follow CCP

Recent blog entries
popular papers

Science Curiosity and Political Information Processing

What Is the "Science of Science Communication"?

Climate-Science Communication and the Measurement Problem

Ideology, Motivated Cognition, and Cognitive Reflection: An Experimental Study

'Ideology' or 'Situation Sense'? An Experimental Investigation of Motivated Reasoning and Professional Judgment

A Risky Science Communication Environment for Vaccines

Motivated Numeracy and Enlightened Self-Government

Making Climate Science Communication Evidence-based—All the Way Down 

Neutral Principles, Motivated Cognition, and Some Problems for Constitutional Law 

Cultural Cognition of Scientific Consensus

The Tragedy of the Risk-Perception Commons: Science Literacy and Climate Change

"They Saw a Protest": Cognitive Illiberalism and the Speech-Conduct Distinction 

Geoengineering and the Science Communication Environment: a Cross-Cultural Experiment

Fixing the Communications Failure

Why We Are Poles Apart on Climate Change

The Cognitively Illiberal State 

Who Fears the HPV Vaccine, Who Doesn't, and Why? An Experimental Study

Cultural Cognition of the Risks and Benefits of Nanotechnology

Whose Eyes Are You Going to Believe? An Empirical Examination of Scott v. Harris

Cultural Cognition and Public Policy

Culture, Cognition, and Consent: Who Perceives What, and Why, in "Acquaintance Rape" Cases

Culture and Identity-Protective Cognition: Explaining the White Male Effect

Fear of Democracy: A Cultural Evaluation of Sunstein on Risk

Cultural Cognition as a Conception of the Cultural Theory of Risk

« Weekend update: Who really did write the CRT-evolution paper then? | Main | Cognitive reflection and "belief in" evolution: critically engaging the evidence »

So we know we can't defeat entropy; but what about overplotting????

I had some correspondence off-line with loyal listener @Steve (aka @sjgenco) about the classic "what does a valid measure of climate-change risk-perceptions look like graph?"  Inspired by loyal listner @FrankL (now that they've finally discovered " missing Malaysia Airlines Flight MH370"--or at least a piece of it--maybe someone will find @FrankL, or at least a piece of him, too), the WDVMCCRLLG graphic has of course achieved iconic status and is pretty much ubiquitous in popular culture.

But it is pretty darn old. Isn't it time for something new? Can't we do better?

Yes, it's  comforting familiarity, its association with memorable moments both personal and worldhistorical, will likely motivate loud howls of protest, at least initially.

But everything, no matter how wonderful, admits of incremental improvement as human knowledge continues to expand as a result of science and improved sports drink formulas.

In response to @Steve's inquiry, I revealed the secret formula for generating the graphic. When Steve said he wasn't enamored of "jitters" as a way to handle overplotting & preferred "bubbles" scaled to reflect observation densities, I directed @Steve to a CCP dataset he could use (one posted with "codebook" the last time the CCP blog was the site for a furious display of graphic genius on the part of @thompn4) to perfect his own improvements.

Here's what he wrote back: 

Hi Dan,
I've been playing around with jitters in R. I like your Gervais jitters. Keeping the clouds more separate helps. That's harder to do when your x-var is continuous, like your libcon variable in your "challenge" dataset.
Your dataset was like catnip so I've squandered a couple of days trying to brush up on my R to see if I could implement my bubble plot idea with your data. For what it's worth, I seem to have succeeded so I thought I'd forward my results. (I use RStudio, btw, I highly recommend it.)
First, I was able to replicate your colored jitter charts in R (seems to require less code than in stata). Here's gwrisk by libcon (making the points 50% transparent also helps highlight the clustering imho):
When I figured out how to put bubbles representing the frequency of responses around each datapoint on the same plot, it looked like this:
It does show the densities nicely, I think. For comparison, here's the bubble plot for scicomp by gwrisk:
You can really see that scicomp clusters in the middle vs. libcon, and how those densities are going to generate a flat regression.
You can also combine the two plots, which is kind of interesting:
Note how the jittering on libcon stretches out the values along the x-axis. There actually aren't any "real" values above 2 or below -2.
I've attached a PPT with all my results, a commented R script for running the plots, and the Rdata image I created for inputting the data.
It was a good excuse for digging into R again. 

So what do people think? Time to retire WDVMCCRLLG? Time to adopt one of @Steve's alternatives as the new symbol of the Un-United States of Risk Perception?

Voice your opinoin --as with everything else relating to this blog, matters will be decided by a democratic vote of the site's 14 billion regular readers -- and by all means try your own hand at devising a graphic that conveys the information in WDVMCCRLLG in an even more compelling, cool way!

And if you want, you can go back to  @thompn4's project to create the perfect 3D graphic presentation that incorporates in addition the impact of science comprehension in magnifying polarization over climate change risk.

I'd offer one of our standard CCP prizes, but obviously the fame of being the originator of the successor of WDVMCCRLLG is incentive enough!

Manny models WDVMCCRLLG high fashionWDVMCCRLLG as backdrop for dramatic & inspired (but ultimately failed) gesture to heal the nation's wounds

PrintView Printer Friendly Version

EmailEmail Article to Friend

Reader Comments (4)

I'd suggest at least retiring the rainbow color scale within the graph. After all, if you're really trying to reduce 6 Americas to 1 dimension of risk, why are you using 7 different hues? And cognitively, the yellow-greens in the middle stand out more to the eye.

I'd recommend one hue (neither blue nor red for political reasons - maybe, dare I say, green?) with the lightest greens at the bottom, and the darkest at the top, depicting increasing concern in darker green.

Or another alternative may highlight the liberal/conservative as well: start with neutral color in the middle of risk, then increase darker blue toward liberal and red darker toward conservative.

Either of these may help focus folks on the trend line and maybe help move toward the super-iconic status a new version is sure to achieve. And they may point to a way to an answer about the bubbles.

Here's a (hopefully user-friendly) document on choosing colors:
Yours isn't spatially-based, but I think the principles would apply.

August 21, 2015 | Unregistered CommenterKatie Stofer

My thoughts re the use of color are already mostly expressed by Katie Stofer's comments. I find my perception wants to give a significance to the colors that is inappropriate. I wasn't a fan of the use of color in the old version either. I'm thinking it wanted alternating colors or alternating lightly shaded background bands.

I'd like to see darker shades of same color perhaps inflecting / changing on the zero of the horizontal axis.

The last graph that combines the old and new styles is interesting especially as it allows one to 'drill down' to the raw data. I'd like to see it with the large bubbles lighter/more transparent -- more as a kind of background to the detail data represented by the data points / tiny bubbles.

Tiny bubbles -- would suggestions for music soundtrack be in order?? ;-)

August 21, 2015 | Unregistered CommenterCortlandt

I vote for the original @DK jitter-plot. For one thing, you can immediately see that the libcon axis is a continuous variable while the gwrisk is discrete. With the @Steve circle-plot, he's had to discretize the gwrisk axis, and the arbitrary choice of how you do this will influence how the plot looks.

Also, I think @Steve hasn't scaled his circles in the right way. Some are huge, others are tiny and almost invisible. I think he's set the radius to be the number in each bin. It would be better to set the radius to be the square root of the number in each bin, so that the area of the circle is proportional to the number. In other words it would be like doing Dan's jitter-plot but arranging the little circles into a neat circular patch instead of jittering them.

August 21, 2015 | Unregistered CommenterPaul Matthews


This is all pretty darn interesting!

You might want to go back & revisit @Thmpn4's frantic, Manhattan-project like effort to develop a 3D color graphic that would allow impact of science comprehension to be displayed w/ partisanship & risk perception all in 1 Figure.

Actually, I think the main problem with his efforts is that he didn't care enough about conveying the density of the observations across the coordinates of his various figures. Obviously, @Steve is obsessed with that!

I agree that being able to observe the density of the observations in "regions of interest" is indeed critical. Seeing sparsely populated regions in the coordinate system is the brilliance of the scatterplot. It's also far too easy to treat noise as signal if one doesn't know that the relationship between 2 or 3 variables in a particular region of the 2- or 3-d plot reflects only a tiny number of observations.

But you'll see that what @Thmpn4 really *loved* was the contrast supplied by color-coding the regions according to a "hot-cold" scheme. Here @Katie & @Cortdlandt find that information not particularly material or even distracting.

Goes to show, I think, why it's so darn hard to do effective graphic reporting of data. Interests and information-processing styles vary a tremendous amount, and on grounds that don't reduce to Numeracy or any other measure of cognitive proficiency.

How to optimize under these conditions is a cool area of study!

August 22, 2015 | Registered CommenterDan Kahan

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>