Data visualization lessons: Jitter charts, screwups, and visionaries
Learn from others' mistakes if you can (less painful than learning from your own)
These are somewhat connected, but not.
Jitter charts – how and why to make them
Jitter charts are my new favorite tool for displaying how distributions change over time.
I used them to great effect in my recent post One Bad Year? Comparing the Long-Term Public Pension Fund Returns Against Assumptions.
I’m often looking at distributions, and wanting to communicate something about how those distributions change over time, or how distributions compare. Often, I have to simply pick out key percentiles in those distributions, or key aspects, such as mean and standard deviation.
But why not graph all the points in one’s sample directly, if one has them?
That’s where jitter charts can help.
If you want to play around with the spreadsheet, you can get it from my DropBox.
Other links shown in the video:
17 July 2020: Classic STUMP: Public Pensions Primer—The Choice of Discount Rate and Return Volatility
20 Sept 2015: Public Pensions Primer: Choice of Discount Rate Influences Results
3 May 2018: Alternative Assets and Pension Performance: A Dive into Data
27 June 2018: Geeking Out: Public Pension Mortality Assumptions
DataViz Screw-Up… that wasn’t the viz per se
This one was funny to me.
I wrote a piece for Nightingale, the journal of the Data Visualization Society:
Dataviz Horror Story: How I Crashed the Top Exec’s Email
and here is a video of me telling the story, and doing a demo of what happened:
So don’t do that. Make different mistakes!
Dataviz visionaries
Obliquely related, I wrote The What of Data Visualization for one of the Society of Actuaries newsletters, January 2017, and at the beginning I mention Florence Nightingale & W.E.B. Du Bois’s use of data visualization… and here are a couple of their examples:
I used this key image from Florence Nightingale:
If you recall, I re-did her graph last year, and looking at it, I’d redo it again, but I don’t have time right now, and…I am super-stoked about this book about to be published on her dataviz work.
I’ll wait until after the book comes out before I try to re-redo the graph. Heh.