• @taiyang
    link
    662 months ago

    I like that they have to use median, because I’m often having to find examples of why you’d use that over mean. My wife for instance is over 5k miles from her mom, and I imagine that’s true of most immigrants. So the skew is probably really, really strong if you didn’t use a non parametric measure like the median.

    In other words, I’m stealing this for my stats class.

    • @[email protected]
      link
      fedilink
      English
      202 months ago

      I like using both. An average of say 300 miles with a median of 5 miles would show you that there is significant bias toward the lower end.

      I’m not a statistician but that’s my understanding of the two metrics

      • @taiyang
        link
        72 months ago

        Yeah but you can’t really do that with a map. In a table you could. A report would likely report both, but also differentiate groups because you don’t usually want to report skewed data without explaining why.

        • @[email protected]
          link
          fedilink
          English
          32 months ago

          I bet if go down to county or city level, you‘ll find differently colored areas such as cities relying on old steel, coal, textile economies. At least here in Germany I know areas where many people left their home areas in the 90ies. But that’s probably a geography lesson.

          • @taiyang
            link
            22 months ago

            Yup! And if you have the right dashboard you can usually drill down by location down to that level and even include those additional factors as an overlay. I used to do that using census and labor statistics data, and it is indeed very cool.