• usualsuspect191@lemmy.ca
        link
        fedilink
        arrow-up
        24
        ·
        9 months ago

        Presumably they are starting wherever the trend “started”, although I’d like to see what it was doing before that to see if this is an unusual trend or not

      • SkyNTP@lemmy.ml
        link
        fedilink
        arrow-up
        19
        arrow-down
        20
        ·
        9 months ago

        Because gaps in data are a thing? I dunno, it doesn’t really seem to change the story or the outcome. Your concerns seem overblown.

        • sharkwellington@lemmy.world
          link
          fedilink
          arrow-up
          28
          arrow-down
          3
          ·
          9 months ago

          Then attention should be drawn to the fact that the timelines are different. The data is presented in a misleading way and we should hold ourselves to a higher standard.

        • 087008001234@lemmy.ml
          link
          fedilink
          arrow-up
          9
          arrow-down
          1
          ·
          9 months ago

          In general, consistency in quantity of data points (in each different insight, not the full study sample size), consistency in period, and consistency in types of data (if categories are present) are nice things to reassure you that the data isn’t be stitched together from sources that are actually saying different things with radically different methodology or data structure.

          I think its a perfectly reasonable question to ask.

    • janabuggs@beehaw.org
      link
      fedilink
      arrow-up
      18
      arrow-down
      1
      ·
      9 months ago

      Omg I didn’t even notice that. It’s like the more you look at this the worse it gets.

    • fidodo@lemmy.world
      link
      fedilink
      English
      arrow-up
      6
      ·
      9 months ago

      I’m guessing the data sets they used were collected at different start times and they didn’t want to truncate it