born in December

[c_sd_m]

Or smart chicks don't want to be pregnant and hot in the summer or have kids with birthdays near Christmas/Thanksgiving or have to get to the hospital in the middle of a major winter storm. So ideally they would plan for May-June.

Re:Born in December

[Anonymous Coward]

Hell, I make that much and never went to college. Are you sure your parents didn't lie to you about your birthday? Maybe you're really a January baby and they were just trying to protect you from the truth.

Unwed mothers?

[Anonymous Coward]

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.

Unwed? What is this, 1950?

Re:Unwed mothers?

[Anonymous Coward]

There's a statistical correlation between childbirth in winter and the parents of the child not being married. Is pointing that out politically incorrect or what are you insinuating?

Re:Unwed mothers?

[r00t]

We have more than enough evidence to conclude that
kids do better in intact 2-parent families.

Casting tradition aside isn't without a cost.

Re:Unwed mothers?

[jonadab]

> Unwed? What is this, 1950?

Statistically, the marital status of the parents is highly relevant to the child's prospects. Children whose parents are married to one another from prior to conception clear through until the child is an adult get on average much better grades in school, are significantly more likely to consistently hold down jobs as adults, make more money on average, are significantly less likely to have a criminal record, are less likely to be smokers, and so on and so forth. These are quite strong correlations.

Now, correlation is not causation. It's possible that the parent's strong marriage does not *cause* the child's good prospects and performance, but rather that both are caused by some of the same socioeconomic factors. But it's still very much relevant in a statistical study like this.

Re:Unwed mothers?

[Lord Kano]

Children who are born to mothers that are not married tend to have less complete support systems and fewer financial resources. Even the best single mother can only do so much in 24 hours. She can't do it all. As a result the children can suffer. Children that grow up with parents who have a healthy relationship have an advantage of those who don't.

There's less social stigma attached to it today, but the results are the same.

LK

Re:Unwed mothers?

[pgillan]

Now, correlation is not causation. It's possible that the parent's strong marriage does not *cause* the child's good prospects and performance, but rather that both are caused by some of the same socioeconomic factors

I like the idea that it's actually a reverse correlation- that stupid children with poor prospects and bad grades cause their parents' divorces.

Re:Unwed mothers?

[Anonymous Coward]

But the statement had nothing to do with whether the child was in an intact 2-parent family. Assuming that's the same as the parents being married is a 1950's mentality.

Re:Unwed mothers?

[rohan972]

Being married with children, I can't help but agree. Having only one parent makes day to day life with children tremendously harder (as you experience temporarily if your spouse is away for some reason, such as being in hospital having the next baby). Doing something as basic as going to the shop to pick up a few items takes a lot more effort if you have to take young children with you compared to one parent going to the shop while the other stays with the children.

Of course, the strength of the relationship is more important than government certification, but people who commit to their relationships are probably more likely to legally formalise the relationship as well.

Re:Unwed mothers?

[slim]

It's always 1950 somewhere...

Different metric

[HangingChad]

If you count backward from January, that puts conception around April/May. Right around graduation. So if you suppose the poor and less educated would be getting married and starting a family instead of getting ready for college, that might explain some of it.

It would probably be just as interesting to track the birth rates correlated to surges in beer and Jagermeister sales.

Re:Different metric

[plague911]

Thats kinda interesting as there has always been that spring/love thing going on. It to me makes sense a lot of babies that are from less educated individuals would be a result of spring time flings (when hormones are high) as opposed to long term planning.

Re:Different metric

[Anonymous Coward]

My guess is that educated people see their friends getting their kids ready for "back to school", and get excited about it (having fond memories of school), and it leads to wishing they had a kid to take back to school. Hence, higher August/September conception rate.

Looking forward to more data being brought in to this discussion to try and tease out other patterns.

Is the effect stronger in the north, where fall is a longer, beautiful season (increasing the Back to School ambiance)? (Here in Texas, the leaves are green one week and the tree is bare the next.) What happens to the numbers if you pull out all mothers younger than 18/likely high school graduation age, and treat the two as unique populations? Or if you separate single and wed mothers?

Re:Different metric

[NoYob]

I know a few folks that are quite well educated but are poor and vice-versa.

I think that's a potential area for error in this study: eduction == socioeconomic status.

Re:Different metric

[ucblockhead]

Lots of studies have shown that higher socioeconomic status correlates with higher education

Re:Different metric

[Anonymous Coward]

I think that's a potential area for error in this study: eduction == socioeconomic status.

Lots of studies have shown that higher socioeconomic status correlates with higher education

Yes, higher socioeconomic status correlates with higher education, but it does not correlate with eduction, which was your parent's claim.

Re:Different metric

[bennomatic]

Actually, April/May is more like the lead-up to finals. People who are going to get a better education are probably a bit busy during that time.

Doesn't change your point, though.

Also, wasn't there a surge in births after the big black-out in New York?

3rd bump

[danlip]

There is a secondary bump around September in each of these charts - it's much smaller but consistent every year. Fascinating.

Re:3rd bump

[wellingj]

New Years and Christmas parties?

Re:3rd bump

[temojen]

Christmas party conceptions. As opposed to the other two which are prom/graduation conceptions and back to school conceptions.

Re:3rd bump

[WMD_88]

New Years resolution: let's have a kid this year! Or something like that. (No, really, I read something to this effect this past January. It's bound to pop back up in the media come the end of this year.)

Re:3rd bump

[Anonymous Coward]

As the father of a September baby, I can confirm this. The hospital we went to for his birth was overwhelmed. We actually had to start in an examination room before moving to a birthing room.

Our birthing class was also much larger than normal and the instructor confirmed that September is always a popular month for babies due to holiday parties and extra time off.

Re:3rd bump

[cheesybagel]

Beginning of the school year? :-)

Correlation is NOT causation

[Anonymous Coward]

The real causative in winter babies is that babies born under winter's astrological signs have shorter lifelines.

Re:Correlation is NOT causation

[ooloogi]

Exactly- and the astrologists are still trying to work out why the characteristics of the signs are exactly opposite between children born in the USA and in Australia.

Anonymous Coward

[Anonymous Coward]

This is all crap, i was born in JAN.. very good physically, fall ill less and already among the first 5 of the class since i was a kid.

Re:Anonymous Coward

[ucblockhead]

Perhaps if you were born in May, you'd understand about significant, but small statistical differences and how they relate to the experience of individuals.

Or to put it in more real world terms, you are like a woman reading an article saying "statistically speaking, the average man is four inches taller than the average woman" and saying "what crap! I'm taller than a lot of men I know!"

Re:Anonymous Coward

[Anonymous Coward]

First 5 of class to do what, fail English?

Conception in July/August

[Bwian_of_Nazareth]

I see the explanation in the fact that married and educated women have sex with their man only once a year during their holiday in July/August. :)

Re:Conception in July/August

[NoYob]

Sonnna-of-a-bitch! Why couldn't they have discovered that when I was young! I was born too goddamn early! I could have been getting laid during those months, but noooooo, I was working and going to Summer school! A lot fucking good it did me! Instead of being washed up and depressed and I could be washed up, depressed, and with some fond memories from my young adulthood of getting laid by randy smart chicks!

Re:Conception in July/August

[Anonymous Coward]

Dangit, I missed it. AGAIN!

Winter where?

[xirusmom]

I wonder if all the data comes from the North Hemisphere? What happens in the south?

Re:Winter where?

[wonmon]

The teenagers conceive in the clockwise direction.

Re:Winter where?

[masmullin]

i think your doing it wrong.

Re:Winter where?

[bennomatic]

These bumps change shape in the southern hemisphere because health and success are much more closely correlated to the quality of available water in the region where you're born and grow up.

Re:Winter where?

[Anonymous Coward]

Yes , On their anniversary

School entrance age cutoffs, maybe?

[e9th]

The age cutoff for entry to kindergarten seems to cycle around mid-September, but varies quite a bit from state to state. But in general, a kid born in the winter will have to wait longer to start school.

Re:School entrance age cutoffs, maybe?

[eh2o]

They should have spring admission to kindergarten! November baby here and I'm about a year older than most of my classmates.

Re:School entrance age cutoffs, maybe?

[e9th]

I suppose it's logistically infeasible, but a true trimestral school year would keep students within 4 months of their peers. Of course, it would also kill summer vacation, so...

Re:School entrance age cutoffs, maybe?

[32Na]

Another effect that might play a small role here: the school year in the US typically ends in May, and school teachers might have tried to 'time' their pregnancy in order to have a baby after school let out for the summer, and so have at least three months with their baby before the next school year started.

This was the case in my family: my mother was a teacher, and both my sister and I were born in May, just as school let out (I'm speculating about cause and effect, however).

Re:School entrance age cutoffs, maybe?

[Mashiki]

I was born in December. I started 3mo early, my parents rammed me through. But I don't live in the US either, I believe their words were something to the effect of "3 months doesn't make a difference when you're already at that curve."

Re:School entrance age cutoffs, maybe?

[masmullin]

Your grammar and spelling are amazing for a 6 year old! Do you understand most the articles on this website?

Coochie Coochie cooo... who's the smart kinder... YOU are, YOU are

Peekabo!

Re:School entrance age cutoffs, maybe?

[Anonymous Coward]

Wouldn't they time it so the baby was born in sept so their maternity leave was not wasted?

Re:School entrance age cutoffs, maybe?

[alex_guy_CA]

I though that it was better for kids to be the older ones in their class. Is there research about this? I just started my daughter in K late instead of early (November birthday) thiking being older would help her excel.

Re:School entrance age cutoffs, maybe?

[msimm]

Heh. Does that mean that winter babies would tend to be physically larger then their spring counter-parts? With the spring babies beginning earlier having less physically developed frames?

Do winter babies get picked more in dodge-ball?

Once and for all, have we discovered the true source of the jock/nerd divide! ;-)

Re:School entrance age cutoffs, maybe?

[Anenome]

There is some research on this in Malcom Gladwell's "Outliers", specifically how age affects spors performance. It turns out that an extremely large number of professional athletes across various sports are all born within certain dates which corresponds to cutoffs for that particular sport.

What's important is to get an extra year of development before you enter at the same level. So, people born just before the cut-off are the best off.

The same is true of academic life. The better off children, both socially and intellectually are those whom are slightly older, yet competing in the same grade. That small advantage begins to snowball with time until it becomes an insurmountable barrier.

Getting your child into school earlier is a mistake, so may be advancing kids a grade. Anyway, check out the book, lots more info in there.

Re:School entrance age cutoffs, maybe?

[Anonymous Coward]

+1 Smartass

Re:School entrance age cutoffs, maybe?

[MLease]

Depends on how generous the maternity leave policy is. I don't know offhand what schools do (and it probably varies widely from state to state), but I know of companies that only offer a couple of weeks of paid maternity leave. If the school system in question only offered that, it would make a lot more sense to shoot for a May birth, and leverage the summer break to care for the baby for the first 3 months of its life.

-Mike

Re:School entrance age cutoffs, maybe?

[frieza79]

You're assuming that school teachers are smarter than average?
And even more of a stretch, that their kids are?!?!

united healthcare will add this to pre existing co

[Anonymous Coward]

united healthcare will add this to pre existing conditions list

Mr. Hungerman? Babies?

[Like2Byte]

Anyone else picture this guy screaming, "Get in my belly!!"?

Forest for the trees

[cenobyte40k]

Looks like someone couldn't see the forest for the trees. All these years of study before someone figured out that there was a releation to the intelegence/eduction/etc of parents. Ugg...

Re:Forest for the trees

[Anonymous Coward]

releation to the intelegence/eduction/etc

I'm guess you were born in the December/January timeframe...

Sample Size?! Confidence Intervals?!

[Anonymous Coward]

Where are the error bars? What was the sample size each year? Were the raw data selected in an unbiased manner? What is the author's definition of "significant"?

Here's what I think is wrong.

[NoYob]

I didn't see anything about them trying to eliminate the socioeconomic attribute from the study. In other words, remove all the poor kids from the data and see if there is still a correlation. If there is a difference among kids from the same socioeconomic background being born in different times of the year, then I would consider that there is something to what season a kid is born.

Re:Here's what I think is wrong.

[armareum]

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.

Well now i dont feel so bad

[binaryseraph]

... and all this time I was pissed because my birthday wasn't on xmass and I didnt get twice the presents. Wish i knew the kids were doomed to being dumbasses. Now I wear my summer birthday(suit) with pride.

Re:Well now i dont feel so bad

[demonlapin]

You do realize that if your birthday is close to Christmas, they buy you one present that's maybe 10% better than the Christmas or birthday present you would have gotten and tell you it's the gift for both, right?

Re:Well now i dont feel so bad

[binaryseraph]

haha well now I feel freakin awesome!

Zodiac

[LoverOfJoy]

The zodiac holds the most obvious relationship. Everyone knows Geminis are smarter than Aquarius folk. It's in the stars.

Re:Zodiac

[Anonymous Coward]

Bah! Everybody knows reading chicken entrails is the only way to be sure.

Re:Zodiac

[ooloogi]

Obviously Southern hemisphere data would confirm or deny that.... There's a serious point in that though, in that many of the speculated reasons for correlation could be investigated by comparing the effect in different countries, and even across the different climates within one country.

School & Sports ??

[elijahu]

It might make an interesting study to compare the success of kids with "late" birthdays who started on-time/early versus those who had to wait an extra year.

I thought I'd heard of a similar study where kids with winter birth dates excelled at sports because they tended to miss cut-off dates for teams, and therefore were older, larger, faster, and more mature than the kids they were teamed with each year. This leads to them getting more time handling the ball as they grow up.

Re:School & Sports ??

[e9th]

Nevada would be a good place to start. Their cutoff dates are 5 by 9/30 for K, 6 by 9/30 for 1st grade. Period. No exceptions. It would be interesting to follow a group of kids born in September and October through the system and see what (if any) patterns emerge.

cause and effect reversed

[cinnamon colbert]

suppose educated women (and education strongly correlates wit income and wealth) "know" htat babies are supposed to be born in the spirng.....
this would rduce the whole thing to a cultural artifact: well to do parents tell thier kids to have a spring baby, and so it goes...

Re:cause and effect reversed

[Anonymous Coward]

Hm...

Actually as an educated woman - may I say that I indeed planned to have a baby in spring because: 1) less germs are around b) there are 6 - 7 sunny months ahead to take the baby out without trying to dress it in 2000 clothes.

Of course it does not work out as planned, but the fact that we TRIED and PLANNED implies that it is NOT RANDOM!

I asked my own mom (not extremely educated - she is just an economist) - same there. All my siblings were planned for March- and indeed were born in May-June windows. Northern Hemisphere, of course.

So I was not surprised at all with the results. Ask your moms, people!

Re:cause and effect reversed

[ooloogi]

With all the studies saying that winter babies perform poorer in life, no wonder that educated parents choose to try to have their children in spring to summer.

Re:let me explain this to you.

[Anonymous Coward]

He's pretty young. You have no idea how stupid he'll turn out ;) /three kids ...

Re:Correllation is Not Causation

[ceoyoyo]

Sigh. Correlation means one of three things with regard to causation. In this case those are:

a) being born in the winter causes increased risk of health and education problems for the baby
b) the baby's increased risk of health and education problems causes him or her to be born in the winter (clearly ridiculous)
c) a third factor causes the baby to both be born in the winter and have increased risk of health and education problems.

The correlation between birth month and risk of health and education problems has been observed. This study is pointing out that the direct causative option (a) is probably not true since they have found possible third factors (c) that appear to influence birth month and are known to have an effect on the risk of health and education problems.

In other words, the study is saying, with actual data and without the childish, misunderstood slogans, the same thing you are - birth month does not cause increased risk of health and education problems.

Showing correlation is required for establishing a causative link between two observations so no, correlation studies do not "need to die." It would be nice if people (including you) understood them a little better though.

Re:Correllation is Not Causation

[icebike]

Of course the larger correlation was also observed, but apparently ignored in the summary:

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.

Spring break, and Back to school seem to correlate as well as anything, and both seem to correlate to higher instance of teen mothers. The numbers of teen mothers probably swamp any other significance.

Bullshit

[Anonymous Coward]

I was born in November in Minnesota and I have an IQ of ~130.

Re:Bullshit

[ooloogi]

I was born in November in Minnesota and I have an IQ of ~130.

They probably weren't measuring IQ though, they may have been measuring skills such as being able to recognise that one data point doesn't confirm or deny a trend.

Re:Bullshit

[Anonymous Coward]

The lower-IQ of winter babies is an accepted fact from many studies. The paper mentioned above is simply putting forward an explanation for it involving the known inheritance of IQ and different demographics having non-equal birth timing throughout the year.

Also, a lower average IQ in winter months does not eliminate the possibility of someone of 130 IQ being born, it means that simply less people of higher IQ are born than other months. A single data point such as your own example is thus completely meaningless.

You'd hope someone with an IQ of 130 (which while not spectacular, should enable reasonable performance at most activities) would be able to recognise this.

Re:Correllation is Not Causation

[Iron Condor]

And don't think there a correlation so profoundly stupid that someone won't publish a "scientific" paper on it.

Sunspots influence the global weather in a measurable (and well-understood) way. Grains grown in a climate either at the upper or lower end of the temperature scale at which they thrive (wheat in Britain, for example, or corn in Arizona) can be pushed into (measurable and predictable) lower harvests and even complete mis-harvests. Why and how global economic measures like the total GDP and the DJA can be sensitive to such things as the global success of food production is left as an exercise to the reader.

Can you find it in your heart to read up to these things? One of the very real, very measurable and very predictable dangers of global warming is the well-studied, well-known and well-understood link between just a degree or two global temperature change and the measurable economic penalties going with it. These things have been measured, tested and modeled for years. (Amongst a myriad of other things, this is one of the ways we know that sunspots are NOT responsible for the drastic global average temperature rise in the 20th century. Because their effect on the global energy budget is measurable.).

Isn't this sort of obvious.

[tthomas48]

People who plan their pregnancies are more likely to be educated, married, and not teenagers. People who plan pregnancies are not likely to try to target November - January, because it's cold and they won't want their babies birth close to Christmas and Thanksgiving.

Re:Isn't this sort of obvious.

[AJNeufeld]

Add to that not wanting to be pregnant during the hot summer months, and wanting to avoid "cabin fever" (for those of us living with serious amounts of winter snow) with a newborn baby, and you're pretty much left with a spring birth.

Re:Isn't this sort of obvious.

[zoefff]

That is under the assumption that the first shot is aimed right....

Re:Isn't this sort of obvious.

[tthomas48]

Not really. You just plan what months of the year you're willing to try. I live in Texas so my wife had no interest in trying for a baby in November through January.

Re:Isn't this sort of obvious.

[Macgrrl]

As an educated woman who has been trying to get pregnant for nearly 3 years now, I can tell you that pregnancy and planned don't really go together. About all you can say is whether it was deliberate or not.

Re:Isn't this sort of obvious.

[tthomas48]

Agreed, all of our terminology is based on the idea that every pregnancy is always deliberate. Really we're talking about procreative sex planning.

We're human. We plan. Even thought it often seems somewhat silly in retrospect.

Re:Isn't this sort of obvious.

[kthejoker]

People who plan pregnancies are not likely to try to target November - January, because it's cold and they won't want their babies birth close to Christmas and Thanksgiving.

(Score:3, Interesting)

I guess "random statement about planned pregnancies that makes no sense when you read it twice" is the same as "interesting" these days? Kind of like the beardy guy smelling like underpass spouting not-real-Bible-quotes at me. "Yes, yes, very interesting ... please let go of my sweater. No, no more crazy, I am full, thanks."

Re:Isn't this sort of obvious.

[tthomas48]

Can you explain what doesn't make sense about that quote? Because it still makes sense to me. My mother had a close to Christmas birthday and always got combo Christmas/Birthday gifts, so she explicitly planned to keep all of her kids birthdays away from the holidays.

I'm currently in the phase of life where most of my friends are having kids and we've often discussed the disadvantage to having kids around Christmas. I have one friend who had a kid with a birthday around Christmas and that was unplanned. I'm not saying that no one has ever planned to have a child in December, I'm just saying that when planning you're more likely to try to steer around it (and as other people have stated once you've been trying a while you'll take a baby in any month of the year).

Re:let me explain this to you.

[Anonymous Coward]

Nice advertisement. Nobody cares about your anecdotal life. And I wouldn't call a 19-month old "intelligent." Maybe just not developmentally challenged.

Was that study done in the winter?

[Anonymous Coward]

My winter born daughter scored a 1600 on the SAT.
My 1st son born in winter scored a 1590 on the SAT.
My 2nd son born in Winter scored a 35/36 on the ACT.

Just think how good they would have been if only they were born in the summer!

So, around here, that study is full of hot air.
Maybe the study was done in the winter (grin).

I think I figured it out:

[Anonymous Coward]

Spring break: baffling economists since 19XX

MomAlways Tole Me I'm Special...

[tunapez]

Sagittarius here, 2 bros and parents all born in spring or summer. I'm the only one who attended college, earned my BS in exactly 36 months. Grades weren't great(2.7GPA) but like I said 36 months, while working 3rd shift 25+ hr/wk merchandising in grocery stores. Shortly after I graduated I was passed over and my employers hired a gal w/ better grades and NO industry experience. That fall('94) I went to work for a brokerage house selling Muni Bonds, 3 months later I found out why my boss transferred from Orange County. Never had a corporate job since, their contract work pays way to good, work when I feel like it and no office politics. Win-win-win. However, I will never come close to making as much as either of my parents(divorced), my brothers tend to earn more(and more regularly) than me, and I am A-OK with that. I have had more trauma and ailments than any of them, but most of it was brought on by thrill-seeking and irresponsible lifestyle choices. Meh, you only live once.

No traffic, no 9-5, work from anywhere there's a signal: Priceless.

Re:Sample Size?! Confidence Intervals?!

[Cal27]

What was the sample size each year?

Approximately everyone.

Missing data?

[nurbles]

Did anyone else skim (or actually read) the 2008 paper by the researchers that was linked in the article? I notice many mentions of winter months and January but nothing about February or March (or the last week of December). In fact, the tables of data at the end of the paper list by month, but omit January, or by quarter of year, but omit the first quarter. What's the point of including data for everything except the two most mentioned time periods in one report?

Something seems bogus to me.

I don't get it...

[T Murphy]

They seem to put a kid as being disadvantaged for having a mother that completed high school in fewer years than her peers.

Re:Correllation is Not Causation

[raju1kabir]

And how may I ask does the month your mother gave birth to you lead to a lifelong plight? If ever their was a classic junk study showing the usual correlation-causation woolly thinking, this is it. Apparently, a lot of unmarried, less educated mothers have more unprotected sex in May (or less in January). Why would this lead you to conclude that being born in winter disadvantages someone. I was born in winter and my mother was married, educated and employed. Has my life been deprived somehow? Do I need extra money or protection or something?

Nope, just a stats class.

Across a population, being tall confers a slight advantage in terms of income.

That doesn't mean any given tall person is going to earn more than he'd earn if he were shorter.

Re:Correllation is Not Causation

[ceoyoyo]

True, the summary is poorly written - it only mentions one of three significant indicators. This IS Slashdot though. If the summaries were well written in the first place what would the editors do?

(To the sarcasm impaired: yes, I'm kidding)

Hilarious..

[tuomoks]

One of kids born the hottest day in 50 years, one born the coldest day in 80 years, one between - don't see any difference. Now, of course, if I would need research funds I might start seeing the differences - heh! Or maybe it was the size of the car in which they were taken home from hospital (need a car analogy in Slashdot) - have to start the research, just have to get maybe government funding for it.

We have hospitals in the Southern Hemisphere.

[ChunderDownunder]

When your wife gets to 7.5 months, take a 6 week vacation. You get to see some different fauna be it kangaroos, llamas or wildebeest. The baby is born during summer and has an exotic location on its birth certificate.

Problem solved!

Re:We have hospitals in the Southern Hemisphere.

[Anonymous Coward]

I thought most countries didn't allow that since it's an easy way for foreigners to get citizenship of convenience for their baby...

Fly in the Ointment

[David_Hart]

I am a December baby and I went far in school (dual Bachelor's, working on a Master's degree) and I have been very healthy. My sister, who was born during the summer, had major allergies as a kid, though she too went far in school (Bachelor's). Maybe I wasn't born far enough into winter. After all, I started school when I was 4 (vs 5) as I was turning 5 before the end of the year. Maybe I won the genetic lottery for winter babies...

David

Re:Fly in the Ointment

[u38cg]

Anecdote != data.

Re:Correllation is Not Causation

[skine]

Furthermore, if the summaries were well written, what would we have to argue about?

Re:Correllation is Not Causation

[MMC Monster]

b) the baby's increased risk of health and education problems causes him or her to be born in the winter (clearly ridiculous)

You are assuming that the time axis is positive in all cases. Do you have a proof this is the case?

Re:Correllation is Not Causation

[ObsessiveMathsFreak]

Sigh. Correlation means one of three things with regard to causation.

So you are telling me that Saturn is somehow connected to the S&P 500? Or that Sunspots are responsible for US GDP? How far are we allowed to take this? How different is this study to the two I've mentioned?

In other words, the study is saying, with actual data and without the childish, misunderstood slogans, the same thing you are - birth month does not cause increased risk of health and education problems.

That is not what the study is saying. The author's of the study claim that it simply means that relatively more winter babies are born to unmarried and less educated mothers. The Wall street journal claims the study has found an explanation for the "lifelong challenges" of winter babies, as did the Slashdot summary. You've claimed something else? What will the tabloid newspapers claim? "Winter babies unhealthy, uneducated, unemployed?" How far do you think they'll go with it? When were you born?

This study has not proved anything. It hasn't even suggested anything. It offers no reasoned explanation for its finding, with even the authors leaving such matters (proms and spring break) to the speculation of the reader. Is this how we do and accept research? Crunching two sets of numbers, finding a 1.2% overall spread in figures and then declaring that people born in winter suffer from a lifelong plight, without even bothering to provide genuine reasoning or enlightenment. Is that ethical? Is it scientific? Is this how we uncover the world?

Showing correlation is required for establishing a causative link between two observations

This is a position which I fundamentally reject. Stephen Hales and Thomas_Young established causative and quantitative links before statistics had even been invented. Correlation is neither a neccessary nor a sufficient condition to establish any relationship between two variables. We cannot understand the world by computing correlation coefficients between data sets. If we continue to rely on them in this way, our understanding of the world will be reduced to the tunnel vision seen in the Slashdot headline; "Winter babies weaker, sicker, poorer, less intelligent".

Theories are about more than finding linear relationships between variables. They are about obtaining a complete and comprehensive understanding of phenomena, on a qualitative and quantitative level. You do not need correlation studies to do this, and you certainly cannot present them as an end result in and of themselves. Yet that's what people do. Take a database, mix it all around, get r=0.2 and a range of 1% and just throw it out in a paper. Let people make whatever they want of it. And they do.

Correlation is not causation, and it is not the modern Oracle of Delphi, revealing great truths. It's more likely to mislead than inform. So why should we trust it now? Read up on Hill's criteria of causation and ask yourself; How many of these (minimal) conditions did the researchers in this study actually establish?

Can't be true...

[Anonymous Coward]

Well I was born in December and by the time I was twelve I had nine Bachelor's degrees, four Master's and two PhDs, all with a GPA of 5.9. I slept with a different supermodel every night all of whom were impressed with my eleven inch penis.

I'm currently earning more money than Bill Gates and I'm stronger and more famous than Superman. Women love me, men want to be me and even my flatus has been bottled and sold for $500 an ounce.

I seem to have forgotten my point, but I'll just have to satisfy myself with having won the "born in winter and on the defensive" pissing contest.

It's simple

[Waccoon]

Birthday Blues! If my birthday was next to Christmas, I'd be depressed all the time, too.

Re:It's simple

[barzok]

It really does suck. Try being half-Jewish and getting your birthday lost amongst Hanukkah & Christmas,

Re:Correllation is Not Causation

[ceoyoyo]

Well, there's always someone like the second poster in this thread (modded to oblivion now) who manages to read the summary and the article and still write a post criticizing the article for... saying the same thing he just did.

Re:Correllation is Not Causation

[ceoyoyo]

Yes, but I've already shown it to you.

They probably modded you flamebait

[pem]

Because there isn't a -1 "Didn't RTFA" mod.

The article clearly states that it was (almost) all U.S. births during a certain time-frame, data courtesy of the CDC.

Re:Correllation is Not Causation

[ceoyoyo]

If you'd like to post a link to the supposed correlation between Saturn and the S&P perhaps we can discuss it. Is it an actual correlation? You do know that correlation doesn't mean "has an r^2 greater than some arbitrary threshold", right?

A correlation means that there IS a link between two things. An r^2 (or r) value indicates the strength of the aparent observed connection, and is also associated with a probability that the observed connection is not simply an artifact due to chance. Perhaps your Saturn-S&P "correlation" is simply that - a statistical fluke, perhaps born of someone doing multiple comparisons and not correcting for them. Actually, that seems extremely likely. I very much doubt someone purposely compared any feature Saturn and the S&P in a single, once-off test. By the way, what do you mean by "Saturn?" It's mass? Orbital period? Colour? The Roman God's independent living index?

That is not what the study is saying. The author's of the study claim that it simply means that relatively more winter babies are born to unmarried and less educated mothers. The Wall street journal claims the study has found an explanation for the "lifelong challenges" of winter babies, as did the Slashdot summary. You've claimed something else? What will the tabloid newspapers claim? "Winter babies unhealthy, uneducated, unemployed?" How far do you think they'll go with it? When were you born?

I don't know what the tabloids will claim (nor do I care), but the Slashdot summary is quite correct. They have found a new explanation for observed differences between winter and summer babies - the winter babies are more likely to be born of unwed, more poorly educated mothers. That explanation may not be THE explanation, but it is certainly AN explanation. I haven't done the background research to verify whether it is NEW or not, but it seems plausible. What part are you objecting to anyway? Perhaps you've confused the meaning of "explanation" with "absolute truth?" Maybe if you paid a little less attention to what the tabloids say....

In other words, the study is saying, with actual data and without the childish, misunderstood slogans, the same thing you are - birth month does not cause increased risk of health and education problems.

That is not what the study is saying.

Actually, you're right. The study shows that there is a small remaining association between birth month and various outcomes, but it is very much weakened when socioeconomic status of the mother is taken into account. So really the study is saying birth month doesn't cause these outcomes, at least not to the degree that was previously believed.

This study has not proved anything. It hasn't even suggested anything. It offers no reasoned explanation for its finding, with even the authors leaving such matters (proms and spring break) to the speculation of the reader.

Actually, they have a whole section on possible explanations for why they see the trends they do, even though that is not the focus of their paper. They even use the phrase "prom baby" except that they have lots of references to actual research that has been done into the phenomenon. Of course, the actual point of their paper is to warn against drawing unwarranted conclusions from the season-outcome correlation, such as that the school intake system is unfair to winter babies. Wait... you did read the paper before you complained about it (and not just it, but condemned all of a large class of studies) right?

This is a position which I fundamentally reject. Stephen Hales and Thomas_Young established causative and quantitative links before statistics had even been invented. Correlation is neither a neccessary nor a sufficient condition to establish any relationship between two variables. We cannot understand the world by computing correlation coe

Home Life.

[MSUskater]

I think that it depends on your home life. If you were born in the winter and your home life was tough such as you were raised by a single parent, or your parent are going through a divorce, or your parents education isn't real impressive then you probably won't be awesome in school because the good example isn't there. Sometimes financial struggles of the parent(s) can also allow for less access to good schools, good school materials, and a good education. Stress from home can cause a lack of motivation in education.

Re:Correllation is Not Causation

[rcamans]

You are correct. Birth month does not CAUSE health and education risks. But birth month does indicate an increased probability of health and educational problems. Let's see. that means that you cannot apply the generalization to specific people. But let's try. I was born in November (of poor parents). I have health problems. I am also highly educated and upper middle class,as I work as a senior engineer. My wife was born in spring, of poor parents. A few minor health problems, educational problems. My son was born in fall (of well-off parents), extremely excellent health, small educational problems (fixed). My daughter was born in spring. Excellent health, no educational problems. So does the generalization work for e? Not only do I not see that, but working for me is a meaningless statement. All It means is that the medical people and insurance companies may spend more paperwork overall on fall kids, and the feds may get less taxes overall from fall kids.

Correlation does not show cause and effect. It only shows that the two items are related (a causative link), and one may be a partial cause of the other, or there may be at least one common partial cause of both.

What is not shown at all is the causes for either greater health issues or educational issues. Far more detailed work would be required to get to that point.

Perhaps babies need the extra sunlight of the summer in their early months for better health and fewer educational problems later in life? Or just the vitamins that sunlight generates in them?

Re:Correllation is Not Causation

[timeOday]

So you are telling me that Saturn is somehow connected to the S&P 500?

Actually that one wouldn't be nearly as interesting if you re-computed it with updated numbers, since the S&P 500 tanked. You don't have to cherrypick the winter birth data that way; the correlation is very robust. And now they are figuring out why.

Re:Correllation is Not Causation

[skine]

I disagree my kind sir.

I didn't RTFA in question, but I know that my facts are right beyond a doubt.

Re:Correllation is Not Causation

[proxima]

Correlation is NOT Causation. Correlation proves nothing. Saturn is correlated to the S&P 500 with r=0.88. And don't think there a correlation so profoundly stupid that someone won't publish a "scientific" paper on it.

This correlation is entirely due to both series being upward-trending. Either the author (presumably you, from your nick) knew this or was being sloppy. To be fair, sloppy statistics are misleading, but this extends to more than just correlations.

Helpfully, the author provided the data. Applying the simplest linear detrending, I obtain a correlation of 0.0371, rather than the 0.8778 without detrending.

This same point was made more clearly by the correlation of pirates and global warming; there, it's obvious that the mistake is to look at general trending variables and infer some sort of correlation, because countless variables trend over time and you'll get a significant positive or negative correlation. With this example, it's more misleading because it might be possible that the deviations from these upward trends actually are correlated, based on the picture. But they aren't.

Uuum, are they dumb or what?

[Hurricane78]

I'm no (so-called) "expert", but what strikes you as the most outstanding difference between summer and winter? Hmm? Hmm?

S-freakin-UN. SUN! And as it is already shown, that lack of sunlight causes depression, imagine what it is for a baby, to in the first months of their life think that there is no other thing than darkness and coldness!
I mean, it boggles my mind, how that can be not totally obvious to someone...
I am a fall child, and my first month of life consisted of laying mostly inside, and seeing hailstorms and rain outside. And I always had a special relationship to that weather.

If you know how the brain works, by forming very global and basic patterns at first, and then making finer and finer details in it, then this is the base imprint of your character right there.
Oh, and besides: There's your explanation for the patterns of similarity in humans, based on their time of birth (part of what is called "zodiac signs"/"astrology").

Hmm I wonder...

[Anonymous Coward]

I was born during a winter month in the Northern Hemisphere but now I live in New Zealand... does that mean these "strikes" against me no longer apply?

They should check the Southern Hemisphere data too

[Ross Finlayson]

It would be interesting to see the corresponding data from developed Southern Hemisphere nations (e.g., Australia, New Zealand, Argentina). Are underachieving children in such countries more likely to have been born in June-August (the cold months) or in January-March (the same as in the US)? And how does the education level of the mothers correlate with this?

blagh

[MrHanky]

I'll tell you what: There's a 1:1 correlation between a comment header stating that correlation is not causation and the comment below it being absolute drivel. Yet, there's no claim that such a header causes the comment to be stupid. You know why? It's because to everyone who doesn't make those idiotic comments, the difference between correlation and causation is fucking obvious. Now fuck off and grow a brain, and stop believing that repeating "wisdoms" from the lowest class of Slashdot morons is in any way insightful.

"Nearly 100%" of births

[Anonymous Coward]

The study uses "nearly 100%" of the births in the U.S. for the time period from CDC records, so while the selection may not be perfect (e.g. there may be some extremely small % of births that were not recorded), nearly 100% is measured.

Re:Correllation is Not Causation

[ceoyoyo]

If you read the paper (which takes about three seconds to find on Google), or the article, or even the summary (!), this story is about a pair of researchers who have found a connection between birth month and socioeconomic background of the mother that explains much of the observed connection between birth month and outcome. No (well, technically very little) musing about sunlight or vitamins needed.

It's also right around Senior Prom....

[brunes69]

.... just FYI

Re:let me explain this to you.

[Anonymous Coward]

Nice advertisement. Nobody cares about your anecdotal life.
Ohhhh... you've never had sex before have you? Ha ha ha ha ha ha ha ha...
All the girls think you're "nice," but would never, ever let you touch them. Why is that? They are fucking, you know that right? It feels sooooo good, way better than your hand. It really is a wonderful, unique experience. Too bad you've been excluded from it. You're going to spend the rest of your days regretting all the missed opportunities, wondering what was wrong with you, why didn't they like you, etc. Bottom line is- you don't get to have sex. Sorry!
Enjoy your shitty life, you asexual fuck-up overweight man-child!

I definitely earned less

[Anonymous Coward]

Compared to other kids who have their birthdays away from the holiday months... I usually get one present "combined" for XMas and my Birthday.

Re:Correllation is Not Causation

[ObsessiveMathsFreak]

Thank's for that. I have been wondering exactly how signals are in fact decorrelated. I knew that any two continuous signals must be correlated almost everywhere along their runs, but I wasn't sure how to account for this. I'll be sure to add your comment to the page.

Basically my point with the Saturn/S&P correlation was to show just how spurious a correlation study can be. I think it's worth noting that along with the Hill's criteria, most studies probably don't even bother to perform such checks as linear detrending, etc. A lot of what we see in correlation studies is just as spurious and incomplete as that example. By the way, it turns out I was not the first to stumble across this result, showing that again, there is not correlation so silly that someone will not accept it as proof of causation.

Basically, my core point is that a lot of correlation studies lack rigour of the most basic kind, and are just a number thrown out to make a point. The more I learn about the subject, the more convinced of this point I become.

Re:Correllation is Not Causation

[proxima]

Basically, my core point is that a lot of correlation studies lack rigour of the most basic kind, and are just a number thrown out to make a point. The more I learn about the subject, the more convinced of this point I become.

The real issue here is the lack of rigour, not the statistical tool in particular. I find it ironic that you dislike studies with correlations because sloppy studies often (mis)use correlations.

As with any statistical tools, you need to know what they mean and how (and when) to apply them. Correlations are a very useful tool, especially early in a particular research agenda.

Nonsense

[Corson]

This is absolute nonsense. I know many people who are Capricorns (born in December-January) and who are over-achievers.

Re: Nonsense

[soliptic]

This is absolute nonsense. I know many people who are Capricorns (born in December-January) and who are over-achievers.

Yes, because of course when scientists talk about statistical trends observed within 52 million cases, the fact that you know "many" people who defy the trend of course sufficient basis to dismiss the trend as statistically nonexistent and "absolute nonsense". Congratulations of your robust grasp of the relationship between large data sets, statistical significance and confidence, and the anecdotal relevance of a couple of your mates' star signs.

Re: Nonsense

[Corson]

I was trying to put an ironic spin on the whole story when I mentioned the Zodiac. Isn't that what astrologers say? That you destiny is controlled by your date of birth? On a more scientific note -- that article reads: "We document large seasonal changes in the characteristics of women giving birth throughout the year in the United States." Therefore, the conclusions apply, at best, to the population in that particular country/population. And it seems to me very much like science with a political edge.

teachers have babies in the summer

[ArgumentBoy]

I've spent my whole life in academia and until recent liberalizations of child care policies, I noticed that inevitably women faculty had their babies in the summer. Male teachers have that preference too (my own kids are June and April). I imagine that this was true of K-12 teachers, too. A few percent of women who carefully planned for summer births would be enough to move the numbers. And notice that employed/well educated women having summer babies would cause an apparent disadvantage to winter babies (i.e., rarely born of those women). I like the prom/graduation pregnancy explanation, too. Together these might well handle the whole observed phenomena.

Re:Correllation is Not Causation

[BZ]

> then declaring that people born in winter suffer from a lifelong plight, without
> even bothering to provide genuine reasoning

You seem to be somewhat confused. There's varied observational data, predating this study, showing that children born in winter tend to do (very slightly) worse in life. The question hast been _why_ this is the case.

This study points out that:

1) Children born in winter are (very slightly) more likely to be born to teen mothers.
2) There are existing studies comparing children born to teen mothers to other children,
        and those born to teen mothers tend to do slightly worse. Again, without saying
        _why_, but that's the observation. Various hypotheses could be advanced to explain
        it, of course.
3) One could assume (and this is an assumption) that children born to teen mothers are,
        on average, the same year round and assume the same for children born to non-teen
        mothers. One could then see, under this assumption, how much of the difference
        observed above in item 1 is accounted for by the known observed differences of item 2.

Depending on how well the numbers one gets from the procedure in item 3 match those observed in item 1, and on how confident one feels in the assumptions made in item 3, one could make the argument that one has discovered something about the causes of item 1: namely that they are likely to be the same as the causes of item 2, whatever those are. Note that the claim is not that one has established causation of anything. However one has advanced a hypothesis: if the causative mechanisms of item 2 are discovered and can be controlled for when studying the data for item 1, one could see whether the effect of item 1 remains.

Re:let me explain this to you.

[Anonymous Coward]

Or, like my wife and I, both above 130 IQ, just had a lot of sex during spring break.

Did you smell her panties too :)~

what did they look like

September

[Anonymous Coward]

I find most people I ask about DOB are born in September. Guess what takes place 9 months before September?

Jesus

[Anonymous Coward]

Jesus was born in December, motherfuckers.

BULLSHIT

[Anonymous Coward]

I was technically born in fall, but I was born during a winter month, and I did exceptionally well. This is bullshit.

Who got paid for this? They need to have their money taken away.

MOD PARENT UP!

[AttilaSz]

Man, that's a brilliant positive feedback loop!

Re:Jumps out - of your pants

[Anonymous Coward]

"The percentage of children born to unwed mothers, teenage mothers and mothers who hadn't completed high school kept peaking in January every year"

What this really shows us is if you want to nail a slutty chick try hitting on her in May.
Perhaps this is the secret to getting nerds laid - besides large sums of cash

Very usefull info!

Finally, an explanation

[alcmaeon]

of why so many stupid, unsuccessful people like Edison, Washington, Darwin, Lincoln, Frederick Douglas, Ayn Rand, and Steve Jobs were born in the winter.

Re:Correllation is Not Causation

[JimFive]

b) the baby's increased risk of health and education problems causes him or her to be born in the winter (clearly ridiculous)

I don't think that this possibility can be dismissed as easily as you would like. It is entirely possible that congenital problems with the fetus, in combination with the stress that cold weather puts on the mother, leads to an increase in premature births in the winter months. This effect, if it exists, would push a certain number of births that would have occurred in the spring, back into the winter months and those births that moved would be precisely those at risk for health problems.

N.B. I'm not actually saying this is true, I'm just pointing out that you shouldn't be so quick to discard the "clearly ridiculous" option out of hand.
--
JimFive

Re:Correllation is Not Causation

[ceoyoyo]

Er, no, your proposal falls under (a): baby's birth month affects later outcome. That is, because of seasonal conditions during the baby's gestation the baby has problems later.

Option (b) requires that because the baby has poorer health and education later in life, it is born during the winter. That is, it requires the future (poor outcome) to influence the past (conditions of conception and birth).

Re:Correllation is Not Causation

[JimFive]

Actually, I'm positing a third factor (a congenital defect) that causes both an increase in the likelihood of a winter birth and an increase in health problems later in life.
--
JimFive

"atleast?"

[pestie]

I wish there was an error bar I could put around the non-word "atleast" every time someone uses it...

Re:Correllation is Not Causation

[ceoyoyo]

Ah, okay, option (c) then: a third factor that influences both birth month and outcome.

Option (b) still requires time travel.