Tag: Data Analysis

Who cares about overpopulation? Smart people and atheists

By Razib Khan | October 2, 2012 7:53 pm

If you had the sense that Paul Ehrlich and Garrett Hardin are very much figures of the 1970s nexus of environmentalism and population control, it seems you are right. According to Google Ngrams mention of these topics has been declining since peaking during the oil crisis, in the afterglow of the influence of the late 1960s counter-culture. The general social survey has a variable, POPGRWTH, which asks:

And please circle one number for each of these statements to show how much you agree or disagree with it. The earth cannot continue to support population growth at its present rate.

The question was asked in the year 2000 and 2010. Demographic breakdowns below for the pooled responses….

Read More

MORE ABOUT: Data Analysis

Catching up to Argentina

By Razib Khan | January 23, 2012 2:19 am

You may not have noticed, but Google has been spiffing up its Data Explorer. Poking around you see nice illustrations of phenomena which you otherwise may just read about. For example, Argentina has been one of the classic illustrations in economic history of stagnation. To a great extent it peaked around 1900, and development has been erratic since then. This is clear when you see how much its neighbors and other Latin American nations have caught up:

This bar graph illustrates it better:

Read More

MORE ABOUT: Data Analysis

Men trust people more than women do

By Razib Khan | May 9, 2011 1:58 am

One of the weird things I randomly noticed when querying the “TRUST” variable in the GSS was that men were more trusting than women. I didn’t think much of that, but take a look at this logistic regression:

Trust in people, sample from after the year 2000
Logistic regression
Variable All Non-Hispanic white
B Probability B Probability
SEX -0.340 0.000 -0.485 0.000
WORDSUM 0.176 0.000 0.201 0.000
DEGREE 0.343 0.000 0.274 0.000
COHORT -0.018 0.000 -0.013 0.001
SEI 0.002 0.393 0.003 0.394
POLVIEWS -0.105 0.011 -0.121 0.018
PARTYID 0.073 0.019 0.011 0.777
GOD -0.035 0.438 0.015 0.765
ATTEND 0.023 0.261 0.038 0.105
Pseduo R-square = 0.096 Pseduo R-square = 0.083

The outcomes are “can trust people = 1” and “cannot trust people = 0.” I removed “depends” (which is never more than 5-10% in a class anyway). For sex 1 = male and 2 = female, so you can immediately see that being a woman will reduce the odds of being trusting. WORDSUM, vocabulary score, and educational attainment go in the direction you’d expect. Interestingly controlling for education doesn’t remove the vocabulary effect. COHORT is the year you were born. Lower values indicate older individuals in the data set. Younger people are less trusting, so this makes sense. To my surprise on the individual level religion doesn’t seem that important.

Since the sample sizes for sex are huge I thought I’d compare sex differences in trust over the years by demographic variable.

Read More

CATEGORIZED UNDER: Data Analysis, GSS, Social Science
MORE ABOUT: Data Analysis, GSS, Trust

The Republican fluency with science

By Razib Khan | March 28, 2011 12:44 am

The Audacious Epigone has a post up, Republicans are more scientifically literate than Democrats or independents are, where he reviews pro vs. anti-science attitude by party in the General Social Survey. He concludes that in fact Republicans are more scientifically literate across the issues than Democrats. Jason Malloy saw this trend four years ago in the GSS, and to some extent so have I. One point to keep in mind is that a few specific politicized scientific issues are very much the outliers in exhibiting tight partisan valences in opinion.

So another question: are conservatives more scientifically literate than liberals? If scientific literacy correlates with being Republican, and being Republican correlates with being conservative, shouldn’t scientific literacy correlate with being conservative? Not necessarily. Such correlations are not transitive. Generally what I’ve seen in the survey data is that Republicans tend to be more pro-science than conservatives. I think part of it is the voting by economic position which has become less stark in our culture, but still remains a force. In any case, my table to accompany AE’s is below. I used his variables:


For political ideology, it’s pretty simple: POLVIEWS(r: 1-3 “Liberal” ; 4 “Moderate”; 5-7 “Conservative”)

The percentages given are the correct science answer, or the more pro-science answer. If you want to know my criteria for that, don’t ask, just go to the General Social Survey website and enter in the variables above, and you’ll see the results and understand clearly how I categorized things.

Read More

MORE ABOUT: Data Analysis, GSS

Is Christine O'Donnell a kook because she's a Creationist?

By Razib Khan | September 26, 2010 12:01 pm

Christine O’Donnell has said a lot of kooky things. Right now people are focusing on her Creationism. Though I’m obviously not a Creationist I think mocking someone for this belief in a political context is somewhat strange: the survey literature is pretty robust that Americans are split down the middle on opinions about evolution. More specifically most of the polling shows that around ~50% of Americans tend to reject the validity of evolutionary theory when asked. This is what I like to call a broad but shallow belief; for the vast majority of Americans attitudes about evolution are really just cultural markers, not stances of deep feeling or impact. One point of evidence for this conjecture is that polling on evolution is easy to massage through framing. Another is that Republican candidates for the presidency do not invariably hew to a Creationist line despite the likelihood that the majority of primary voters are Creationist. Politicians react to incentives, and my own hunch is that there isn’t a strong push from the Christian Right on evolution as there is on abortion or gay marriage.

I’ve posted plenty on how Creationists are more female, less intelligent, more conservative, more likely to be ethnic minorities, less educated, etc. Here I want to put the spotlight parameters which might shed some light on the O’Donnell race. Is her kooky opinion on evolution a particular liability in Mid-Atlantic Delaware? Are Creationists less likely to vote? And what are the regional breakdowns which might explain the bi-coastal shock and amusement at O’Donnell’s opinions?

Read More

CATEGORIZED UNDER: Creationism, Data Analysis, GSS

People with heterodox opinions are just confused

By Razib Khan | September 13, 2010 5:11 am

I was having a touch of insomnia a few days ago, and wasn’t alert enough to do anything intellectually challenging, so I decided to poke around the General Social Survey. I found an interesting variable, POSTLIFE, which asks people if they believed in life after death. I decided to cross-check that against those who were atheists and agnostics, and specifically look at the distribution of WORDSUM scores of those who did, and didn’t, believe in life after death. My hunch before I checked was this: those who believe in life after death despite not believing in the existence of God are going to be less intelligent than those who don’t.

My reasoning was that it was close to philosophically incoherent to reject supernatural agents, but then accept some post-material existence. I know that this is actually not necessarily philosophically incoherent. Asian religious traditions have long had a strand which accepts both immortality of consciousness as well as agnosticism or atheism in relation to supernatural agents, gods. And, there are some secular Western philosophers who make an analytic case for the afterlife despite their lack of belief in the supernatural. But most people are not deeply involved in the philosophical literature on the afterlife, or, Jains.* Rather, I think those who are atheists or agnostics, and, who accept an afterlife, are relying on intuition and not following through deductively on the inferences from their avowed axioms. In other words, I believed they’d be likely to be less intelligent, and habitually make less use of analytic modes of thinking. To double-check on the thesis that the less intelligent are more likely to hold inconsistent views I also looked at self-identified liberals, conservatives, Democrats and Republicans, on specific policy issues and their relationship to intelligence.

Before we get to the tables, some methodology. I used WORDSUM, which has a 0.7 correlation with IQ. I recoded WORDSUM so that in terms of intelligence you have the following classes:

Low (0-3) – 11% of the sample, 6% non-Hispanic whites
Below Average (4-5) – 27%, 25% non-Hispanic whites
Average (6) – 22%, 21% non-Hispanic whites
Above Average (7-8) – 27%, 34% non-Hispanic whites
High (9-10), 13%, 15% non-Hispanic whites

For the religion related questions I used the whole GSS data set. For the politics related questions I limited to non-Hispanic whites, which also constrains the data set to the 2000s (politics tends to be racially polarized more than religion, so I wanted to remove the racial variable). The rows in each column below add up to 100%, so what you’re seeing are the intelligence distributions within each class. So, if you see 22% in the Low category, that means that the class has twice as many people in that category than the general population. Please note that ~20% of the population rejects an afterlife, a higher proportion than those who are irreligious, or atheists or agnostics. A substantial number of religious people don’t believe in an afterlife, just as a substantial proportion of atheists and agnostics do.

Read More

CATEGORIZED UNDER: Culture, Data Analysis, GSS
MORE ABOUT: Data Analysis, GSS

Fundamentalists are not as "intelligent"

By Razib Khan | September 9, 2010 3:09 am

Inherit_the_wind_trailer_(1)_Spencer_Tracy_Fredric_MarchYesterday I pointed to an OKCupid study on personals ads on their network. I didn’t highlight the fact that the analysis of the ads seem to suggest that secular people have more sophisticated prose, and that of those who claim a religious affiliation the less strongly committed tend to be more sophisticated. The blog Political Math is skeptical of the findings, and points to some evidence that the analytic technique might be biased against the type of things religious people are prone to say.

That’s fine, but there are two major issues with this sort of objection. First, there are clear confounds here which could be responsible for this correlation. Both blacks and Latinos seem less sophisticated, while Asians and Indians seem more so. The overwhelming majority of blacks are Protestants, and a majority of Latinos are Roman Catholic, and both of these religious groups rank low on sophistication according to OKCupid. Conversely, Hindus and Buddhists rank high. Though most Asian Americans are not Buddhists, around half of American Buddhists are Asian American. And the vast majority of American Hindus are Indian. As I noted yesterday the results correlate rather well with educational attainment by group in the USA.

Read More

MORE ABOUT: Data Analysis, GSS

Fertility by non-Hispanic white ethnic group, etc.

By Razib Khan | September 2, 2010 11:14 am

In my post on American fertility rates by racial group Mike Keesey asks: ‘It’d also be interesting to see what’s going on within “non-Hispanic whites”.’ One can explore this question in the GSS. Let’s look at ancestry group (e.g., German, French, etc.), religion, belief in God, political ideology, intelligence and education, for non-Hispanic whites. The data is limited to the 2000s, and I also constrained to those age 45 and up. Then I looked at the “CHILDS” variable, which asks the respondent how many children they have. Taking the mean of this value gives us a sense of the rank order in fertility. Note that this is not total fertility rate. That should be clear from the values being well above 2 in most cases. Additionally, I recombined some categories, so that “British” is the amalgamation of English, Scottish and Welsh ancestry. The “Irish” class almost certainly includes both Scotch-Irish (doing the regional and religious breakdown this seems obvious), and the Irish without modifiers. For intelligence I used “WORDSUM”. The variables I input into the GSS can be found at the bottom of the post so you can replicate.

Read More


Discover's Newsletter

Sign up to get the latest science news delivered weekly right to your inbox!

Gene Expression

This blog is about evolution, genetics, genomics and their interstices. Please beware that comments are aggressively moderated. Uncivil or churlish comments will likely get you banned immediately, so make any contribution count!

See More


RSS Razib’s Pinboard

Edifying books

Collapse bottom bar