Plotting the signal or the noise

Antonio alerted me to the following graphic that appeared in the Economist. This is a playful (?) attempt to draw attention to racism in the game of football (soccer).

The analyst proposed that non-white players have played better in stadiums without fans due to Covid19 in 2020 because they have not been distracted by racist abuse from fans, using Italy's Serie A as the case study.

Econ_seriea_racism

The chart struggles to bring out this finding. There are many lines that criss-cross. The conclusion is primarily based on the two thick lines - which show the average performance with and without fans of white and non-white players. The blue line (non-white) inched to the right (better performance) while the red line (white) shifted slightly to the left.

If the reader wants to understand the chart fully, there's a lot to take in. All (presumably) players are ranked by the performance score from lowest to highest into ten equally sized tiers (known as "deciles"). They are sorted by the 2019 performance when fans were in the stadiums. Each tier is represented by the average performance score of its members. These are the values shown on the top axis labeled "with fans".

Then, with the tiers fixed, the players are rated in 2020 when stadiums were empty. For each tier, an average 2020 performance score is computed, and compared to the 2019 performance score.

The following chart reveals the structure of the data:

Junkcharts_redo_seriea_racism

The players are lined up from left to right, from the worst performers to the best. Each decile is one tenth of the players, and is represented by the average score within the tier. The vertical axis is the actual score while the horizontal axis is a relative ranking - so we expect a positive correlation.

The blue line shows the 2019 (with fans) data, which are used to determine tier membership. The gray dotted line is the 2020 (no fans) data - because they don't decide the ranking, it's possible that the average score of a lower tier (e.g. tier 3 for non-whites) is higher than the average score of a higher tier (e.g. tier 4 for non-whites).

What do we learn from the graphic?

It's very hard to know if the blue and gray lines are different by chance or by whether fans were in the stadium. The maximum gap between the lines is not quite 0.2 on the raw score scale, which is roughly a one-decile shift. It'd be interesting to know the variability of the score of a given player across say 5 seasons prior to 2019. I suspect it could be more than 0.2. In any case, the tiny shifts in the averages (around 0.05) can't be distinguished from noise.

***

This type of analysis is tough to do. Like other observational studies, there are multiple problems of biases and confounding. Fan attendance was not the only thing that changed between 2019 and 2020. The score used to rank players is a "Fantacalcio algorithmic match-level fantasy-football score." It's odd that real-life players should be judged by their fantasy scores rather than their on-the-field performance.

The causal model appears to assume that every non-white player gets racially abused. At least, the analyst didn't look at the curves above and conclude, post-hoc, that players in the third decile are most affected by racial abuse - which is exactly what has happened with the observational studies I have featured on the book blog recently.

Being a Serie A fan, I happen to know non-white players are a small minority so the error bars are wider, which is another issue to think about. I wonder if this factor by itself explains the shifts in those curves. The curve for white players has a much higher sample size thus season-to-season fluctuations are much smaller (regardless of fans or no fans).

 

 

 

 


Visualizing change over time: case study via Arstechnica

ArsTechnica published the following chart in its article titled "Grim new analyses spotlight just how hard the U.S. is failing in  pandemic" (link).

Artechnica-covid-mortality

There are some very good things about this chart, so let me start there.

In a Trifecta Checkup, I'd give the Q corner high marks. The question is clear: how has the U.S. performed relative to other countries? In particular, the chart gives a nuanced answer to this question. The designer realizes that there are phases in the pandemic, so the same question is asked three times: how has the U.S. performed relative to other countries since June, since May, and since the start of the pandemic?

In the D corner, this chart also deserves a high score. It selects a reasonable measure of mortality, which is deaths per population. It simplifies cognition by creating three grades of mortality rates per 100,000. Grade A is below 5 deaths, Grade B, between 5 and 25, and Grade C is above 25. 

A small deduction for not including the source of the data (the article states it's from a JAMA article). If any reader notices problems with the underlying data or calculations, please leave a comment.

***

So far so good. And yet, you might feel like I'm over-praising a chart that feels distinctly average. Not terrible, not great.

The reason for our ambivalence is the V corner. This is what I call a Type V chart. The visual design isn't doing justice to the underlying question and data analysis.

The grouped bar chart isn't effective here because the orange bars dominate our vision. It's easy to see how each country performed over the course of the pandemic but it's hard to learn how countries compare to each other in different periods.

How are the countries ordered? It would seem like the orange bars may be the sorting variable but this interpretation fails in the third group of countries.

The designer apparently made the decision to place the U.S. at the bottom (i.e. the worst of the league table). As I will show later, this is justified but the argument cannot be justified by the orange bars alone. The U.S. is worse in both the blue and purple bars but not the orange.

This points out that there is interest in the change in rates (or ranks) over time. And in the following makeover, I used the Bumps chart as the basis, as its chief use is in showing how ranking changes over time.

Redo_junkcharts_at_coviddeathstable_1

 

Better clarity can often be gained by subtraction:

Redo_junkcharts_at_coviddeathstable_2


Working with multiple dimensions, an example from Germany

An anonymous reader submitted this mirrored bar chart about violent acts by extremists in the 16 German states.

Germanextremists_bars

At first glance, this looks like a standard design. On a second look, you might notice what the reader discovered- the chart used two different scales, one for each side. The left side (red) depicting left-wing extremism is artificially compressed relative to the right side (blue). Not sure if this reflects the political bias of the publication - but in any case, this distortion means the only way to consume this chart is to read the numbers.

Even after fixing the scales, this design is challenging for the reader. It's unnatural to compare two years by looking first below then above. It's not simple to compare across states, and even harder to compare left- and right-wing extremism (due to mirroring).

The chart feels busy because the entire dataset is printed on it. I appreciate not including a redundant horizontal axis. (I wonder if the designer first removed the axis, then edited the scale on one side, not realizing the distortion.) Another nice touch, hidden in the legend, is the country totals.

I present two alternatives.

The first is a small-multiples "bumps chart".

Redo_junkcharts_germanextremists_sidebysidelines

Each plot presents the entire picture within a state. You can see the general level of violence, the level of left- and right-wing extremism, and their year-on-year change. States can be compared holistically.

Several German state names are rather long, so I explored a horizontal orientation. In this case, a connected dot plot may be more appropriate.

Redo_junkcharts_germanextremists_dots

The sign of a good multi-dimensional visual display is whether readers can easily learn complex relationships. Depending on the question of interest, the reader can mentally elevate parts of this chart. One can compare the set of blue arrows to the set of red arrows, or focus on just blue arrows pointing right, or red arrows pointing left, or all arrows for Berlin, etc.

 

[P.S. Anonymous reader said the original chart came from the Augsburger newspaper. This link in German contains more information.]


When the pie chart is more complex than the data

The trading house, Charles Schwab, included the following graphic in a recent article:

Charleschwab_portfolio_1000

This graphic is more complicated than the story that it illustrates. The author describes a simple scenario in which an investor divides his investments into stocks, bonds and cash. After a stock crash, the value of the portfolio declines.

The graphic is a 3-D pie chart, in which the data are encoded twice, first in the areas of the sectors and then in the heights of the part-cylinders.

As readers, we perceive the relative volumes of the part-cylinders. Volume is the cross-sectional area (i.e. of the base) multipled by the height. Since each component holds the data, the volumes are proportional to the squares of the data.

Here is a different view of the same data:

Redo_junkcharts_schwab_portfolio

This "bumps chart" (also called a slopegraph) shows clearly the only thing that drives the change is the drop in stock prices. Because the author assumes no change in bonds or cash, the drop in the entire portfolio is completely accounted for by the decline in stocks. Of course, this scenario seems patently unrealistic - different investment asset classes tend to be correlated.

***

A cardinal rule of data visualization is that the visual should be less complex than the data.


Graph literacy, in a sense

Ben Jones tweeted out this chart, which has an unusual feature:

Malefemaleliteracyrates

What's unusual is that time runs in both directions. Usually, the rule is that time runs left to right (except, of course, in right-to-left cultures). Here, the purple area chart follows that convention while the yellow area chart inverts it.

On the one hand, this is quite cute. Lines meeting in the middle. Converging. I get it.

On the other hand, every time a designer defies conventions, the reader has to recognize it, and to rationalize it.

In this particular graphic, I'm not convinced. There are four numbers only. The trend on either side looks linear so the story is simple. Why complicate it using unusual visual design?

Here is an entirely conventional bumps-like chart that tells the story:

Redo_literacyratebygender

I've done a couple of things here that might be considered controversial.

First, I completely straightened out the lines. I don't see what additional precision is bringing to the chart.

Second, despite having just four numbers, I added the year 1996 and vertical gridlines indicating decades. A Tufte purist will surely object.

***

Related blog post: "The Return on Effort in Data Graphics" (link)


The Bumps come to the NBA, courtesy of 538

The team at 538 did a post-mortem of their in-season forecasts of NBA playoffs, using Bumps charts. These charts have a long history and can be traced back to Cambridge rowing. I featured them in these posts from a long time ago (link 1, link 2). 

Here is the Bumps chart for the NBA West Conference showing all 15 teams, and their ranking by the 538 model throughout the season. 

Fivethirtyeight_nbawest_bumps

The highlighted team is the Kings. It's a story of ascent especially in the second half of the season. It's also a story of close but no cigar. It knocked at the door for the last five weeks but failed to grab the last spot. The beauty of the Bumps chart is how easy it is to see this story.

Now, if you'd focus on the dotted line labeled "Makes playoffs," and note that beyond the half-way point (1/31), there are no further crossings. This means that the 538 model by that point has selected the eight playoff teams accurately.

***

Now what about NBA East?

Fivethirtyeight_nbaeast_bumps

This chart highlights the two top teams. This conference is pretty easy to predict at the top. 

What is interesting is the spaghetti around the playoff line. The playoff race was heart-stopping and it wasn't until the last couple of weeks that the teams were settled. 

Also worthy of attention are the bottom-dwellers. Note that the chart is disconnected in the last four rows (ranks 12 to 15). These four teams did not ever leave the cellar, and the model figured out the final rankings around February.

Using a similar analysis, you can see that the model found the top 5 teams by mid December in this Conference, as there are no further crossings beyond that point. 

***
Go check out the FiveThirtyEight article for their interpretation of these charts. 

While you're there, read the article about when to leave the stadium if you'd like to leave a baseball game early, work that came out of my collaboration with Pravin and Sriram.


Message-first visualization

Sneaky Pete via Twitter sent me the following chart, asking for guidance:

Sneakypete_twitter

This is a pretty standard dataset, frequently used in industry. It shows a breakdown of a company's profit by business unit, here classified by "state". The profit projection for the next year is measured on both absolute dollar terms and year-on-year growth.

Since those two metrics have completely different scales, in both magnitude and unit, it is common to use dual axes. In the case of the Economist, they don't use dual axes; they usually just print the second data series in its own column.

***

I first recommended looking at the scatter plot to see if there are any bivariate patterns. In this case, not much insights are provided via the scatter.

From there, I looked at the data again, and ended up with the following pair of bumps charts (slopegraphs):

Redo_jc_sneakypete

A key principle I used is message-first. That is to say, the designer should figure out what message s/he wants to convey via the visualization, and then design the visualization to convey that message.

A second key observation is that the business units are divided into two groups, the two large states (A and F) and the small states (B to E). This is a Pareto principle that very often applies to real-world businesses, i.e. a small number of entities contribute most of the revenues (or profits). It is very likely that these businesses are structured to serve the large and small states differently, and so the separation onto two charts mirrors the internal structure.

Then, within each chart, there is a message. For the large states, it looks like state F is projected to overtake state A next year. That is a big deal because we're talking about the largest unit in the entire company.

For the small states, the standout is state B, decidedly more rosy than the other three small states with similar projected growth rates.

Note also I chose to highlight the actual dollar profits, letting the growth rates be implied in the slopes. Usually, executives are much more concerned about hitting a dollar value than a growth rate target. But that, of course, depends on your management's preference.

 


Crazy rich Asians inspire some rich graphics

On the occasion of the hit movie Crazy Rich Asians, the New York Times did a very nice report on Asian immigration in the U.S.

The first two graphics will be of great interest to those who have attended my free dataviz seminar (coming to Lyon, France in October, by the way. Register here.), as it deals with a related issue.

The first chart shows an income gap widening between 1970 and 2016.

Nyt_crazyrichasians_incomegap1

This uses a two-lines design in a small-multiples setting. The distance between the two lines is labeled the "income gap". The clear story here is that the income gap is widening over time across the board, but especially rapidly among Asians, and then followed by whites.

The second graphic is a bumps chart (slopegraph) that compares the endpoints of 1970 and 2016, but using an "income ratio" metric, that is to say, the ratio of the 90th-percentile income to the 10th-percentile income.

Nyt_crazyrichasians_incomeratio2

Asians are still a key story on this chart, as income inequality has ballooned from 6.1 to 10.7. That is where the similarity ends.

Notice how whites now appears at the bottom of the list while blacks shows up as the second "worse" in terms of income inequality. Even though the underlying data are the same, what can be seen in the Bumps chart is hidden in the two-lines design!

In short, the reason is that the scale of the two-lines design is such that the small numbers are squashed. The bottom 10 percent did see an increase in income over time but because those increases pale in comparison to the large incomes, they do not show up.

What else do not show up in the two-lines design? Notice that in 1970, the income ratio for blacks was 9.1, way above other racial groups.

Kudos to the NYT team to realize that the two-lines design provides an incomplete, potentially misleading picture.

***

The third chart in the series is a marvellous scatter plot (with one small snafu, which I'd get t0).

Nyt_crazyrichasians_byethnicity

What are all the things one can learn from this chart?

  • There is, as expected, a strong correlation between having college degrees and earning higher salaries.
  • The Asian immigrant population is diverse, from the perspectives of both education attainment and median household income.
  • The largest source countries are China, India and the Philippines, followed by Korea and Vietnam.
  • The Indian immigrants are on average professionals with college degrees and high salaries, and form an outlier group among the subgroups.

Through careful design decisions, those points are clearly conveyed.

Here's the snafu. The designer forgot to say which year is being depicted. I suspect it is 2016.

Dating the data is very important here because of the following excerpt from the article:

Asian immigrants make up a less monolithic group than they once did. In 1970, Asian immigrants came mostly from East Asia, but South Asian immigrants are fueling the growth that makes Asian-Americans the fastest-expanding group in the country.

This means that a key driver of the rapid increase in income inequality among Asian-Americans is the shift in composition of the ethnicities. More and more South Asian (most of whom are Indians) arrivals push up the education attainment and household income of the average Asian-American. Not only are Indians becoming more numerous, but they are also richer.

An alternative design is to show two bubbles per ethnicity (one for 1970, one for 2016). To reduce clutter, the smaller ethnicites can be aggregated into Other or South Asian Other. This chart may help explain the driver behind the jump in income inequality.

 

 

 

 

 


Two good charts can use better titles

NPR has this chart, which I like:

Npr_votersgunpolicy

It's a small multiples of bumps charts. Nice, clear labels. No unnecessary things like axis labels. Intuitive organization by Major Factor, Minor Factor, and Not a Factor.

Above all, the data convey a strong, surprising, message - despite many high-profile gun violence incidents this year, some Democratic voters are actually much less likely to see guns as a "major factor" in deciding their vote!

Of course, the overall importance of gun policy is down but the story of the chart is really about the collapse on the Democratic side, in a matter of two months.

The one missing thing about this chart is a nice, informative title: In two months, gun policy went from a major to a minor issue for some Democratic voters.

***

 I am impressed by this Financial Times effort:

Ft_millennialunemploy

The key here is the analysis. Most lazy analyses compare millennials to other generations but at current ages but this analyst looked at each generation at the same age range of 18 to 33 (i.e. controlling for age).

Again, the data convey a strong message - millennials have significantly higher un(der)employment than previous generations at their age range. Similar to the NPR chart above, the overall story is not nearly as interesting as the specific story - it is the pink area ("not in labour force") that is driving this trend.

Specifically, millennial unemployment rate is high because the proportion of people classified as "not in labour force" has doubled in 2014, compared to all previous generations depicted here. I really like this chart because it lays waste to a prevailing theory spread around by reputable economists - that somehow after the Great Recession, demographics trends are causing the explosion in people classified as "not in labor force". These people are nobodies when it comes to computing the unemployment rate. They literally do not count! There is simply no reason why someone just graduated from college should not be in the labour force by choice. (Dean Baker has a discussion of the theory that people not wanting to work is a long term trend.)

The legend would be better placed to the right of the columns, rather than the top.

Again, this chart benefits from a stronger headline: BLS Finds Millennials are twice as likely as previous generations to have dropped out of the labour force.

 

 

 

 


Several problems with stacked bar charts, as demonstrated by a Delta chart designer

In the Trifecta Checkup (link), I like to see the Question and the Visual work well together. Sometimes, you have a nice message but you just pick the wrong Visual.

An example is the following stacked column chart, used in an investor presentation by Delta.

Delta_aircraft

From what I can tell, the five types of aircraft are divided into RJ (regional jet) and others (perhaps, larger jets). With each of those types, there are two or three subtypes. The primary message here is the reduction in the RJ fleet and the expansion of Small/Medium/Large.

One problem with a stacked column chart with five types is that it takes too much effort to understand the trends of the middle types.

The two types on the edges are not immune to confusion either. As shown below, both the dark blue (Large) type and the dark red (50-seat RJ) type are associated with downward sloping lines except that the former type is growing rapidly while the latter is vanishing from the mix!

Redo_delta_aircraft

 In this case, the slopegraph (Bumps-type chart) can overcome some of the limitations.

Redo_deltaaircraft_2

***

This example was used in my new dataviz workshop, launched in St. Louis yesterday. Thank you to the participants for making it a lively session!