The New York Times on Wednesday published an editorial by Andrew Gelman, Nate Silver and Daniel Lee on the motivations of the 100 US Senators with regard to their opinion on the healthcare legislation currently under debate. Using multilevel regression and post stratification, they reveal that many senators’ motivations may be linked more closely to the President’s popularity in their state (and, by proxy, their chances of re-election) than the wishes or needs of their constituents.
On his blog, Gelman has posted an interesting behind-the-scenes look on what it takes to make a statistical analysis into a political op-ed. I was particularly interested to see how the graphics department converted this chart created with R:
into this graphic …
The New York Times on Wednesday published an editorial by Andrew Gelman, Nate Silver and Daniel Lee on the motivations of the 100 US Senators with regard to their opinion on the healthcare legislation currently under debate. Using multilevel regression and post stratification, they reveal that many senators’ motivations may be linked more closely to the President’s popularity in their state (and, by proxy, their chances of re-election) than the wishes or needs of their constituents.
On his blog, Gelman has posted an interesting behind-the-scenes look on what it takes to make a statistical analysis into a political op-ed. I was particularly interested to see how the graphics department converted this chart created with R:
into this graphic:
Usually it’s a bit more obvious when R is used as the basis of an NYT graphic, but it’s interesting here how they’ve taken the raw data and presented it in a more accessible fashion. It’s also very cool to see how widely R is being used in political science discussions — see also this analysis of the controversial NY-23 congressional race by Boris Shor that was cited in the NYT and Mother Jones.
New York Times: The Senate’s Health Care Calculations