Sketching Realistic Graphs (2005) | Hacker News Reader

Sketching Realistic Graphs (2005)

statmodeling.stat.columbia.edu

41 pointsluu4 comments

It may be for the same reason they can't convincingly create fake books, rig elections, or fabricate data:

https://en.wikipedia.org/wiki/Benford%27s_law

"The law states that in many naturally occurring collections of numbers, the leading significant digit is likely to be small. For example, in sets that obey the law, the number 1 appears as the leading significant digit about 30% of the time, while 9 appears as the leading significant digit less than 5% of the time. If the digits were distributed uniformly, they would each occur about 11.1% of the time. Benford's law also makes predictions about the distribution of second digits, third digits, digit combinations, and so on. "

I was thinking this was gonna be some long ago theoretical work on something like roughViz https://github.com/jwilber/roughViz

Isn't drawing a cartoon character very different from drawing a scatterplot?

I'm not sure how the end conclusion about practice is relevant. I see how practicing would help in both drawing cartoon characters and drawing scatterplots. But I don't see the link between the two; it seems to me that practice would also help people who e.g. play an instrument.

I think that you pretty much hit on the gist of the post. Professor needs to practice to draw cartoons, students need to practice to draw graphs, he shouldn’t be frustrated with students inability to draw graphs because they are at the beginning of their journey. Just as a cartoonist could possibly draw Bert and Ernie without any reference material compared to an amateur who can’t even when copying from a picture. A student can’t “draw” the scatter plot as well as a professor who has worked with the data for their whole career because they may be putting marks on the paper but they don’t necessarily “see” the data/ information. Certain data is going to have a certain form to it that may only be apparent to someone who works with it regularly so if asked to draw the data, you leave out details that are obvious to an expert such as making the made up data conform to the regression line or failing to include non-negative numbers. The exercise made the professor empathize with the students about being expected to do something trivial for the expert but difficult for the beginner.

Reply on news.ycombinator.com