[FRIAM] What Is the Real Coronavirus Toll in Each State? - The New York Times

[uǝlƃ ☣]

I disagree, of course. >8^D I think dividing out population and area are a misguiding distraction. The simple slopes are better. As we've discussed ad nauseum, these "normalizers" are *also* models. And all models are always wrong. So, for every derivation, you're stacking wrongness upon wrongness. If you're super careful, the stacks of wrongness *might* help you see some aspect of the situation better. But by "super careful", I mean *professional* modeling ... something that costs a lot of time, money, attention, and skill.

Our fondness for blinky lights, bells and whistles, pornographic evocation of our love for *metaphor* will only mislead us. Data first, metaphor second (or better yet, never).

On 5/8/20 8:03 AM, Steven A Smith wrote:
> Very interesting view on these three counties...  numbers normalized to population count and population density are a "good start"!


-- 
☣ uǝlƃ