Because I have spent all week in R

Since I’m already ranting and possibly pissing off people, let me toss this out there: I think that there are differences between the sexes and races in things like intelligence. I’m almost certain of it. So please stop acting like it’s immoral to claim that such a thing is possible. However, the data and statistical modeling skills that you would need to uncover such a difference are substantial: you’d need to control for upbringing, culture, nutrition, age, and a million other things. And even if you got that all totally under control, you’d still have to account for the fact that your sample – even if it were the entire population of earth – is not truly the whole population of human beings.

Don’t believe me? Here are five simulations of intelligence scores (note: to get this empirically, you would have to have a perfect metric for intelligence). Back is male, red is female, n=10,000,000. All these simulations are randomly-generated normals – except that one sex has each score shifted to the right by a fairly significant amount, to account for its superiority. It’s the same sex shifted by the same amount in all five simulations. Sorry for the low-quality pics:

Can you tell which sex has the advantage? Me, either. And if you could, would it change the way you acted toward individuals of a particular sex? Me, either – they overlap so much that you would be foolish to assume that the person in question fell into the left- or right-most areas, where sex actually makes a difference. Either way, the person would probably be so stupid or brilliant that you wouldn’t really be wonder if somebody of the opposite sex might be just a bit dumber or smarter.

*I am praying to God (please forgive me for my years of agnosticism!) that no quantitative people read this and shred my simulation technique.



Filed under Uncategorized

5 responses to “Because I have spent all week in R

  1. Status construction theory?
    If you consistently meet with a person of one sex, race, etc. of a particular level of intelligence, that would affect how you treat them, which would affect you in future interactions, which would affect how others treat them as well?

  2. Well, yes. But status construction theory only affects the way your perceptions if you allow anecdotal evidence into your calculations. And I never do that. Oh no. Strictly scientific over here, y’all, 24/7.

  3. Anonymous

    What are the variables that go into a simulation for intelligence?

  4. Heh. None, really – I just assumed that intelligence is normally distributed for both sexes and used the rnorm random number generation function in R.

    Um… in retrospect, I’m not really sure what the point of this post was. I was just SO RILED UP that it kind of spilled out. Ah, well.

  5. So it’s all about you?
    Sometimes “you” can refer to random person x, y or z.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s