« Self-sufficient charts | Main | Oil spills bring out the worst »

Comments

Knut

What's a ripleyesque reply?

Barry Rowlingson

Never mind the radar charts that look like a drunk spider has wandered over your data, this report has pie charts with ordered values.

Page 11 shows a pie chart of "[...] how much trust do you have in the government [...]", and the pie shows the percentage in each of categories: none, a little, some, a great deal, and don't know, which are clearly ordered but presented in a circle. I've just had to page back and forth lots of times to work out that the Singaporeans trust their government the most, and Italians the least (as if I couldn't have guessed that myself).

Anyway, the data for the pie charts for all the countries could easily be represented in one graphic taking up just as much space. If these people can't get pie charts right, what hope have they to control crawling spiders?

Nick Cox

Presumably the allusion is to Brian Ripley of Oxford University, a leader in the R community.

Brian has helped many more people on R mailing lists with precise and correct information than most of the people who take exception to his terse style and/or to his attitude that it is reasonable to expect R users to try to help themselves a bit, say by trying to read the documentation.

More could be said, but it is predictable that others will say it!

James Pearce

Brian's replies are always spot on, but in these days, my first port-of-call for R problems is Google rather than documentation. This means often the first thing is an R-help discussion featuring Brian's replies. In this context, they're not always helpful, but they weren't designed to be.

Alex Cook

I should clarify: when I wrote "Ripleyesque", it was meant as a reference to the folk-lore image of Brian Ripley and his terse R-help replies, not to my actual opinion of the man. Actually I find his replies very helpful when, like James, I'm googling around trying to find out how to do something in R and find he's already sorted out someone with a similar problem. Of course, he's not obligated to give that help, so the reputation is quite unfair.

Kaiser's much worse: you send him a prime example of junk chart and he replies with an email containing nothing but the data, without even writing "Do it yourself"! :o)

Oh, and further to James' comment, if you're using google for R searches, you might try Dan Goldstein's webpage: http://www.dangoldstein.com/search_r.html
I don't know how it works but it does a great job of filtering out pages to do with the letter "r" etc.

Kaiser

Ripleyesque is basically an inside joke. Those who have used R-help before would get it. I am also a fan of Brian's responses. The "hint" of controversy is because Brian is not beneath sending a reply telling the poster to search the archives before posting something that has already been asked, which I find totally appropriate.

Naomi B. Robbins

The Association for Research Libraries uses similar radar charts for surveys where the respondents are asked for minimum acceptable levels, desired levels and perceived levels. I show examples and present alternative graphs in Creating More Effective Graphs (Wiley 2005).

Verify your Comment

Previewing your Comment

This is only a preview. Your comment has not yet been posted.

Working...
Your comment could not be posted. Error type:
Your comment has been posted. Post another comment

The letters and numbers you entered did not match the image. Please try again.

As a final step before posting your comment, enter the letters and numbers you see in the image below. This prevents automated programs from posting comments.

Having trouble reading this image? View an alternate.

Working...

Post a comment

Marketing analytics and data visualization expert. Author and Speaker. Currently at Vimeo and NYU. See my full bio.

Book Blog



Link to junkcharts

Graphics design by Amanda Lee

The Read



Good Books

Keep in Touch

follow me on Twitter

Residues