« Valentine's Day Recommendations | Main | Books I Purchased This Morning »

February 15, 2011


One problem with this analysis, however, is that it doesn't take into account cost-of-living in different states. The $11,000 per pupil in WI could be comparable (or even higher) than the $13,000 in MA, for instance.

It would be nice if you could circle each region. New England? Nice circle. Mid-Atlantic? Wider, but definitely overlapping New England, and owns a distinct part of the graph. The South? Take out Virginia, and there is a clump, with few other states inside. But divide that clump into two pieces, and notice that the lower piece is the lower South....

Circles are fun. And illuminating

yeah, I like circles--but how about this? let's draw a little circle around NV, then draw a little arrow pointing to the circle, and draw three little letters as a caption:


'cause that is horrific.

Nevada claims they're not really that bad, and they have a point. Graduation rates are quite difficult to calculate for a district with a lot of transients; for instance, Clark County, Nevada. If a student moves away without providing the district with forwarding information that allows them to confirm that the student is still in school, that student counts as a dropout, even though it's quite likely that the kid really is still in school somewhere.

That said, even by Nevada's own reckoning, they're graduating less than 70% of their students. Here's a link with more info: http://www.lasvegassun.com/news/2010/jun/17/graduation-rate-state-bad-it-bad/

The outlier data looks really interesting. I'd love to have a look at the original data in the raw, and draw multiple random samples to see if the outlier trend is a constant, and if so, see if I can eliminate other variables like SES status to see if the upper quartile outliers just simply have a better program.

Every brave man is a man of his word

The comments to this entry are closed.