Tag Archives: names

Science finds tiny things nowadays (Malia edition)

We have to get used to living in a world where science — even social science — can detect really small things. Understanding how important really small things are, and how to interpret them, is harder nowadays than just finding them.

Remember when Hanna Rosin wrote this?

One of the great crime stories of the last twenty years is the dramatic decline of sexual assault. Rates are so low in parts of the country — for white women especially — that criminologists can’t plot the numbers on a chart.

Besides being wrong about rape (it has declined a lot, but it’s still high compared with most countries), this was a funny statement about science (I’ve heard we can even plot negative numbers now!). But the point is we have problems understanding, and communicating about, small things.

So, back to names.

In 2009, the peak year for the name Malia in the U.S., 1,681 girls were given that name, according to the Social Security Administration, or .041% of the 4.14 million children born that year (there are no male Malias in the SSA’s public database, meaning they have never recorded more than 4 in one year). That year, 7.5% of women ages 18-44 had a baby. If my arithmetic is right, say you know 100 women ages 18-44, and each of them knows 100 others (and there is no overlap in your network). That would mean there is a 30% chance one of your 10,000 friends of a friend had a baby girl and named her Malia in 2009. But probably there is a lot of overlap; if your friend-of-friend network is only 1,000 women 18-44 then that chance would fall to 3%.

Here is the trend in girls named Malia, relative to the total number of girls born, from 1960 to 2016:

names.xlsx

To make it easier to see the Malias, here is the same chart with the y-axis on a log scale.

names.xlsx

This shows that Malia has been on a long upward trend, from less than 50 per year in the 1960s to more than 1,000 per year now. And it also shows a pronounced spike in 2009, the year Malia peaked .041%. In that year, the number of people naming daughters Malia jumped 75% before declining over the next three years to resume it’s previous trend. Here is the detail on the figure, just showing the Malia in 2005-2016:

names.xlsx

What happened there? We can’t know for sure. Even if you asked everyone why they named their kid what they did, I don’t know what answers you would get. But from what we know about naming patterns, and their responsiveness to names in the news (positive or negative), it’s very likely that the bump in 2009 resulted from the high profile of Barack Obama and his daughter Malia, who was 11 when Obama was elected.

What does a causal statement like that that really mean? In 2009, it looks to me like about 828 more people named their daughters Malia than would have otherwise, taking into account the upward trend before 2008. Here’s the actual trend, with a simulated trend showing no Obama effect:

names.xlsx

Of course, Obama’s election changed the world forever, which may explain why the upward trend for Malia accelerated again after 2013. But in this simple simulation, which brings the “no Obama” trend back into line with the actual trend in 2014, there were 1,275 more Malias born than there would have been without the Obama election. This implies that over the years 2008-2013, the Obama election increased the probability of someone naming their daughter Malia by .00011, or .011%.

That is a very small effect. I think it’s real, and very interesting. But what does it mean for anything else in the world? This is not a question of statistical significance, although those tools can help. (These names aren’t a probability sample, it’s a list of all names given.) So this is a question for interpreting research findings now that we have these incredibly powerful tools, and very big data to analyze with them. The number alone doesn’t tell the story.

1 Comment

Filed under Me @ work

Donald is not the biggest loser (among winning and losing names)

From 2015 to 2016 there was a 10% drop in U.S. boys given the name Donald at birth, from 690 to 621, plunging the name from 900th to 986th in the overall rankings. Here is the trend in Donalds born from 1880 to 2016, shown on a log scale, from the Social Security names database.

donald-name-trend

That 2016 drop is relatively big in percentage terms, but it’s been dropping an average of 6% per year since 1957 (it dropped 26% in the 8 years after the introduction of Donald Duck in 1934). I really wish it was a popular name so we could more easily see if the rise of Donald Trump is a factor in this. With so few new Donalds, and the name already trending downward, there’s no way to tell if Trump fanatics may be counterbalancing regular people turned off to the name.

Stability over change

How big is a fall of 69 births, which seems so trivial in relation to the 3.9 million children born last year? Among names with more than 5 births in each year, only 499 fell more, compared with 26,052 that fell less or rose. So Donald is definitely a loser.

But I am always amazed at how little change there is in most names from year to year. It sounds obvious to describe a trend as rising or falling, but names are scarily regular in their annual changes given that the statistics from one year to the next reflect independent decisions by separate people who overwhelmingly don’t know each other.

Here is away of visualizing the change in the number of babies given each name, from 2015 to 2016. There is one dot for each name. Those below the diagonal had a decrease in births, those above had an increase; the closer to the line the less change there was. (To adjust for the 1% drop in total births, these are shown as births per 1,000 total born.)

2015-2016 count change

No name had a change of more than 1700 births this year (Logan dropped 1697, a drop of 13%; Adeline increased 1700, or 71%). There just isn’t much movement. I find that remarkable. (Among top names, James stands out this year: 14,773 born in 2015, rising by 3 to 14,776 in 2016.)

Here’s a look at the top right corner of that figure, just showing names with 3 per 1,000 or more births in either 2015 or 2016:

2015-2016 count change 3per1000

Note that most of these top names became less popular in 2016 (below the diagonal). That fits the long-term trend, well known by now, for names to become less popular over time, which means name diversity is increasing. I described that in the history chapter of my textbook, The Family; and going back to this old blog post from 2011. (This great piece by Tristan Bridges explores why there is more diversity among female names, as you can see by the fact that they are outnumbered among the top names shown here.)

Anyway, since I did it, here are the top 20 winners and losers, in numerical terms, in 2016. Wow, look at that catastrophic 21% drop in girls given the name Alexa (thanks, Amazon). I don’t know what’s up with Brandon and Blake. Your explanations will be as good as mine for these.

namewinners

namelosers

For the whole series of name posts on this blog, follow the names tag, including a bunch on the name Mary


Here’s the Stata code I used (not including the long-term Donald trend), including the figure and tables. The dataset is in a zip file at Social Security, here. There is a separate file for each year. The code below runs on the two latest files: yob2015.txt and yob2016.txt.

clear
import delimited [path]\yob2016.txt
sort v2 v1
rename v3 count16
save "[path]\n16.dta", replace
clear
import delimited [path]\yob2015.txt
sort v2 v1
rename v3 count15
merge 1:1 v2 v1 using [path]\n16.dta
drop _merge

gen pctchg = 100*(count16-count15)/count15
drop if pctchg==. /* drops cases that don't appear in both years (5+ names) */

gen countchg = count16-count15
rename v2 sex
rename v1 name

gsort -count16
gen rank16 = _n

gsort -count15
gen rank15 = _n

gsort -countchg
gen riserank=_n

gsort countchg
gen fallrank=_n

gen rankchg = rank15-rank16

format pctchg %9.1f 
format count15 count16 countchg %15.0fc

gen prop15 = (count15/3978497)*1000 /* these are births per 1000, based on NCHS birth report for 15 & 16 */
gen prop16 = (count16/3941109)*1000

*winners table
sort riserank
list sex name count15 count16 countchg pctchg rank15 rank16 rankchg in 1/20, sep(0)

*losers table
sort fallrank
list sex name count15 count16 countchg pctchg rank15 rank16 rankchg in 1/20, sep(0)

*figure for all names
twoway (scatter prop16 prop15 if sex=="M", mc(blue) m(Oh) mlw(vvthin)) (scatter prop16 prop15 if sex=="F" , m(Oh) mc(pink) mlw(vvthin))

*figure for top names
twoway (scatter prop16 prop15 if sex=="M" & (prop15>=3 | prop16>=3), ml(name) ms(i) mlabp(0)) (scatter prop16 prop15 if sex=="F" & (prop15>=3 | prop16>=3), ml(name) ms(i) mlabp(0))

1 Comment

Filed under Me @ work

Mary lives? (You’re welcome edition)

Things are looking up since last I wrote about the fate of the name Mary. It’s too early to tell, but it’s just possible things are beginning to turn around.

In 2014, Mary held steady at the 120th most-popular girls name in the U.S., as recorded by the Social Security Administration. That’s two years she’s been above her worst-ever showing of 123rd in 2012. Here’s the trend, starting with her last year at Number One, 1961:

Mary2014

You may recall that I first breathlessly reported Mary’s fall in 2009 when she dropped out of the top 100 U.S. girls names for the first time in recorded history (presumably ever). At the time I also speculated that she might have a chance of bouncing back, especially given the historical precedent of Emma, currently enjoying rare return to Number One:

Mary2014

Note that Emma had about 10 years of uncertainty before definitively tracking upward. With just a couple years of stall it’s way too early to write Mary’s triumph narrative, but you have to weight her odds of recovery higher than average because of the whole Christianity thing — especially with Catholics, who are holding their own amidst the general crisis of Christ.

names.xlsx

What is the basis for a potential Mary revival? We have seen before that popular events can hurt a name (Forrest, Monica, Ellen), or help a name (Maggie, Brandy, Angie, and my favorite, Rhiannon). In this case historians my someday date the resugence of Mary to the appearance in 2012 — her worst year ever — of my essay in The Atlantic with the memorable illustration:

atlanticmary

Call it a classic bottoming out.

1 Comment

Filed under In the news

Mary free fall continues

For the past two years I’ve been tracking the fate of the name Mary as given to girls born in the U.S., spurred by the observation that Mary was no longer in the top 100 names, after an unparalleled run at #1 that lasted for all but six years of recorded history.

It’s a difficult job, but it’s got to be done. (Follow the Mary tag for historical background, examples, and more figures.)

So: 2012 was another rough year, according to data from the Social Security Administration.

There was another 5% drop in the number of Marys born, and as a result Mary fell a record 11 ranks, from 112 to 123. The 2,535 Marys born in 2012 were a mere 0.13% of the 1.9 million girls recorded born. Once upon a time, in 1880, more than 7% of all girls born were named Mary.

mary2012rankPart of the point of the Mary name project is to show the predictability of (much) human behavior, even including rare events, such as naming girls Mary. I have a simple model which predicts that the number of girls named Mary will decline at a rate equal to the average decline over the previous five years — what falls continues to fall. This year, out of 1.9 million girls born and 2,535 named Mary, my model was off by a microscopic 79 girls. The model predicted the number of Marys to within 3.2%.

Take that, indeterminancy, free will, or postmodernism (your pick).

P.S. Despite the continued free fall of Mary, my model missed low, incidentally — or, Mary-naming Americans beat expectations by 3.2%. Since my Mary post on the Atlantic site last December was shared more than 5,000 times, unless proven otherwise we have to assume the 79-girl bump was a Mary-name-blog effect. (File under reflexivity.)

ADDENDUM: MARIA

By request, here is the trend for Maria. It is not the case that Maria is replacing Mary — both are trouble. In fact, with Maria falling steeply in the last decade, she has also dropped out of the top 100 for the first time since 1943!

maria-ranks

Speculation: As Marias of Latina origin grow more common, perhaps their increase is not enough to compensate for the resulting perception among non-Latinas that Maria is a Spanish name. (Remember, this is just girls born in the U.S.)

10 Comments

Filed under Uncategorized

Big name drops in the news

A few more suggestions have come in for cultural events upending name trends.

The story behind these name shocks seem self-apparent. Both Monica and Ellen were mildly popular, though trending downward, before their names were associated with sex in a bad way, apparently leading to their collapse. Forrest was enjoying a run-up in popularity, tragically cut short by the movie Forrest Gump.

nineties-names

My series of posts on names is here.

The names database is here.

7 Comments

Filed under Uncategorized

Hit song, hit name

In the comments of my Atlantic post about the name Mary, and in a number of personal emails, people have suggested pop culture triggers for changes in name direction – like the turnaround in Emma and its eventual peak at #1 in 2002. In that year, Emma jumped 9 places, from 13th to 4th among U.S. girls. There are other examples, but I prefer a few that date back to a golden era of pop songs with women’s names in the titles.

Some hits in the 1960s did not produce name bounces (Sharona, Sherry). But in the 1970s three #1 songs produced name bounces: Maggie (from “Maggie May,” by Rod Stewart in 1971), Brandy (Looking Glass, 1972), and Angie (Rolling Stones, 1973). I added a personal favorite, Rhiannon (Fleetwood Mac, 1975).

song-names

Each of these tells a good story.

  • Rhiannon and Brandy both debuted in the top 1,000 names the year they made the charts, with Brandy making a credible run for the top before collapsing in the 1990s. Rhiannon hung on as a niche name until the 2000s.
  • Maggie changed direction the year of the Rod Stewart hit, reversing a long slide.
  • Angie, which gained popularity in the 1950s (Angie Dickinson?) seemed to get a boost from the Stones song, but it was not long lasting (it is a breakup song, after all). I don’t know why Angie came back in the 1990s (1994 movie with Geena Davis?).

My series of posts on names is here.

The names database is here.

11 Comments

Filed under Me @ work

Why Don’t Parents Name Their Daughters Mary Anymore?

Originally published on TheAtlantic.com.

Understanding the rapid decline of what was once America’s most popular name

virgin mary tattoo

Each year I mark the continued calamitous decline of Mary as a girls’ name in the United States. Not to be over-dramatic, but in the recorded history of names, nothing this catastrophic has ever happened before. Mary was the most common name given to girls every year from the beginning of record-keeping (at least back to 1800) through 1961 (except for a six-year dip to #2, behind Linda).

And then it happened. In 2011, according to the latest report from the Social Security Administration (SSA), Mary fell three more places, to 112th. In absolute numbers, the number of girls given the name Mary at birth has fallen 94 percent since 1961. Here is the trend:

cohen_mary.png

The modernization theory of name trends, advanced most famously by the sociologist Stanley Lieberson, sees the rise of individualism in modern naming practices. “As the role of the extended family, religious rules, and other institutional pressures declines,” he wrote, “choices are increasingly free to be matters of taste.” Mary—both a traditional American name and a symbol religious Christianity—embodies this trend.

The other day I did a search of newspaper birth announcements for the name “Mary,” and turned up a lot of grandmothers named Mary. Here, from a recent day’s birth announcement page from Rock Hill, South Carolina, are three Marys in the grandparent generation, in three different families announcing the births of Mazie, Ja’Nae, and Asani. I diagrammed the family names:

cohen_mary2.png

Other generational sequences in recent announcements also mirror the history of common names: Mary–Jennifer–Madelyn; Mary–Ashley–Emily; Mary–Cora–Elizabeth.

In the tradition of treating statistical trends as horse races, I imagine that there is one person named Mary, who is constantly falling behind: first behind Linda, then Lisa, Jennifer, Ashley, Jessica, and so on, all the way to Isabella and now Sophia.

But that’s not how it happens—it just looks that way because of the amazing regularity in human behavior, which produces an orderly succession of names. Incredibly, out of 1.7 million girls’ names recorded by the SSA in 2011, I was able to predict to within 87 how many would be named Mary. By simply taking the number born in 2010 and subtracting the 5-year average decline, I predicted 2,584 would be born; the actual number was 2,671 (an error of 3.3 percent).

Somehow, out of the millions of individual decisions parents make, they produce steady trends like this. (If you’re as amazed as I am, consider a career in sociology! If not, please bear with me.)

So what does the Mary trend mean? First, it’s the growing cultural value of individuality, which leads to increasing diversity. People value names that are uncommon. When Mary last held the number-one spot, in 1961, there were 47,655 girls given that name. Now, out of about the same number of total births, the number-one name (Sophia) was given only 21,695 times. Conformity to tradition has been replaced by conformity to individuality. Being number one for so long ruined Mary for this era.

Second, America’s Christian family standard-bearers are not standing up for Mary anymore. It’s not just that there may be fewer devout Christians, it’s that even they don’t want to sacrifice individuality for a (sorry, it’s not my opinion) boring name like Mary. In 2011 there were more than twice as many Nevaehs (“Heaven” spelled backwards) born as there were Marys. (If there is anything more specific going on within Christianity, please fill me in.)

I’m not here to give advice to people who want to bring back the “traditional family.” But if I were I would recommend putting your names where your tradition is—and producing some more Marys.

There are precedents for bringing names back. My simple linear prediction method fails once in a while, when a name’s trend turns around. The greatest example is probably Emma. Emma was at number three when the SSA records begin, in 1880. She fell almost down to #500 by the 1970s. But after a decade of uncertainty she began a fantastic run, finally reaching number one in 2008.

cohen_mary3.png

I don’t know (yet) what makes a name turn around like that. Why Emma and not Mildred or Bertha, both former top-10s who fell into oblivion? But if any name has a chance for a similar resurgence, it might be Mary, at least as long as Christianity keeps hanging around.

10 Comments

Filed under Me @ work