Do rich people like bad data tweets about poor people? (Bins, slopes, and graphs edition)

Almost 2,000 people retweeted this from Brad Wilcox the other day.

bradpoorstv

Brad shared the graph from Charles Lehman (who noticed later that he had mislabeled the x-axis, but that’s not the point). First, as far as I can tell the values are wrong. I don’t know how they did it, but when I look at the 2016-2018 General Social Survey, I get 4.3 average hours of TV for people in the poorest families, and 1.9 hours for the richest. They report higher highs (looks like 5.3) and lower lows (looks like 1.5). More seriously, I have to object to drawing what purports to be a regression line as if those are evenly-spaced income categories, which makes it look much more linear than it is.

I fixed those errors — the correct values, and the correct spacing on the x-axis — then added some confidence intervals, and what I get is probably not worth thousands of self-congratulatory woots, although of course rich people do watch less TV. Here is my figure, with their line (drawn in by hand) for comparison:

tvfaminc-bradcharles

Charles and Brad’s post got a lot of love from conservatives, I believe, because it confirmed their assumptions about self-destructive behavior among poor people. That is, here is more evidence that poor people have bad habits and it’s just dragging them down. But there are reasons this particular graph worked so well. First, the steep slope, which partly results from getting the data wrong. And second, the tight fit of the regression line. That’s why Brad said, “Whoa.” So, good tweet — bad science. (Surprise.) Here are some critiques.

First, this is the wrong survey to use. Since 1975, GSS has been asking people, “On the average day, about how many hours do you personally watch television?” It’s great to have a continuous series on this, but it’s not a good way to measure time use because people are bad at estimating these things. Also, GSS is not a great survey for measuring income. And it’s a pretty small sample. So if those are the two variables you’re interested in, you should use the American Time Use Survey (available from IPUMS), in which respondents are drawn from the much larger Current Population Survey samples, and asked to fill out a time diary. On the other hand, GSS would be good for analyzing, for example, whether people who believe the Bible is the “the actual word of God and is to be taken literally, word for word” watch TV more than those who believe it is “an ancient book of fables, legends, history, and moral precepts recorded by men” (Yes, they do, about an hour more.) Or looking at all the other social variables GSS is good for.

On the substantive issue, Gray Kimbrough pointed out that the connection between family income and TV time may be spurious, and is certainly confounded with hours spent at work. When I made a simple regression model of TV time with family income, hours worked, age, sex, race/ethnicity, education, and marital status (which again, should be done better with ATUS), I did find that both hours worked and family income had big effects. Here they are from that model, as predicted values using average marginal effects.

tv work faminc

The banal observation that people who spend more time working spend less time watching TV probably wouldn’t carry the punch. Anyway, neither resolves the question of cause and effect.

Fits and slopes

On the issue of the presentation of slopes, there’s a good lesson here. Data presentation involves trading detail for clarity. And statistics have both have a descriptive and analytical purpose. Sometimes we use statistics to present information in simplified form, which allows better comprehension. We also use statistics to discover relationships we couldn’t otherwise — such as multivariate relationships that you can’t discern visually. The analyst and communicator has to choose wisely what to present. A good propagandist knows what to manipulate for political effect (a bad one just tweets out crap until they get lucky).

Here’s a much less click-worthy presentation of the relationship between family income and TV time. Here I truncate the y-axis at 12 hours (cutting off 1% of the sample), translate the binned income categories into dollar values at the middle of each category, and then jitter the scatterplot so you can see how many points are piled up in each spot. The fitted line is Stata’s median spline, with 9 bands specified (so it’s the median hours at the median income in 9 locations on the x-axis). I guess this means that, at the median, rich people in America watch about an hour of TV per day less than poor people, and the action is mostly under $50,000 per year. Woot.

gss tv income

Finally, a word about binning and the presentation of data (something I’ve written about before, here and here). We make continuous data into categories all the time, starting from measurement. We usually measure age in years, for example, although we could measure it in seconds or decades. Then we use statistics to simplify information further, for example by reporting averages. In the visual presentation of data, there is a particular problem with using averages or data bins to show relationships — you can show slopes that way nicely, but you run the risk of making relationships look more closely correlated than they are. This happens in the public presentation of data when analysts are showing something of their work product — such as a scatterplot with a fitted line — to demonstrate the veracity of their findings. When they bin the data first, this can be very misleading.

Here’s an example. I took about 1000 men from the GSS, and compared their age and income. Between the ages of 25 and 59, older men have higher average incomes, but the fit is curved with a peak around 45. Here is the relationship, again using jittering to show all the individuals, with a linear regression line. The correlation is .23

c1That might be nice to look at but it’s hard to see the underlying relationship. It’s hard to even see how the fitted line relates to the data. So you might reduce it by showing the average income at each age. By pulling the points together vertically into average bins, this shows the relationship much more clearly. However, it also makes the relationship look much stronger. The correlation in this figure is .65. Now the reader might think, “Whoa.”

c2Note this didn’t change the slope much (it still runs from about $30k to $60k), it just put all the dots closer to the line. Finally, here it is pulling the averages together in horizontal bins, grouping the ages in fives (25-29, 30-34 … 55-59). The correlation shown here is .97.

c3

If you’re like me, this is when you figured out that reducing this to two dots would produce a correlation of 1.0 (as long as the dots aren’t exactly level).

To make good data presentation tradeoffs requires experimentation and careful exposition. And, of course, transparency. My code for this post is available on the Open Science Framework here (you gotta get the GSS data first).

Leave a comment

Filed under Uncategorized

The changing household age range, U.S. 1900-2017

One way to understand daily interaction, and intergenerational resource exchange, is just to look at the structure of households. This doesn’t tell you everything that goes on in households, but it gives some strong clues. And we can measure it going back more than a century, thanks to IPUMS.org’s collection of Census microdata.

In 1900, the most common situation for an American was to live in a household where the age difference between the oldest and youngest person was about 38 years. Now the most common situation is an age range of 0 — either living alone, or with someone of the exact same age. And there are a lot more people living in households with only similar-aged adults, with age ranges of less than 10.

In between 1900 and 2017, life expectancy increased, the age at first birth increased, and the tendency to live in multigenerational households fell and then rose again. So the household structure story is complicated, and this is just one perspective.

But it’s one indicator of how life has changed. Line up your household from youngest to oldest, look to your left and look to your right — how far can you see?

household age range

 

Data and Stata code (for all decades 1900-2000, then individual years to 2017) are available on the Open Science Framework, here.

1 Comment

Filed under Me @ work

Review of Relational Inequalities: An Organizational Approach, with audio

cover of Relational Inequalities

I had the privilege of sitting on an author-meets-critics panel for the the book Relational Inequalities: An Organizational Approach, by Donald Tomaskovic-Devey and Dustin Avent-Holt, at the Eastern Sociological Society meetings this weekend. The panel was organized by Steven Vallas, and included Adia Harvey Wingfield. Because two other panelists canceled, I had a lot of time and ended up speaking for 25 minutes. We had a great discussion after the formal remarks, which only deepened my appreciation for the book. I recorded my remarks. Here is audio, with 4 minutes of ums and dead ends edited out:

 

And here is a lightly edited transcript:

I want to thank Steve, as well as Don and Dustin, for organizing and writing, respectively. It’s really been a pleasure. In the same way that once upon a time I used to run faster when I played competitive sports, because someone was yelling at me to run faster, reading a book knowing that I’m going to offer commentary on it to an audience of people whose opinions I respect makes me try harder and pay more attention, and focus more on it. So it’s a privilege to have this be one part of my job. I don’t normally read books all the way through and think about them carefully and sketch out my thoughts, so I really learned a lot doing that.

In the process, you know, it’s 10 months ago whenever we got this invitation, and then finally the book comes, and then I skim through it, then I put it down, and then you know it comes down to the last couple of days in my room reading the book carefully, and it’s been great. And fresh. Very fresh, right through breakfast.

I want to start by talking about my own work. Just kidding.

I have an outline. I start with praise. And then questions about what’s the relationship between organizations and inequality, as far as creating, reflecting, reproducing inequality; discussion of the role of education, as one of the things that it is external to organizations; and then a discussion of inequality within and between organizations, and where this fits in with the path of social change.

Praise

It’s a really really good book. And I look forward to putting it on our comprehensive exam reading list for the inequality reading group, I think it teaches this stuff really well – the literature on organizations and inequality. A great audience for it is people who are designing research projects having to do with inequality, and what is the role of organizations going to be in the work.

One of the things that’s really important, and you have to get to it right away, is the disconnect between the method of most research which is individual observation, and mostly surveys, and the theorized mechanisms about how inequality works, which are largely relational. And so we look at individuals and we say, oh look people with more education have more income, or we say we have racial inequality and we have immigration, and we have all these measures which are usually at the individual level, and then the mechanisms which we think are producing these are schools and segregation and discrimination, and things that are all interactional, or relational, between people within and around organizations. And so that’s just a sociological take that is very important here.

I love the mezo/contextual way of thinking in the analysis, between the individual and the country or the state or something like that, and at the organizational level that complexity and variation – how there is so much difference in the patterns of inequality within organizations. Yes, men make more money than women, but how that works is very different across different organizations and places and times, and the dispersion is different, and the patterns of dispersion change, and all that variation gives us leverage to understand how inequality works, but also where policy and law can intervene. Because if you have a range of practices, and you can see the consequences of the range of practices, that’s where you get something like the idea for a policy – we should do more of this and less of this, and so on. So that variation is key, and having it at the organizational level is important.

They set out a really useful research agenda. They talk a lot about workplace ethnographies and surveys, and various ways that organizational dynamics of inequality have been studied, and the research agenda that emerges has to do with comparative organizational studies, with attention to the role of external influences on organizations. So the gold standard is sort of multi-organizational research where the context is carefully considered between the different organizations and the workings of the relations within the organizations, and hopefully between them.

The relational framework they have here is sort of Charles Tilly’s Durable Inequality plus Cecilia Ridgeway – that’s my background reading on this, which is kind of thin, admittedly. And so it’s categories and the durableness of them within institutions and organizations, and putting people into cognitive categories and how that represents the integration of social structure into personality and interaction and so on. So that’s sort of the frame, which I think is really useful.

And then the moral framework they have is very clear, at the end; and the policies they give us to talk about, both “what about worker cooperatives,” and, “what about a universal basic income” – sort of state level and organizational level policies that address the variety of problems and inequalities that we have.

Organizations and inequality

A key question, and a motivating question for them, is what is the role of organizations in the wider system of inequality – that is, are they creating inequality, are they reflecting inequality that comes to them from the outside of the organization, what’s their role in the reproduction of inequality. And so you have the organization – it’s a workplace, which is mostly what they talk about – and there are things coming at it from the outside: cognitive categories and hierarchies, status between groups, privilege groups, esteem groups, minority groups that are less privileged and so on. And then there’s a law and regulatory policy environment that they’re working within, there are market conditions that they’re working within, and then there are the workers that are coming to them with their range of unequal skills and education, their health, their social capital, their histories of incarceration – everything that workers bring to the organization. So you could ignore organizations and say, look we have all this inequality out there, outside the organization, and the organization is basically just sort of applying formulas to this: “Well, men are privileged over women, so we pay them a little bit more, we discriminate against people with criminal records, if you don’t have the skills to do the job you’re out, if you’re health is not good, if you have children, if you can’t show up…” You could think of organizations as just sort of administering the system of inequality, the structures of inequality that they’re in, or you can think of them as implementing or enacting the inequality. So until the organization gets its hands on it, all that inequality is sort of not really operationalized, it’s not really functioning – the status inequality between men and women doesn’t really happen until somebody decides to pay the man more than the woman. That’s sort of their view, not necessarily – [Don: “I agree”] – not necessarily true, but that’s the question, are organizations doing that, or they just sort of receiving that.

And the authors point out – I’ll give you a little taste of this (p. 14): “Most inequalities are generated through the relationships in and around workplaces.” That’s a very strong statement, although “most” is a little bit vague, it’s 51% to 99%. That clearly gives you a strong reason to focus on workplaces, and it’s somewhat debatable.

And they point out in a footnote (p. 58): “Obviously, power can be exercised as violence in addition to discursive claims-making [so it’s not just people debating over rewards within organizations]. Strong-armed robbery and colonial conquest are examples of violent exploitation, genocide, ethnic cleansing, political suppression via arrest of social movements’ claims of dignity and access are the violent faces of closure.” Well, none of that stuff is happening within workplaces. So if you think colonial conquest, genocide, ethnic cleansing, and political suppression are important parts of inequality, and we know that those aren’t happening within workplaces, you know the field is generating a lot of inequality outside workplaces. You have to weigh that up against their, “most of inequality comes from within workplaces,” And to their credit, it’s an empirical question, which they note. It’s hard to quantify and it’s kind of pointless to quantify but the question is where should our focus be?

By the time they’re to their conclusion, they write, “We are not arguing that only organizations matter for inequality,” ok, they are definitely not arguing that – but if you have to say that, it’s obviously relevant, so that’s a question. It really is an organizations manifesto, the book, the importance of organizations, and it makes the case very strongly. It’s extremely useful and valuable and informative. And the fact that they make the claims really strongly helps motivate it and make it clear. And whether I want to argue about whether it’s 51% or 80% of inequality that comes from workplaces, for most uses of it that’s not the point.

Related to the question of what organizations do – whether they’re creating or reflecting – is inequality, unequal what? What are we talking about? Most obviously money, some people have more money than others. But especially when you’re talking about intersectional questions, are race and class and gender just three different ways of deciding who’s going to have how much money? No, it’s much more than money, it’s cultural in terms of who’s valued and esteemed, and who gets to set the discourse, and it’s status in terms of whose opinions get respected, and voice within organizations, and it’s also geographic with segregation, and so on. And so they talk a lot about “organizational resources” being what’s at issue. Whenever I teach inequality I push sociology grad students to get beyond thinking of all these status inequalities as being different ways of deciding how much money we get. And especially, what is the content of the inequality. Unequal amounts of what are we actually talking about? And that’s why I think the feminist discourse over sexuality is so important. Because control over sexuality is sort of orthogonal to the amount of money that you have – it’s obviously related, but it’s a different quality. So that stuff is really important and there’s a lot of food for thought on that here.

I mentioned genocide and ethnic cleansing, and there are other things which are happening outside organizations that are relevant. Things that happen outside workplaces, that may be in other organizations: welfare, taxation, the education system, residential segregation, incarceration – these are all things that are packaging inequality that arrive at the doorstep of the workplace. So I’ll give two possible policy ideas that are totally outside workplaces: if we had a 90% marginal tax rate on upper incomes, you might say, “who cares about inequality within organizations?” You get rich, and the government takes your money and gives it to poorer people. And so that lowers the stakes. And partly they focus on organizations because in the United States we don’t do that. And so that question of how much empirically are organizations creating of the system of inequality, is partly that number is higher because we don’t have that kind of society. So it’s not a statement about how inequality will always forever work, it’s really driven by the reality that we have now. And the other policy challenge to thinking organizationally is reparations. If the government stepped in and had a big reparations program and orientation, that is totally outside of individual workplaces, what would that do? So those are just things to think about.

Education

Their attitude toward education is interesting. And it’s – what do you call that when it’s not traditional, it’s not “heretic,” it’s very challenging. [The word I was looking for is “heterodox.”] They basically treat education as a proxy for claims-making resources. So the amount of education people have, when they get to the workplace, allows them to essentially bargain for or demand more or less money. Which, if you’ve ever had surgery, from a doctor, you want your surgeon to have gone to medical school. [Don: “You want your surgeon to be a good surgeon.”] Right, exactly. In our system, the proxy for that is that they’ve gone to medical school, and the board certifying and all that. So their issue is how much doctors are paid, not who gets to be a doctor. They’re not talking about inequality in the education system, all the things that create the unequal distribution of medical education.

Consider this also: there are limits to the organizational variation in this. There are no organizations in the United States that let people perform surgery without medical degrees. So that’s something very strong coming from the external reality that workplaces have to deal with. They can only hire people with medical degrees to do surgery, and surgery is very valued, it commands a lot of money in the market. So if they’re going to say “wages and jobs are organizational phenomena,” which they say, and education is this way of making claims on those things, then it’s interesting to push them on this issue of who gets to have the education. They say, sort of grudgingly in my opinion, yes, sometimes educational credentialing has to do with the skills required to do the job, but basically it’s about how much money you can extract from your employer. That’s why I focus on surgery, because lots of other education is just a cruder proxy for particular skills and whatnot.

They review literature on how factories work in Mexico and the U.S., including within the same multinational company, and the gender difference between maquiladoras. But if you think globally, the difference between a doctor in the U.S. and a factory worker in Mexico, and the vast inequality in resources they command, is not determined by the practices of their organizations, right? And an interesting thing about doctors in particular, is we pay a fortune in this country because the government (because of doctors) doesn’t let foreign doctors come practice here. Our doctors get paid ridiculously high amounts (Dean Baker, the economist, has written very compellingly about this). If we allowed foreign doctors to come here, foreign doctors would make a lot more money than they’re making, our doctors would make less money, and we would all pay less for equally good healthcare. So that’s a state policy, and not something that the hospitals can address.

While we’re thinking about the external factors, and I’m pushing them on this, they do a little review of Devah Pager’s work, “the mark of a criminal record” – employers don’t hire people with criminal records – so is that a problem of employer practices or is that a problem of mass incarceration and the distribution of criminal records? It’s both, but you couldn’t understand it by only studying the practices of employers, because that’s not a fixed quantity of a randomly distributed stigma.

So when you get to the intersectional stuff – consider race, class, and gender in our system of inequality. They point out gender and race integration in education “led to a weakening of gender and race based closure” (and that shows up in Don and Kevin’s previous book, and that’s reviewed here). So there’s less job segregation by race and gender than there used to be, and less exclusion, “while leaving unchallenged, or perhaps even strengthening, education based closure.” Well, by one way of thinking, of course, if race and gender are becoming less determinative of workplace outcomes, and education is becoming more determinative, that’s literally the goal of rational modern society, is to stop with the ascriptive criteria, and start using rational educational criteria, for skills and productivity. So they’re all up in arms about this, but it’s interesting to say, well, wait a second isn’t that kind of the point, like meritocracy. “There is an intersectional reality weakening closure on the basis of race and gender even as closure rules around education remain hegemonic.” So it would be worth it to explain, and I guess they do explain, why they think this is not the definition of progress. I’m being provocative. It’s not like education is fairly distributed, so it’s still all about ascriptive inequalities through the education system.

Between and within organizations

So what about inequality between and within organizations. And here it’s interesting because the world has changed while they were writing this book. In making their case for why organizations are so important, they write, “We are born and die in organizations.” OK, I like that, they obviously think it’s very important. “We spend a great deal of our lives working alongside others in organizations” – and then listen to this list of sort of other things: “We go to one organization to be educated (schools), to another to get income (workplaces), which we then spend in another (stores), in order to bring food and clothing to a fourth (households).” So they’re telling your other organizational fields. What’s interesting is that in schools, stores, and households, there’s more inequality between than within organizations. And so they’re very focused on workplaces, where probably you find more inequality within the organizations. They’re interested in those dynamics: What causes inequality within organizations, why do CEOs make so much, why is there gender segregation in the division of labor, and so on. Interestingly, and the trend over time is probably toward more inequality between. And if you think about families, in the old days, if you had an employed man and three children and a woman who had no income, then you have a tremendous amount of inequality within that organization, within that family. Nowadays if you have two children and the parents both have jobs, you have fewer people with no income and more people with income, and so there’s less within-household inequality, and that’s a trend over time.

In their second-to-last chapter they have a very good discussion about how this is also happening with firms and workplaces in the U.S. So if General Motors outsources their custodial service (I’m just making this up), some big company outsources lower status, or higher status, work, there’s a firm that is less hierarchical somewhere, that’s just all custodians. And there’s a firm that’s just all engineers. And General Motors is like bundling those services. So the inequality is increasingly between organizations there, rather than within. So instead of hierarchy within Amazon being from Bezos to the drivers, the drivers are all contracted, and so on. And Uber, and self-employment, and the gig economy, and all that stuff is sort of like if every Uber driver is an organization the way Uber thinks they are, then the inequality is all between organizations.

And so that’s the direction of social change, and it’s a challenge for their theory. If their theory is focused on inequality within firms, and organizations, then what’s happening in world, and how does their theory address this? And they say, “even if there were no internal inequalities within firms, there still might be considerable inequality between firms, as a function of firm resource inequality.” So they’re sort of already projecting to a world where every company had no inequality within it. We’re not there at all, but their answer to that is maybe more aspirational than empirical, and I think it’s debatable, and it’s worth debating, it’s: “The processes governing inequality between organizations is fundamentally the same as that governing inequality within organizations: relational claims-making, exploitation, and social closure.” OK, that’s a very strong statement. It says we’ve sketched out this whole theory about how inequality works within organizations, we see that the world is moving toward inequality between organizations, and we’re going to apply the concepts that we’ve developed to this new reality also. And that is a challenge for future work in this area. And so I’m not expecting them to have established this empirically before they do it, but that’s their case.

That’s one of the many examples of the great research agenda that comes out of this really interesting and important work. And with that I close. Thank you.

Leave a comment

Filed under Research reports

Let’s raise the legal age of marriage in Maryland

Today I sent the following letter to the Maryland House Judiciary Committee, which is scheduled to hold a hearing on these bills tomorrow. Under current law in Maryland, marriage is permitted as young as age 15 with parental consent and evidence of pregnancy or childbirth, and age 16-17 with one or the other, and these exceptions are granted by county clerks rather than judges. By my calculations, from 2008 to 2017, based on the American Community Survey, the annual marriage rate for girls ages 15-16 was 5 per 1000 in Maryland, behind only Hawaii, Nevada, and West Virginia. HB 855 would raise the age at marriage to 18, while HB 1147 would establish an emancipated minor status, requiring review by a judge, under which 17-year-olds could marry. For more on the effort to end child marriage in the U.S., visit the Tahirih Justice Center site.


March 6, 2019

To the House Judiciary Committee:

I write in support of Maryland House Bill 855, concerning age requirements for marriage; and House Bill 1147, concerning the emancipation of minors.

My relevant background

  • I am a Professor of Sociology, and family demographer, at the University of Maryland, College Park, where I have been on the faculty since 2012. I also earned my PhD at the University of Maryland, College Park, in 1999, and I live in Silver Spring.
  • I have written two books and many peer-reviewed articles on family sociology, including on topics related to marriage and divorce, family structure, gender inequality, health and disability, infant mortality, adoption, race and ethnicity, and the division of labor.
  • I have served as a consultant to the U.S. Census Bureau on the measurement of family structure, and testified before Congress on gender discrimination.

My support of the bills

In general, the rise of the age at marriage and childbearing in U.S. have been positive developments for women and children, allowing mothers to devote more years of early adulthood to education and career development, which is beneficial to both adults and their children.

Very early marriage in particular is detrimental to women’s opportunity to finish high school. More urgently, research and service work shows that very early marriage is usually unwanted, coerced, or forced. Very young women should not be expected to protect themselves legally or socially from such impositions, which are usually from older men and dominant family members. Very early marriage often follows statutory rape or other sexual assault, compounding rather than mitigating the harms of these crimes against children. Rather than protect a young woman, very early marriage instead provides protection from scrutiny for her abuser(s), and makes state intervention on her behalf all the more difficult to accomplish in the following years. The privacy and discretion we bestow upon families has benefits, of course, but it also makes the family a dangerous place for the victims of abuse.

Research, including my own, unequivocally shows that very early marriage leads to the highest rates of divorce. I have written several papers on divorce rates in the United States (see references). For illustration, here I used the same method of analysis, and present only the relationship between age at marriage and incidence of divorce. As you can see from the figure, divorce rates are highest by far – estimated at 2.5% per year – for women who married before age 18. This is about twice as high as divorce rates for those who marry in their 30s, for example. (These estimates hold constant other factors; data and code are available here.) The evidence is very strong.

predicted odds of divorce by aam

I only reluctantly support increasing state restrictions on women’s freedom with regard to family choices, but in the case of marriage before adulthood I see the restriction as a protection from the exploitative behavior of others, rather than an imposition on young women’s rights.

At present in Maryland, exceptions allowing marriage before age 18 – based on pregnancy and/or parental consent – are granted without adequate legal review. Together, HB 855 and HB 1147 would set the minimum age at marriage in Maryland to 18, with an exception only for court emancipated minors of age 17. This would improve the state’s protection of young women from unwanted, coerced, forced, or ill-advised marriages without unduly restricting the freedom to marry for younger women (age 17), who may be emancipated by a court after a direct application and careful review of circumstances.

I urge your support for these bills. I would be happy to provide further information or testimony at your request.

Sincerely,

Philip N. Cohen

References

Cohen, Philip N. 2015. “Recession and Divorce in the United States, 2008-2011. Population Research and Policy Review 33(5):615-628.

Cohen, Philip N. 2018. “The Coming Divorce Decline.” SocArXiv. November 14. https://osf.io/preprints/socarxiv/h2sk6. To be presented at the Population Association of America meetings, 2019.

5 Comments

Filed under In the news, Politics

Googling “Lost in Translation” versus “nativity scenes” across state political identities

Gallup’s tracking poll asks people “whether they describe their political views as liberal, moderate or conservative.” They released state rates for these identities yesterday. It’s useful for people who need current data on political characteristics of states. This is their map:

vbxijunpyuoyr2wdggsc3g

I put the conservative-liberal gap, and the liberal-conservative gap, into Google Correlate, to see what searches are correlated with each index. The results are quite similar to the ones I got in September 2016 when I did this with 538’s predicted Clinton versus Trump margins. (Google doesn’t say exactly what period the searches cover.)

Google gives you the top 100 most-correlated searches with each index you upload. These are the ones correlated with the conservative-liberal difference, with my coding categories:

conlib

Here are the liberal-conservative correlated terms:

libcon

Draw your own conclusions. Fun coding exercise. Remember these aren’t the most common searches in conservative or liberal states, they’re the most correlated, meaning the most common ones in liberal states that are also uncommon in conservatives states, and vice versa.

Google outputs the numbers as z-scores, each search term having a mean of 0 and standard deviation of 1. And once you get them for the two different sets of correlations you can merge them together to see, for example, the negative correlation between searches for Lost in Translation (liberal) and nativity scenes (conservative):

litnat

Or vegetarian food and cook steaks:

vegcook

I did look at the “moderate” rates, and they yielded a bland list with nothing remarkable — things like “men’s volleyball shoes” and “print screen.” Also, Google couldn’t find a lot of search terms highly correlated with the “moderate” prevalence, the top correlation was only .73, versus .90-.92 for the liberals and conservatives. The average state is 36% moderate but the category seems to mean little.

Anyway, I love this stuff. You can see a whole series of these under the Google tag.

2 Comments

Filed under Politics

White children are 2.7-times more likely than Black children to live with a parent who has a PhD

For a reflection Amy Harmon was working on, a followup to her article on the experience of Black mathematicians in American academia, I took a shot at the question: How many children have parents with PhDs?

The result was the highlighted passage (17 words and a link!) in her piece:

[all the racial biases that contribute to Black underrepresentation include] the well-documented racial disparities in public-school resources, the selection of students for gifted programs — and the fact that having a parent with a Ph.D. is helpful to getting one in math, while black children are less than half as likely as white children to live with such a parent.

To get there: I used data from the U.S. Census Bureau via IPUMS.org: The 1990 5% Public Use Microdata Sample (decennial census); and the 2000, 2010, and 2017 American Community Surveys.

I coded race/ethnicity into four mutually-exclusive categories: Single-race White, Black, and Asian/Pacific Islander (API); and Hispanic (including those of any race). I dropped from the analysis non-Hispanic children with multiple races reported, and American Indian / Alaska Natives (for whom about 0.5 percent lived with a PhD parent in 2017).

IPUMS made a tool that attaches values of parents’ variables to children with whom they share a household. I used that to calculate the highest level of education of each child’s coresident parents. In the Census data, children may have up to two parents present (which may be of the same sex in 2010 and 2017). Children living with no parent in the household were not included.

This let me calculate the percentage of children living (at the moment of the survey) with one or more parents who had a PhD. For each of the four groups the percentage of children living with a parent who has a PhD roughly doubled between 1990 and 2017. API children had the highest chance of living with a PhD parent, reaching 6.8 percent in 2017. The percentages for the other groups were: Whites, 2.7 percent; Blacks, 1.0 percent; and Hispanics, 0.7 percent:

pe1

The 2.7% for White children, versus, 1.0% for Black children, is the basis for her statement above.

Details (including the whole parents’ education distribution), data, codebook, and code, are available on the Open Science Framework at: https://osf.io/ry3zt/ under CC-BY 4.0 license.

Math bias

Both of Amy’s pieces are important reading for academics in many disciplines, including sociology, to reflect on the experience of Black colleagues in the environments we inherit and reproduce.

With regard to math, Amy points out that Black exclusion is not just about denying economic opportunity, it’s also about denying the public the benefits of all the lost Black math talents — and about denying Black potential mathematicians the joy and satisfaction of a passion for math realized.

As Daniel Zaharopol, the director of a program for mathematically talented low-income middle-school students, put it when I interviewed him for a 2017 article: “Math is beautiful, and being a part of that should not be limited to just some people.”

And Amy makes a good case that math bias and its outcomes contribute directly to racism much more broadly:

Some misguided people claim that there are not many black research mathematicians because African-Americans are not as intelligent as other races. These people, whom I have reported on for other stories in recent months, almost invariably use mathematical accomplishment as their yardstick for intelligence. They note that no individuals of African descent have won the Fields Medal, math’s equivalent of the Nobel Prize. They lack any genetic evidence to explain the gap in average I.Q. scores between white and black Americans that they cite as the basis of their belief, or reason to think that a genetic trait would be impervious to social or educational intervention, or that high I.Q. is key to math ability, which Timothy Gowers, a 1998 Fields medalist, has attributed largely to “the capacity to become obsessed with a math problem.”

But I have been reporting on these topics for several years, and I am acutely aware that math prowess factors heavily into the popular conception of intelligence. There’s a vicious cycle at work: The lack of African-American representation in math can end up feeding pernicious biases, which in turn add to the many obstacles mathematically talented minorities face. Which was one more reason it seemed especially important to hold up to the light all the racial biases that contribute to that underrepresentation.

Leave a comment

Filed under Me @ work