[jldugger]

More formally, this is the origin story for Simpson's paradox: when you combine subgroups, trends can disappear or even reverse. The more dimensions you analyze, the close to 'truth' you can get.

This is why you have such varying claims about stuff like women earning equal pay with men. People who want social change (activists, politicans) group together the entire population, and come to the conclusion that women make 83 cents on the dollar. But when you break out along other dimensions (age/YOE, occupation, hours worked), the gap is reduced. But never eliminated!

What I'd really like to do some day is be smart enough to replicate https://www.metafilter.com/126704/with-numbers-like-these-wh... and see how more recent census data compares.

[xenocyon]

"The more dimensions you analyze, the close to 'truth' you can get."

Data scientist here. The above is not the correct takeaway from Simpson's paradox. It is not generally correct that the trends seen in subdivided groups are closer to truth than overall groups; sometimes the opposite is the case. It depends entirely on what the divisions are and whether they make sense.

With regard to gender-based pay disparity, there are a multiplicity of factors, from the most obvious ("equal pay for equal work") to other factors such as the fact that professions largely staffed by women tend to get paid less than professions largely staffed by men. For instance childcare is miserably compensated, despite being a position of high responsibility and impact.

The consensus regarding women during the pandemic (not limited to tech workers) was that women have disproportionately sacrificed their careers to cover the needs of childcare and at-home schooling during the pandemic.

[tmule]

Without defining truth and correct, the rejoinder makes little sense, your data science credentials notwithstanding.

What seems like a plausible interpretation to my un-credentialed, low-IQ self is: 1. Within dimension comparisons in this instance may suggest that “like” populations are similar across gender, suggesting that there is no bias in how tech compensates women and men. 2. The distribution of said dimensions differing between men and women may reflect exogenous effects that are not controllable by tech since they’re upstream of the tech hiring process.

[xenocyon]

Regarding Simpson's paradox, you can see a good treatment here [0] describing whether splitting a group is correct or not (based on causality); see Section 2.2 specifically.

[0] http://ftp.cs.ucla.edu/pub/stat_ser/r414.pdf

[jldugger]

Well, that's definitely going on the reading backlog. Thanks!

[jldugger]

> The above is not the correct takeaway from Simpson's paradox. It is not generally correct that the trends seen in subdivided groups are closer to truth than overall groups;

This is why the word truth was in scare quotes. And the word 'can' was also doing a lot of work in that sentence.

[droopyEyelids]

Should people who sacrifice their careers for noble goals be paid less?

Not that I am demanding an answer from you specifically. It's just a weird question in the context of a country where wage labor is the only real source of income for individuals.

[AmericanChopper]

What does “paid less” even mean in this context? If you sacrifice your career, you sacrifice the remuneration you were receiving from it. It’s part of the career…

[tchanglington]

That’s just simple economics - if they’re willing to settle for a noble job even if they get paid less then they’ll get paid less on average

[mbrodersen]

In a market driven economy: yes. It’s the same reason why game developers are paid less than developers in other high skill jobs: game developers are willing to get paid less in return for working on games.

[gremloni]

Your goal is the “noble” goal now, not your career.

[klipt]

I'm pretty sure the origin of the wage gap is just that relatively, income is a bigger status booster for men than it is for women. Women have other status boosters like being seen as a good parent, and if you look at those dimensions there's a gap in favor of women. People are simply, on average, optimizing for what benefits them most in society, and those things are different for men and women.

This explains observations like, when a field becomes more lucrative, it attracts more men. Or when a field becomes less lucrative, men abandon it and it ends up disproportionately female. So even if there's equal pay for the same job, men will earn more on average by being more likely to pursue the higher earning jobs.

Of course, we could say the fact that society values different things in men and women is sexism. That's true, but I'm not convinced it's sexism exclusively against women: a man who'd rather spend time with his kids is also negatively affected by society pushing him to be a breadwinner instead.

In the end, do wages matter more than general life satisfaction (not sure if either gender does better here), or other measures like life expectancy (which favors women)?

[mbrodersen]

I agree. Also because men has to compete hard to be an attractive mate for woman. Woman have more choices than men and are smart enough to pick men who are more successful in life.

[whiskyant]

>the gap is reduced. But never eliminated!

https://www.payscale.com/data/gender-pay-gap

The controlled salary (same job/qualifications) for Asians, have both men and women earning the same (women a tad higher even).