How Common is Your Birthday? This Visualization Might Surprise You

By Matt Stiles | | Topics: Demographics, News

It’s baby season in America, with September the busiest month for births on average in the last two decades. So it seemed like the right time to remix this blog’s most-popular post: How Common is Your Birthday?

That old heatmap, which highlighted specific dates for popularity, has been viewed more than 500,000 times here and published across the web. But it was flawed, namely that it used ordinal data (birthday ranks by date) rather than continuous data (actual births counts by date). This graphic finally addresses that problem:

This new version of the heatmap, which is interactive on larger screens, uses births by day from 1994 to 2014, thanks for the fine folks at FiveThirtyEight, whose reporters posted the tables on Github for an unrelated project. It lists the average number of births by day, the rank (number one is most common) and an estimated — if slightly irresponsible — conception date.

Some highlights:

  • Holidays: People generally seem to have time for baby making during their time off. Several of the most-common birth dates, in September, correspond with average conception periods around Christmas. Sept. 9 is most-common in this dataset, though other days in that month are close. Sept. 19 is second. Following a customary gestation period, many of these babies would, in theory, have been conceived on Dec. 17 and 27, respectively.
  • Choice: Clearly, some people choose when they have their children. While they’re making babies during the holidays, many people aren’t really having them then. The least-common birthdays in this dataset were Christmas Eve, Christmas and New Year’s Day. Dates around Thanksgiving aren’t as common. July 4 is also at the bottom of the list. Conversely, Valentine’s Day ranks relatively high, as you can see in the graphic, as are the days just before a new tax year begins.
  • Skewed: There are some fun patterns in this data, but the difference between your birthday — unless it’s on a truly rare day — isn’t that much different than a top date in September. There a left-tailed skewness to the data, which ranges from 6,500 births per day to more than 12,000. The median number of births per day, though, is around 11,000. The most-common day had 12,300 births, on average. More on the data distribution soon.

You can have a look at the data for yourself in this table:

Chances are you came here looking for the legacy birthday graphic. If you must, find it here, along with a related post about the flawed methodology.

Meanwhile, check out your birthday, share your thoughts in the comments — and tell the Internet to do the same.

Credits: Thanks, Cynthia Brewer, for your wonderful color guide. After trying several of your sample palettes, I couldn’t decide. So my three-year-old daughter — who celebrates a birthday Sept. 22 — chose this one. It looked the most like a birthday cake, she said. Also, thanks to publicdomainpictures.net for the cake image.

Follow me on Twitter @stiles, and keep up with The Daily Viz posts on Facebook.

22 thoughts on “How Common is Your Birthday? This Visualization Might Surprise You

  1. This is accurate. I was unfortunate enough to have been told the actual day of my conception, and the chart says I should have been conceived just the day before. Given all the variables in play, one day off is incredibly accurate.

  2. The data is still somewhat biased because of the irregular sample size. In order to have completely unbiased data you need to have a number of samples such that each day falls on a particular day of the week the same number of times as any other day.

    By looking at the graph there are clear spikes on April 4, 11, and 18. We know this is a cause of this bias because:

    For example, the day April 11th, from 1994-2014, falls on:
    Monday 3 times (1994, 2005, 2011)
    Tuesday 3 times (1995, 2000, 2006)
    Wednesday 3 times (2001, 2007, 2012)
    Thursday 3 times (1996, 2002, 2013)
    Friday 3 times (1997, 2003, 2008, 2014)
    Saturday 2 times (1998, 2009)
    Sunday 3 times (1999, 2004, 2010)

    It has more occurrences on a Friday and less occurrences on a Saturday compared to the other days of the week. Because of other studies showing that weekend birthdays are less common than weekday ones, we can conclude that the lowered frequency of weekend dates for the days April 4, 11, and 18 are causing a spike.

    In order to have unbiased data you need a sample size of a 28-year span (e.g: 1989-2016) in which each day of the year falls on each day of the week exactly 4 times, expect Feb. 29 in which it falls on each day of the week exactly once.

  3. My birthday is the rarest by far. Interesting seeing the slump around Christmas. I wonder if Christmas babies were as rare in the past as they are now?

  4. I’m not sure how February 29 is not last. Is that controlled for somewhere to normalize that date against the others? Far fewer people are born on February 29 than on any other date, so I presume some kind of statistical adjustment has been made.

    I always tell people that I almost never meet anyone who shares my birthday, November 23. Sure enough, it’s 359th!

    1. That’s a good question, and I honestly can’t remember whether I thought about it then. I should either 1) exclude it or 2) do a weighted average. Thanks for prompting me to check it out.

  5. I also notice the 13th of every month is low. I always thought your birthday was just whatever day it was but it seems there is way more control than I thought. I’d like to see what the numbers for 9/11 look like after 2001. I’ll bet money that day drops way off.

  6. I’m surprised there is no mention of planned c-section, (and also to a lesser extent, inductions) being less likely to be planned for public holidays, weekends. Some women offered dates for planned c-section may be less likely to choose the 13th of the month, or Friday the 13th.

    I also thought it was widely assumed that the increase of births in August September time is at least partially due to the ‘Christmas Spirit’ – Spending more time with loved ones, or Christmas Parties or/and drinking more alcohol causing ‘accidents’ with contraception or simply not using it.

    As for the increase in births starts in June July time. I wonder if there is a corresponding increase in prescriptions of antibiotics in the Autumn and start of Winter? Some pregnancies occur as the mother’s contraceptive pill has been made ineffective by antibiotics, either because the couple didn’t know they needed to use additional contraception or because they forgot to.

  7. It would be interesting to see the graphic split for planned c-sections, and another for all other births (vaginal delivery, emergency c-section, any induction).

    Something else that might be interesting to know – is there a time of year where it is more likely for IVF (embryos to be transferred back) and similar other fertility treatment to be carried out? The resulting pregnancies have a higher chance of twins, and (in the UK at least) a higher chance of the mother being under consultant care rather than midwife/GP team. Being under consultant care it is more likely babies will be born by c-section.

  8. I was born on April 1, but it was in 1993, so if they could calculate the birthdays from 1990-2000, that would be great

  9. Yes, this is surprising, because with my friends group we hate november 20-25 because 12 of them (of 28) born on those dates. Five on 23.

Leave a Reply

Your email address will not be published. Required fields are marked *