• Hirom@beehaw.org
    link
    fedilink
    English
    arrow-up
    7
    ·
    4 days ago

    Averages are affected a lot by outliers with very large values, and the effect is larger when there’s large inequalities. If measuring by income or wealth (higher is better) in a stadium with 1 billionaire and 999 homeless people, the average people is millionnaire.

    This study still uses averages and flips the effect with a povery score (higher is worse). It gives more weight to the other end of a spectrum, very poor persons that need 300min to win 1$ makes the average much higher.

    Using median values, or better 20-80 centiles values would be more meaningful.

    • NoneOfUrBusiness@fedia.io
      link
      fedilink
      arrow-up
      3
      ·
      4 days ago

      I mean giving the lower end more weight is kind of the whole point of this exercise. The effect you’re describing is a good thing in this scenario.