That's a great analysis, but the scatterplot makes me almost physically uncomfortable: it WANTS a simple cubic or logit curve drawn through it! This clear gentle bend! Or maybe a rank transformation. Because of that, a huge part of ubran effect remains unexplained.
-
-
-
There’s a fork button if you want to respond to Jake’s analysis with your own.

- Još 1 odgovor
Novi razgovor -
-
-
Really cool work Jake (is he on Twitter?)! There is a funny pattern on the correlation scatterplot though, seems like there are some issues with the population of Alaska. I noticed it because I had the same issue looking at Colombian datapic.twitter.com/lBO8gTy8JD
-
Alaska doesn’t report county-level (census area-level) results, but you can get population data, hence the flat line.
- Još 2 druga odgovora
Novi razgovor -
-
-
Reminds me of one of the first
@d3js_org applications I saw by@mtraven at a#d3Meetup http://hyperphor.com/election/scatterstates.html … Beautiful stuffHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
Prikaži još odgovora, uključujući one koji mogu sadržavati uvredljiv sadržaj
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.