April 28, 2014

Income inequality perception

If you ask people in the US to estimate the income of someone at the 80th percentile, they underestimate it, thus underestimating income inequality (PDF).

However, if you specify a dollar amount and ask how many people have income above that amount, you get an underestimate of high incomes.

The take-home message? It’s hard to design good survey questions.


Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »


  • avatar
    Elliot Lawes

    Super interesting article. I don’t really know this field, but I wonder how good people are at estimating any distribution with which they aren’t familiar.

    3 years ago

  • avatar
    Megan Pledger

    In the first study they measured wealth. In the second study they measured yearly income (but I couldn’t see how they defined that – is it just wage income, taxed income or all source income?)

    So people underestimate how much wealth those at the top of that distribution have and over estimate how much yearly income those at the top of that distribution have.

    That sort of plays into the long held beliefs of Americans that anyone can attain the “American dream” if they work hard enough i.e. the rich are rich because they are working hard for it rather than they are living off the wealth they, or someone else, created earlier. Whereas Andrew Gelman has a view about how meritocracy ends…

    3 years ago