« October 2016 | Main | December 2016 »

Involuntary head-shaking is probably not an intended consequence of data visualization

This chart is in the Sept/Oct edition of Harvard Magazine:

Naep scores - Nov 29 2016 - 4-21 PM

Pretty standard fare. It even is Tufte-sque in the sparing use of axes, labels, and other non-data-ink.

Does it bug you how much work you need to do to understand this chart?

Here is the junkchart version:


In the accompanying article, the journalist declared that student progress on NAEP tests came to a virtual standstill, and this version highlights the drop in performance between the two periods, as measured by these "gain scores."

The clarity is achieved through proximity as well as slopes.

The column chart form has a number of deficiencies when used to illustrate this data. It requires too many colors. It induces involuntary head-shaking.

Most unforgivingly, it leaves us with a puzzle: does the absence of a column means no progress or unknown?


PS. The inclusion of 2009 on both time periods is probably an editorial oversight.



Political winds and hair styling

Washington Post (link) and New York Times (link) published dueling charts last week, showing the swing-swang of the political winds in the U.S. Of course, you know that the pendulum has shifted riotously rightward towards Republican red in this election.

The Post focused its graphic on the urban / not urban division within the country:


Over Twitter, Lazaro Gamio told me they are calling these troll-hair charts. You certainly can see the imagery of hair blowing with the wind. In small counties (right), the wind is strongly to the right. In urban counties (left), the straight hair style has been in vogue since 2008. The numbers at the bottom of the chart drive home the story.

Previously, I discussed the Two Americas map by the NY Times, which covers a similar subject. The Times version emphasizes the geography, and is a snapshot while the Post graphic reveals longer trends.

Meanwhile, the Times published its version of a hair chart.


This particular graphic highlights the movement among the swing states. (Time moves bottom to top in this chart.) These states shifted left for Obama and marched right for Trump.

The two sets of charts have many similarities. They both use curvy lines (hair) as the main aesthetic feature. The left-right dimension is the anchor of both charts, and sways to the left or right are important tropes. In both presentations, the charts provide visual aid, and are nicely embedded within the story. Neither is intended as exploratory graphics.

But the designers diverged on many decisions, mostly in the D(ata) or V(isual) corner of the Trifecta framework.


The Times chart is at the state level while the Post uses county-level data.

The Times plots absolute values while the Post focuses on relative values (cumulative swing from the 2004 position). In the Times version, the reader can see the popular vote margin for any state in any election. The middle vertical line is keyed to the electoral vote (plurality of the popular vote in most states). It is easy to find the crossover states and times.

The Post's designer did some data transformations. Everything is indiced to 2004. Each number in the chart is the county's current leaning relative to 2004. Thus, left of vertical means said county has shifted more blue compared to 2004. The numbers are cumulative moving top to bottom. If a county is 10% left of center in the 2016 election, this effect may have come about this year, or 4 years ago, or 8 years ago, or some combination of the above. Again, left of center does not mean the county voted Democratic in that election. So, the chart must be read with some care.

One complaint about anchoring the data is the arbitrary choice of the starting year. Indeed, the Times chart goes back to 2000, another arbitrary choice. But clearly, the two teams were aiming to address slightly different variations of the key question.

There is a design advantage to anchoring the data. The Times chart is noticeably more entangled than the Post chart. There are tons more criss-crossing. This is particularly glaring given that the Times chart contains many fewer lines than the Post chart, due to state versus county.

Anchoring the data to a starting year has the effect of combing one's unruly hair. Mathematically, they are just shifting the lines so that they start at the same location, without altering the curvature. Of course, this is double-edged: the re-centering means the left-blue / right-red interpretation is co-opted.

On the Times chart, they used a different coping strategy. Each version of their charts has a filter: they highlight the set of lines to demonstrate different vignettes: the swing states moved slightly to the right, the Republican states marched right, and the Democratic states also moved right. Without these filters, the readers would be winking at the Times's bad-hair day.


Another decision worth noting: the direction of time. The Post's choice of top to bottom seems more natural to me than the Times's reverse order but I am guessing some of you may have different inclinations.

Finally, what about the thickness of the lines? The Post encoded population (voter) size while the Times used electoral votes. This decision is partly driven by the choice of state versus county level data.

One can consider electoral votes as a kind of log transformation. The effect of electorizing the popular vote is to pull the extreme values to the center. This significantly simplifies the designer's life. To wit, in the Post chart (shown nbelow), they have to apply a filter to highlight key counties, and you notice that those lines are so thick that all the other countries become barely visible.



Mapping the two Americas

If you type "two Americas map" into Google image search, you get the following top results:


Designers overwhelmingly pick the choropleth map as the way to depitct the two nations.

Now, look at these maps from the New York Times (link):


and this:


I believe the background is a relief map. Would like to see one where the color is based on the strength of support for Democrats or Republicans.

The pair of maps is extremely effective at bringing out the story about the splitting of the U.S. population. From a design standpoint, I really like it.

I love, love, love the cute annotations everywhere on the page. I imagine the designer had fun coming up with them.


Pittsburgh Puddle, Cleveland Cove, Cincinnati Slough, ...


There is an artistic (or data journalistic) license behind the way the data are processed. Most likely, a 50% cutoff is applied to determine which map a county sits atop. The analysis is at the county level so there is neccessarily some simplification... in fact, this aggregation is needed to make the "islands" and other features contiguous.

I am a bit sad that at this moment, we are so focused on what sets us apart, and not what binds us together as a nation.


PS. Via twitter, Maciej reacted negatively to these maps: "Horribly tendentious map visualization from the NYT makes the candidate who won more votes look like a tiny minority."

This is a good illustration of selecting the chart form to bring out one's message. If the goal of the chart is to show that Clinton has more votes, I agree that these maps fail to convey that message.

What I believe the NYT designer wants to point out is that the supporters of Clinton are clustered into these densely populated urban areas, leaving the Republicans with most of the land mass. (Like I said above, because of the 50% cutoff criterion, we are over-simplifying the picture. There are definitely Democrats living somewhere in Trump's nation, and likewise Republicans residing in Clinton strongholds.)

Here are the cool graphics from the election

There were some very nice graphics work published during the last few days of the U.S. presidential election. Let me tell you why I like the following four charts.

FiveThirtyEight's snake chart


This chart definitely hits the Trifecta. It is narrowly focused on the pivotal questions of election night: which candidate is leading? if current projections hold, which candidate would win? how is the margin of victory?

The chart is symmetric so that the two sides have equal length. One can therefore immediately tell which side is in the lead by looking at the middle. With a little more effort, one can also read from the chart which side has more electoral votes based only on the called states: this would be by comparing the white parts of each snake. (This is made difficult by the top-bottom mirroring. That is an unfortunate design decision - I'd would have preferred to not have the top-bottom reversal.)

The length of each segment maps to the number of electoral votes for the particular state, and the shade of colors reflect the size of the advantage.

In a great illustration of less is more, by aggregating all called states into a single white segment, and not presenting the individual results, the 538 team has delivered a phenomenal chart that is refreshing, informative, and functional.

 Compare with a more typical map:


 New York Times's snake chart

Snakes must be the season's gourmet meat because the New York Times also got inspired by those reptiles by delivering a set of snake charts (link). Here's one illustrating how different demographic segments picked winners in the last four elections.



They also made a judicious decision by highlighting the key facts and hiding the secondary ones. Each line connects four points of data but only the beginning and end of each line are labeled, inviting readers to first and foremost compare what happened in 2004 with what happened in 2016. The middle two elections were Obama wins.

This particular chart may prove significant for decades to come. It illustrates that the two parties may be arriving at a cross-over point. The Democrats are driving the lower income classes out of their party while the upper income classes are jumping over to blue.

While the chart's main purpose is to display the changes within each income segment, it does allow readers to address a secondary question. By focusing only on the 2004 endpoints, one can see the almost linear relationship between support and income level. Then focusing on the 2016 endpoints, one can also see an almost linear relationship but this is much steeper, meaning the spread is much narrower compared to the situation in 2004. I don't think this means income matters a lot less - I just think this may be the first step in an ongoing demographic shift.

This chart is both fun and easy to read, packing quite a bit of information into a small space.


Washington Post's Nation of Peaks

The Post prints a map that shows, by county, where the votes were and how the two Parties built their support. (Link to original)


The height represents the number of voters and the width represents the margin of victory. Landslide victories are shown with bolded triangles. In the online version, they chose to turn the map sideways.

I particularly like the narratives about specific places.

This is an entertaining visual that draws you in to explore.


Andrew Gelman's Insight

If you want quantitative insights, it's a good idea to check out Andrew Gelman's blog.

This example is a plain statistical graphic but it says something important:


There is a lot of noise about how the polls were all wrong, the entire polling industry will die, etc.

This chart shows that the polls were reasonably accurate about Trump's vote share in most Democratic states. In the Republican states, these polls consistently under-estimated Trump's advantage. You see the line of red states starting to bend away from the diagonal.

If the total error is about 2%, as stated in the caption of the chart, then the average error in the red states must have been about 4%.

This basic chart advances our understanding of what happened on election night, and why the result was considered a "shock."



How will the Times show election results next week? Will they give us a cliffhanger?

I don't know for sure how the New York Times will present election results next week; it's going to be as hard to predict as the outcome of the election!

The Times just published a wonderful article describing all the different ways election results have been displayed in the past.

tldr; The designer has to make hard choices. Some graphics are better at one thing but worse at another. If the designer can prioritize the Qs, then the choice will come naturally. This is why the Q corner is at the top of the Trifecta framework (link).

Nytimes_election_2000I particularly like the non-map shown right, published in 2000.

This chart doesn't answer every question you want. But it gives a sense of how the candidates built their path to victory.

The imagery of a building works well here. The foundation of a building is its bottom, consisting of states which lean heavily to one party or the other. These foundational blocks scale with either the skew of the support or the number of electoral votes. The lower down in the building, the more solid is the bloc, which makes a lot of sense.

The three-tier color scheme helpfully separates partisan states, competitive states and swing states.

It's not easy to learn the exact vote totals for each state but the vertical axis is pure Tufte and sufficient for most readers.

All in all, this graphic is top-notch. It takes a little time to perfect but not too much. It has clear takeaways and I feel like I learned much more from this chart than I could in a "purple map" type of rendition.


There is a little room for augmentation. It's how they handled the "undecided" states. For me, that is the suspense of this graphic. It's the cliffhanger.

Staring at the chart for the first time, I find that it doesn't address the question of the night: who won? Neither of the "buildings" hit the 270 level required to win the election. Also, there isn't a current vote count so readers have to figure out how many votes are required to win. That's frustrating.

There is an annotation in the middle right, explaining that three states with 37 votes have not yet issued results. That text is better placed near the peaks of the buildings next to the gap where the undecided states would eventually show up.

Also, it is interesting to expand the graphic a bit to address the question of who's likely to win and how. With three states remaining that can go either way, there are eight possible scenarios. It turns out that everything comes down to Florida. Whoever wins Florida wins the election. The other two contests don't matter! (Florida has 25 votes, New Mexico 7, Oregon 5. Gore needs 16 more votes, and Bush needs 24.)

Here is one way to present these scenarios. A little bit of hover-over effect will help here, to provide some details of each scenario.





An example of focusing the chart on a message

Via Jimmy Atkinson on Twitter, I am alerted to this chart from the Wall Street Journal.


The title of the article is "Fiscal Constraints Await the Next President." The key message is that "the next president looks to inherit a particularly dismal set of fiscal circumstances." Josh Zumbrun, who tipped Jimmy about this chart on Twitter, said that it is worth spending time on.

I like the concept of the chart, which juxtaposes the economic condition that faced each president at inauguration, and how his performance measured against expectation, as represented by CBO predictions.

The top portion of the graphic did require significant time to digest:


A glance at the sidebar informs me that there are two scenarios being depicted, the CBO projections and the actual deficit-to-GDP ratios. Then I got confused on several fronts.

One can of course blame the reader (me) for mis-reading the chart but I think dataviz faces a "the reader is always right" situation -- although there can be multiple types of readers for a given graphic so maybe it should say "the readers are always right."

I kept lapsing into thinking that the bold lines (in red and blue) are actual values while the gray line/area represents the predictions. That's because in most financial charts, the actual numbers are in the foreground and the predictions act as background reference materials. But in this rendering, it's the opposite.

For a while, a battle was raging in my head. There are a few clues that the bold red/blue lines cannot represent actual values. For one thing, I don't recall Reagan as a surplus miracle worker. Also, some of the time periods overlap, and one assumes that the CBO issued one projection only at a given time. The Obama line also confused me as the headline led me to expect an ugly deficit but the blue line is rather shallow.

Then, I got even more confused by the units on the vertical axis. According to the sidebar, the metric is deficit-to-GDP ratio. The majority of the line live in the negative territory. Does the negative of the negative imply positive? Could the sharp upward turn of the Reagan line indicate massive deficit spending? Or maybe the axis should be relabelled surplus-to-GDP ratio?


As I proceeded to re-create this graphic, I noticed that some of the tick marks are misaligned. There are various inconsistencies related to the start of each projection, the duration of the projection, the matching between the boxes and the lines, etc. So the data in my version is just roughly accurate.

To me, this data provide a primary reference to how presidents perform on the surplus/deficit compared to expectations as established by the CBO projections.


I decided to only plot the actual surplus/deficit ratios for the duration of each president's tenure. The start of each projection line is the year in which the projection is made (as per the original). We can see the huge gap in every case. Either the CBO analysts are very bad at projections, or the presidents didn't do what they promised during the elections.