« Visually exploring the relationship between college applicants and enrollment | Main | Say it thrice: a nice example of layering and story-telling »

Comments

Dave C.

There may also be some seasonality to consider. NHTSA shows a correlation between fatalities and monthly average temperature. April is a month that has school bus traffic as well as people getting on motorcycles and bicycles.
Could you change your graph to compare 4/20 to other days in April and May with similar temperatures?

Kaiser

Dave: Would recommend reading the more detailed report at Harper's site. He and Palayew tried two other set of reference days: going two weeks instead of one week around the analysis day; something they call "all other control days," which I think means the same day of the week in the other 51 weeks. They also compared analyses of April 20 and of July 4. The July 4 effect is much more solid. Doesn't directly address your question but a similar type of analysis.

The comments to this entry are closed.

BOOTCAMP SUMMER '19



Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Book Blog



Link to junkcharts

Graphics design by Amanda Lee

The Read



Keep in Touch

follow me on Twitter

Residues