Skip to content

Not the best time for a parallel coordinate plot . . . but it’s not actually so bad here

Ben Hyde and Aleks both sent me this:


The graph isn’t as bad as all that, but, yes, a scatterplot would make a lot more sense than a parallel coordinate plot in this case. Also, I don’t know how they picked which countries to include. In particular, I’m curious about Taiwan. We visited there once and were involved in a small accident. We were very impressed by the simplicity and efficiency of their health care system. France’s system is great too, but everybody knows that.


  1. Snoop Dogg says:

    I like the chart.

    3 dimensional scatter plots are not easy to read.

    Perhaps a scatter plot where the points are bubbles representing the number of doc visits?

  2. Andrew Gelman says:

    I wasn't suggesting a 3-D scatterplot. I was suggesting a 2-D scatterplot, with lifespan on one axis and spending on the other.

  3. Keith O'Rourke says:

    Doubly fair comparisons are likely more than doubly hard to make.

    Some methodological work has been done on causal inference in cost/benifit analyses (aka health economic analysis), but likely more is needed.

    Here the apparent dramatic differences in outcomes and costs might make conclusions less tenuous, but getting a fair comparison is going to require substaintial methodological work if not development.


  4. Seth Roberts says:

    I'd recommend use log cost not cost and equalizing some measure of variation(such as standard deviation) for the two measures. Now cost varies a lot more (spatially) than life expectancy.

  5. Andrew Gelman says:

    Seth: Definitely. Take a look at my later post on the topic.