# 2011 reader survey preliminary results

By Razib Khan | July 15, 2011 11:57 pm

My sample size for the reader survey is now ~200. I’m aiming for ~500. If you are a regular reader of this weblog, please consider filling out the survey. The software is telling me that the average reader is taking about ~10 minutes. All questions are optional, so you can quickly skip over confusing ones or those which you don’t want to divulge.

The results so far are here. At least for the questions which weren’t open ended. I added a lot of open ended numeric questions so that I could run some scatterplots and more natural statistics (i.e., I don’t have to convert categorical responses into numerics and so forth).

To give a taste for the kind of stuff I’m running on the nerd-heavy data set I thought I would explore how # of sexual partners relates to age and IQ. First, let me admit that I assume that the IQ distribution of the readership here is somewhat artificially shifted upward (to the right of the distribution). Those with higher IQs are more likely to know their IQs. And whether unconsciously or consciously individuals will almost certainly self-report results which are drawn from the higher range of their results distribution. Additionally, since the readers are ~85% male there’s an expectation that there’ll be a slight padding of the # of sexual partners. But since I’m really curious about correlations I’ll assume that these biases are independent across the two result sets.

Below are some simple summary statistics, density distribution plots and scatterplots. Also some information on the virgins for those who are curious.

Age: median: 34, mean: 37, standard deviation: 13.

# of sexual partners: median: 4, mean: 8, standard deviation: 21.

IQ: median: 135, mean: 133, standard deviation: 11.

The people with 200 sexual partners are ridiculous, so I yanked those few outliers out of the data set (I’m not judging, I’m just saying that the promiscuous readers tend to make the charts hard to read).

# of sexual partners & IQ: correlation ~0.03

# of sexual partners & Age: correlation ~0.37

I was curious if there was a relationship between IQ and # of sexual partners controlling for age, so I ran a partial correlation. There wasn’t. The correlation was -0.03 with a p-value of 0.71. So amongst the readers of this weblog there isn’t a relationship between # of sexual partners and intelligence (sorry Geoffrey Miller!). Of course the distribution of IQs is not natural. The lowest reported values were 100, which is the American population average. The median of the distribution would come in at exactly the 99th percentile. This is almost certainly too high, but I doubt the median is much lower than the 90th percentile.

Finally, the virgins. Here are there ages & IQs:

 Age & IQ of virgins Age IQ 69 130 38 130 37 100 30 137 29 135 28 156 25 125 25 145 25 140 24 135 23 131 21 130 20 160 20 110 20 135 19 142 18 140

Finally, if there are specific statistical questions you want explored, ask here. I can’t guarantee I’ll look at it, but I might.

CATEGORIZED UNDER: Blog
• Matthew Carroll-Schmidt

“The owner of this survey [2462467] has not made the Results Public. ”

I can’t believe you didn’t graph BMI/Sex Partners.

• Anthony

I can’t tell you how much I dislike seeing BMI on such surveys. It’s an entirely subjective reponse based on the fact that by such measurements I’m considered to be extremely overweight when the reality is that I work out. I know Razib will be aware of inherent problems associated with literal interpretations of BMI but still, it’s a personal irritant.

• http://blogs.scientificamerican.com/crude-matter/ EcoPhysioMichelle

I don’t think BMI would be a very good predictor of sexual partners because BMI can fluctuate drastically in a short period of time, and the BMI that a person is now is probably not likely the same BMI that they were when they were accumulating sexual partners, especially if they’re married/committed.

Personal anecdatum: I had a BMI of almost 30 in college when I was accumulating sexual partners. I’m almost a 19 BMI now. Fat me got WAY more strange ass than skinny me. I am tipping the hot end of my personal attractiveness scale right now; I look the best I ever have and probably the best I ever will, but I’m not getting any strange because I like my boyfriend (most of the time).

• skatr

I’m absolutely flabbergasted that the average number of sexual partners is so low although perhaps I shouldn’t be as it sort of confirms the stereotype of the nerdy socially inept geek with thick glasses. OTOH, I spent my young adulthood in the pre-AIDS era so perhaps that has something to do with my perspective on this.

• http://blogs.discovermagazine.com/gnxp Razib Khan

I’m absolutely flabbergasted that the average number of sexual partners is so low although perhaps I shouldn’t be as it sort of confirms the stereotype of the nerdy socially inept geek with thick glasses

this isn’t that different from academic studies i’ve seen. eg 1994 ‘sex in america’

• http://blogs.discovermagazine.com/gnxp Razib Khan

but I’m not getting any strange because I like my boyfriend

once u go brown, u turn everything else down.

• ackbark

You should chart sex partners vs. alcohol consumption vs. education level.

• http://ecophysio.fieldofscience.com/ EcoPhysioMichelle

He didn’t ask about alcohol consumption. I would like to see partners vs. education level, though. Also personality type.

• Selphin

What’s surprising to me is the number of folks who are competent programers. I’m going to assume this it’s associated with the academic proclivities of the readers. I’m a soft scientist, but I’m guessing that some variety of programming usually picked up in the life sciences and physics, and is most definitely acquired in mathematics and computer science.

• http://blogs.discovermagazine.com/gnxp Razib Khan

who said competent? :=) but i think a scripting language at least is de rigueur.

• John Emerson

I doubt that BMI is closely correlated with attractiveness outside very limited and fashionable circles of young people. Starved supermodels look that way for business and for photography, not to be sexy. My guess is that as long as the body shape is appropriate (no gut, no big butt, no hanging slabs of fat) BMI makes little difference for 90% of the population.

• http://blogs.scientificamerican.com/crude-matter/ EcoPhysioMichelle

Hey, some people like big butts!

• http://blogs.discovermagazine.com/gnxp Razib Khan

BMI is most informative at the population level. once you keep that in mind a lot of the issues disappear.

as for politics, i don’t talk about it is much, do i? even when i have opinions on stuff if it’s shaped by my values i tend to stay away from preaching. i’m not here to persuade. i only bring up my politics when newbies forget themselves and think i share their liberal values when i really don’t. almost all of my friends that i know through science blogging share a set of liberal presuppositions which shapes their communal discourse on topics, but that doesn’t matter to me because i don’t stick my nose into their conversations.* they interest me as much as a lot of religious conservative talk grounded in the bible. the stuff is real to people who already share some axioms.

* the only time i will probably saying anything is when they joke that conservatives are all morons, and i will wonder if the think i’m a moron

• skatr

“i think a scripting language at least is de rigueur.”

Smart programmers use the highest level language possible. Interpreted languages with dynamic typing aren’t the “least”, they are the most!

http://www.newlisp.org/

• http://blogs.discovermagazine.com/gnxp Razib Khan

• http://entitledtoanopinion.wordpress.com TGGP

Real Programmers like Mel write machine code. That is, if they are not simply rewiring switches without the crutch of a “language”. In fact, they hate computers and write software only so they can add undetectable and never-corrected bugs.

• JL

Quite a lot of bisexuals there. Are they disproportionately female?

• Liesel

I was surprised you asked about the Meyers-Briggs test on the survey. I took it twice and got two different answers. I swear this wasn’t intentional!

Anyhow, then I picked one and put that as my answer. I hope I didn’t screw up the survey. Aren’t those tests like a horoscope, people agree with the parts they like or recognize and forget the parts that are wrong or unflattering?

• http://blogs.scientificamerican.com/crude-matter/ EcoPhysioMichelle

#19, I’d like to know that as well.

• http://blogs.discovermagazine.com/gnxp Razib Khan

#20, ppl asked about personality tests. i don’t have much faith in meyers-briggs. though i think one can guess readers of this weblog tend to be shy nerds.

• http://blogs.discovermagazine.com/gnxp Razib Khan

here are the breakdowns by sex by orientation:

het: 82% male, 18% female
homo: 86% male, 14% female
bi: 48% male, 52% female

• http://blogs.scientificamerican.com/crude-matter/ EcoPhysioMichelle

So disproprortionately female compared to your m:f ratio.

• http://blogs.discovermagazine.com/gnxp Razib Khan

yes. N = 27 for bi’s.

• http://changelog.ca/ Charles Iliya Krempeaux

Razib,

I’d be interested in seeing Meyers-Briggs results versus the various political/moral and economic questions.

Also, seeing IQ versus the various political/moral and economic questions.

(Although I’d expect some artifacts in the results. Many IQ tests (that I’m familiar with) don’t give scores above 140 , so a person who typically scores at or near 140 on those tests could in fact be higher.)

I suppose math versus the various political/moral and economic questions and even programming language versus the various political/moral and economic questions could be interesting too.

There is something specific I’m looking for these if it matters

It’s too bad you don’t release the raw results anymore, people could check these themselves, instead of pestering you

• http://blogs.discovermagazine.com/gnxp Razib Khan

i will release them when the survey closes.

• skatr

“even programming language versus the various political/moral and economic questions could be interesting too.”

I wouldn’t be surprised to see a high correlation between Java coders and low socio-economic status as it is almost a tautology.

• http://blogs.discovermagazine.com/gnxp Razib Khan

men of class lisp….

• http://entitledtoanopinion.wordpress.com TGGP

I should note that I filled the survey out fast as I could before heading to work, and answered every question even when I had to guess based on some fuzzy memories (BMI and Myers-Briggs). I even had my age off by one. But I figure with a large sample size that noise wouldn’t affect things much. But apologies for that bit of inaccuracy.

• Miley Cyrax

@ 3. EcoPhysioMichelle
“Personal anecdatum: I had a BMI of almost 30 in college when I was accumulating sexual partners. I’m almost a 19 BMI now. Fat me got WAY more strange ass than skinny me. I am tipping the hot end of my personal attractiveness scale right now; I look the best I ever have and probably the best I ever will, but I’m not getting any strange because I like my boyfriend (most of the time).”

As expected. Number of sexual partners for girls should be weakly to moderately inversely correlated with their attractiveness, even without adjusting for number of suitors (attractive girls will have more suitors). Attractive girls don’t need to put out to maintain consistent male attention and are abandoned with lesser celerity after first intercourse, thus keeping the number of total sexual partners down. Going from 30 to 19 BMI does a similar thing for your sexual and dating options as does going from 900 to 1500 SAT does for your college prospects.

In general I would imagine the relationship between male IQ and number of sexual partners to be parabolic, with very low-IQ and high-IQ men left out of the dating scene. I would have also guessed a tighter relationship between readership age and # of sexual partners, as there’s no generational differences in promiscuity, despite what people may presume.

• http://blogs.discovermagazine.com/gnxp Razib Khan

In general I would imagine the relationship between male IQ and number of sexual partners to be parabolic, with very low-IQ and high-IQ men left out of the dating scene.

have you looked in the GSS? easy to find.

• http://entitledtoanopinion.wordpress.com TGGP
• http://blogs.scientificamerican.com/crude-matter/ EcoPhysioMichelle

#31, my point was that *current* BMI is not likely to be very predictive because it is so open to fluctuation. You’d have to rephrase the question, like ask how many partners one has had in the last year or something to that effect. However the married folk will still throw everything off.

• http://blogs.discovermagazine.com/gnxp Razib Khan

#34, i think our ludwig von mises of female behavior just wanted to engage in some praxeology

NEW ON DISCOVER
OPEN
CITIZEN SCIENCE

### 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!