bsmall2> The first rule of table construction is to:
> Order the rows and columns in a way that makes sense. We are almost never interested in “Austria First.”
...
> Round-a lot! This is so for three reasons:
> a. Humans cannot understand more than two digits very easily.
> b. We can almost never justify more than two digits of accuracy statistically.
> c. We almost never care about accuracy of more than two digits.
https://diasp.org/posts/12734726
http://www.jstor.org/stable/1176346
#HowardWainer #DataOrder
I have to print these visualizations out and take the time to see i...
I have to print these visualizations out and take the time to see if they are useful. maybe I can get a few people to look at them and see if they come up with any questions. My first impression is that it's helpful to have the row-based and column-based plots side by side. Maybe taking up so much space is hard to justify in a printed publication, but maybe the side-by-side view would work in a small group. Everyone gets a page to ponder and discuss. The screen probably distracts from free discussion, the screen probably privileges the preparer or speaker in a way that distracts from a free-and-equal give-and-take conversation... Wrestling with Minamata's important data table is giving me confidence with Racket. I feel like, with enough time and focus, I can create what I want with a table of data. This work(play?) has given me an opportunity to appreciate "functional programming" while using sort. Racket's sort lets me adhere to Howard Wainer's(fn:1) advice on table construction. I...