Two thousand five hundred ways to say the same thing

Wallethub published a credit card debt study, which includes the following map:

Wallethub_creditcardpaydownbyCity

Let's describe what's going on here.

The map plots cities (N = 2,562) in the U.S. Each city is represented by a bubble. The color of the bubble ranges from purple to green, encoding the percentile ranking based on the amount of credit card debt that was paid down by consumers. Purple represents 1st percentile, the lowest amount of paydown while green represents 99th percentile, the highest amount of paydown.

The bubble size is encoding exactly the same data, apparently in a coarser gradation. The more purple the color, the smaller the bubble. The more green the color, the larger the bubble.

***

The design decisions are baffling.

Purple is more noticeable than the green, but signifies the less important cities, with the lesser paydowns.

With over 2,500 bubbles crowding onto the map, over-plotting is inevitable. The purple bubbles are printed last, dominating the attention but those are the least important cities (1st percentile). The green bubbles, despite being larger, lie underneath the smaller, purple bubbles.

What might be the message of this chart? Our best guess is: the map explores the regional variation in the paydown rate of credit card debt.

The analyst provides all the data beneath the map. 

Wallethub_paydownbyCity_data

From this table, we learn that the ranking is not based on total amount of debt paydown, but the amount of paydown per household in each city (last column). That makes sense.

Shouldn't it be ranked by the paydown rate instead of the per-household number? Divide the "Total Credit Card Paydown by City" by "Total Credit Card Debt Q1 2018" should yield the paydown rate. Surprise! This formula yields a column entirely consisting of 4.16%.

What does this mean? They applied the national paydown rate of 4.16% to every one of 2,562 cities in the country. If they had plotted the paydown rate, every city would attain the same color. To create "variability," they plotted the per-household debt paydown amount. Said differently, the color scale encodes not credit card paydown as asserted but amount of credit card debt per household by city.

Here is a scatter plot of the credit card amount against the paydown amount.

Redo_creditcardpaydown_scatter

A perfect alignment!

This credit card debt paydown map is an example of a QDV chart, in which there isn't a clear question, there is almost no data, and the visual contains several flaws. (See our Trifecta checkup guide.) We are presented 2,562 ways of saying the same thing: 4.16%.

 

P.S. [6/22/2018] Added scatter plot, and cleaned up some language.

 

 

 


Steel tariffs, and my new dataviz seminar

I am developing a new seminar aimed at business professionals who want to improve their ability to communicate using charts. I want any guidance to be tool-agnostic, so that attendees can implement them using Excel if that’s their main charting software. Over the 12+ years that I’ve been blogging, certain ideas keep popping up; and I have collected these motifs and organized them for the seminar. This post is about a recent chart that brings up a few of these motifs.

This chart has been making the rounds in articles about the steel tariffs.

2018.03.08steel_1

The chart shows the Top 10 nations that sell steel to the U.S., which together account for 78% of all imports. 

The chart shows a few signs of design. These things caught my eye:

  1. the pie chart on the left delivers the top-line message that 10 countries account for almost 80% of all U.S. steel imports
  2. the callout gives further information about which 10 countries and how much each nation sells to the U.S. This is a nice use of layering
  3. on the right side, progressive tints of blue indicate the respective volumes of imports

On the negative side of the ledger, the chart is marred by three small problems. Each of these problems concerns inconsistency, which creates confusion for readers.

  1. Inconsistent use of color: on the left side, the darker blue indicates lower volume while on the right side, the darker blue indicates higher volume
  2. Inconsistent coding of pie slices: on the right side, the percentages add up to 78% while the total area of the pie is 100%
  3. Inconsistent scales: the left chart carrying the top-line message is notably smaller than the right chart depicting the secondary message. Readers’ first impression is drawn to the right chart.

Easy fixes lead to the following chart:

Redo_steelimports_1

***

The central idea of the new dataviz seminar is that there are many easy fixes that are often missed by the vast majority of people making Excel charts. I will present a stack of these motifs. If you're in the St. Louis area, you get to experience the seminar first. Register for a spot here.

Send this message to your friends and coworkers in the area. Also, contact me if you'd like to bring this seminar to your area.

***

I also tried the following design, which brings out some other interesting tidbits, such as that Canada and Brazil together sell the U.S. about 30% of its imported steel, the top 4 importers account for about 50% of all steel imports, etc. Color is introduced on the chart via a stylized flag coloring.

Redo_steelimports_2

 

 

 

 

 


The tech world in which everyone is below average

Laura pointed me to an infographic about tech worker salaries in major tech hubs (link).

What's wrong with this map?

Entrepreneur_techsalaries_map

The box "Global average" is doubly false. It is not global, and it is not the average!

The only non-American cities included in this survey are Toronto, Paris and London.

The only city with average salary above the "Global average" is San Francisco Bay Area. Since the Bay Area does not outweigh all other cities combined in the number of tech workers, it is impossible to get an average of $135,000.

***

Here is the second chart.

What's wrong with these lines?

Entrepreneur_techsalaries_lines

This chart frustrates the reader's expectations. The reader interprets it as a simple line chart, based on three strong hints:

  • time along the horizontal axis
  • data labels show dollar units
  • lines linking time

Each line seems to show the trend of average tech worker salary, in dollar units.

However, that isn't the designer's intention. Let's zoom in on Chicago and Denver:

Entrepreneur_techsalaries_lines2

The number $112,000 (Denver) sits below the number $107,000 (Chicago). It appears that each chart has its own scale. But that's not the case either.

For a small-multiples setup, we expect all charts should use the same scale. Even though the data labels are absolute dollar amounts, the vertical axis is on a relative scale (percent change). To make things even more complicated, the percent change is computed relative to the minimum of the three annual values, no matter which year it occurs.

Redo_entrepreneurtechsalarieslines2

That's why $106,000 (Chicago) is at the same level as $112,000 (Denver). Those are the minimum values in the respective time series. As shown above, these line charts are easier to understand if the axis is displayed in its true units of percent change.

The choice of using the minimum value as the reference level interferes with comparing one city to the next. For Chicago, the line chart tells us 2015 is about 2 percent above 2016 while 2017 is 6 percent above. For Denver, the line chart tells us that 2016 is about 2 percent above the 2015 and 2017 values. Now what's the message again?

Here I index all lines to the earliest year.

  Redo_junkcharts_entrepreneurtechsalaries_lines

In a Trifecta Checkup analysis (link), I'd be suspicious of the data. Did tech salaries in London really drop by 15-20 percent in the last three years?

 

 


Why line charts are better than area charts

I saw this chart on Business Insider recently:

Businessinsider_dj_2018-02-07

This links to Market Insider, where there is a tool to make different types of charts. Despite the huge drop depicted above, by last week, the Dow Jones index has recovered to the level at the start of 2018:

Marketinsider_dj_line

The same chart can be made as an area chart (called a "mountain chart" by Market Insider).

Marketinsider_dj_area

The painting of the area serves no purpose here because the area doesn't mean anything.

Imagine adding an inch of space to the bottom of each chart. The area chart is sensitive to the choice of the minimum value of the vertical axis while the line chart isn't. Since the data did not change, it's not a good idea for the display to shift perception. That's why I prefer the line chart.


A look at how the New York Times readers look at the others

Nyt_taxcutmiddleclass

The above chart, when it was unveiled at the end of November last year, got some mileage on my Twitter feed so it got some attention. A reader, Eric N., didn't like it at all, and I think he has a point.

Here are several debatable design decisions.

The chart uses an inverted axis. A tax cut (negative growth) is shown on the right while a tax increase is shown on the left. This type of inversion has gotten others in trouble before, namely, the controversy over the gun deaths chart (link). The green/red color coding is used to signal the polarity although some will argue this is bad for color-blind readers. The annotation below the axis is probably the reason why I wasn't confused in the first place but the other charts further down the page do not repeat the annotation, and that's where the interpretation of -$2,000 as a tax increase is unnatural!

The chart does not aggregate the data. It plots 25,000 households with 25,000 points. Because of the variance of the data, it's hard to judge trends. It's easy enough to see that there are more green dots than red but how many more? 10 percent, 20 percent, 40 percent? It's also hard to answer any specific questions, say, about households with a certain range of incomes. There are various ways to aggregate the data, such as heatmaps, histograms, and so on.

For those used to looking at scientific charts, the x- and y-axes are reversed. By convention, we'd have put the income ranges on the horizontal axis and the tax changes (the "outcome" variable) on the vertical axis.

***

The text labels do not describe the data patterns on the chart so much as they offer additional information. To see this, remove the labels as I have done below. Try adding the labels based on what is shown on the chart.

Nyt_taxcutmiddleclass_2

Perhaps it's possible to illustrate those insights with a set of charts.

***

While reading this chart, I kept wondering how those 25,000 households were chosen. This is a sample of  households. The methodology is explained in a footnote, which describes the definition of "middle class" but unfortunately, they forgot to tell us how the 25,000 households were chosen from all such middle-class households.

Nyt_taxcutmiddleclass_footnote

The decision to omit the households with income below $40,000 needs more explanation as it usurps the household-size adjustment. Also, it's not clear that the impact of the tax bill on the households with incomes between $20-40K can be assumed the same as for those above $40K.

Are the 25,000 households is a simple random sample of all "middle class" households or are they chosen in some ways to represent the relative counts? It's also useful to know if they applied the $40K cutoff before or after selecting the 25,000 households. 

Ironically, the media kit of the Times discloses an affluent readership with median household income of almost $190K so it appears that the majority of readers are not represented in the graphic at all!

 


The visual should be easier to read than your data

A reader sent this tip in some time ago and I lost track of who he/she is. This graphic looks deceptively complex.

MW-FW350_1milli_20171016112101_NS

What's complex is not the underlying analysis. The design is complex and so the decoding is complex.

The question of the graphic is a central concern of anyone who's retired: how long will one's savings last? There are two related metrics to describe the durability of the stash, and they are both present on this chart. The designer first presumes that one has saved $1 million for retirement. Then he/she computes how many years the savings will last. That, of course, depends on the cost of living, which naively can be expressed as a projected annual expenditure. The designer allows the cost of living to vary by state, which is the main source of variability in the computations. The time-based and dollar-based metrics are directly linked to one another via a formula.

The design encodes the time metric in a grid of dots, and the dollar-metric in the color of the dots. The expenditures are divided into eight segments, given eight colors from deep blue to deep pink.

Thirteen of those dots are invariable, appearing in every state. Readers are drawn into a ranking of the states, which is nothing but a ranking of costs of living. (We don't know, but presume, that the cost of living computation is appropriate for retirees, and not averaged.) This order obscures any spatial correlation. There are a few production errors in the first row in which the year and month numbers are misstated slightly; the numbers should be monotonically decreasing. In terms of years and months, the difference between many states is immaterial. The pictogram format is more popular than it deserves: only highly motivated readers will count individual dots. If readers are merely reading the printed text, which contains all the data encoded in the dots, then the graphic has failed the self-sufficiency principle - the visual elements are not doing any work.

***

In my version, I surface the spatial correlation using maps. The states are classified into sensible groups that allow a story to be told around the analysis. Three groups of states are identified and separately portrayed. The finer variations between states within each state group appear as shades.

Redo_howlonglive

Data visualization should make the underlying data easier to comprehend. It's a problem when the graphic is harder to decipher than the underlying dataset.

 

 

 


Fifty-nine intersections supporting forty dots of data

My friend Ray V. asked how this chart can be improved:

Econ_rv_therichgetsricher

Let's try to read this chart. The Economist is always the best at writing headlines, and this one is simple and to the point: the rich get richer. This is about inequality but not just inequality - the growth in inequality over time.

Each country has four dots, divided into two pairs. From the legend, we learn that the line represents the gap between the rich and the poor. But what is rich and what is poor? Looking at the sub-header, we learn that the population is divided by domicile, and the per-capita GDP of the poorest and richest regions are drawn. This is a indirect metric, and may or may not be good, depending on how many regions a country is divided into, the dispersion of incomes within each region, the distribution of population between regions, and so on.

Now, looking at the axis labels, it's pretty clear that the data depicted are not in dollars (or currency), despite the reference to GDP in the sub-header. The numbers represent indices, relative to the national average GDP per head. For many of the countries, the poorest region produces about half of the per-capita GDP as the richest region.

Back to the orginal question. A growing inequality would be represented by a longer line below a shorter line within each country. That is true in some of these countries. The exceptions are Sweden, Japan, South Korea.

***
It doesn't jump out that the key task requires comparing the lengths of the two lines. Another issue is the outdated convention of breaking up a line (Britian) when the line is of extreme length - particularly unwise given that the length of the line encodes the key metric in the chart.

Further, it has low data-ink ratio a la Tufte. The gridlines, reference lines, and data lines weave together in a complex pattern creating 59 intersections in a chart that contains only 40  36 numbers.

***

 I decided to compute a simpler metric - the ratio of rich to poor.  For example, in the UK, the richest area produces about 20 times as much GDP per capita as the poorest one in 2015.  That is easier to understand than an index to the average region.

I had fun making the following chart, although many standard forms like the Bumps chart (i.e. slopegraph) or paired columns and so on also work.

Redo_econ_jc_richgetricher

This chart is influenced by Ed Tufte, who spent a good number of pages in his first book advocating stripping even the standard column chart to its bare essence. The chart also acknowledges the power of design to draw attention.

 

 

PS. Sorry I counted incorrectly. The chart has 36 dots not 40. 


Getting into the head of the chart designer

When I look at this chart (from Business Insider), I try to understand the decisions made by its designer - which things are important to her/him, and which things are less important.

Incomegendergapbystate-both-top-2-map-v2

The chart shows average salaries in the top 2 percent of income earners. The data are split by gender and by state.

First, I notice that the designer chooses to use the map form. This decision suggests that the spatial pattern of top incomes is of top interest to the designer because she/he is willing to accept the map's constraints - namely, the designer loses control of the x and y dimensions, as well as the area and shape of the data containers. For the U.S. state map, there is no elegant solution to the large number of small states problem in the Northeast.

Second, I notice the color choice. The designer provides actual values on the visualization but also groups all state-average incomes into five categories. It's not clear how she/he determines the boundaries of these income brackets. There are many more dark blue states than there are light blue states in the map for men. Because women incomes are everywhere lower than men, the map at the bottom fits all states into two large buckets, plus Connecticut. Women incomes are lower than men but there is no need to break the data down by gender to convey this message.

Third, the use of two maps indicates that the designer does not care much about gender comparisons within each state. These comparisons are difficult to accomplish on the chart - one must involuntarily bob one's head up and down to make the comparisons. The head bobbing isn't even enough: then you must pull out your calculator and compute the ratio of women to men average. If the designer wants to highlight state-level comparisons, she/he could have plotted the gender ratio on a single map, like this:

Screen Shot 2017-09-18 at 11.47.23 PM

***

So far, I infer that the key questions are (a) the gender gap in aggregate (b) the variability of incomes within each gender, or the spatial clustering (c) the gender gap within each state.

(a) is better conveyed in more aggregate form. Goal (b) is defeated by the lack of clear clustering. (c) is not helped by the top-bottom split.

In making the above chart, I discover a pattern - that women fare better in the smaller states like Montana, Iowa, North & South Dakota. Meanwhile, the disparity in New York is of the same degree as Oklahoma and Wyoming.

  Jc_redo_top2pcincomes2b

 This chart tells readers a bit more about the underlying data, without having to print the entire dataset on the page.

 

 

 


The salaries are attractive but the chart isn't

Ieee_engineersalaries
The only reason why the IEEE Spectrum magazine editors chose this chart form is because they think they need to deliver precise salary figures to readers.

This chart is just so... sad.

The color scheme is all wrong, the black suggesting a funeral. The printed data occupying at least half of the width of each bar frustrate any attempt to compare lengths. We enter an unusual place where higher numbers appear under smaller numbers. The job titles are regrettably dressed in the same cloth as the median salary bars. It's not clear how the regions are ordered but in any case, it's hard to figure out regional disparities. In reality, no one is getting precisely the listed salaries - rounding up those numbers makes them easier to grasp.

This is a chart that repels rather than attracts readers.

***

A test of sufficiency immediately nails the problem. When the data set is removed, there is almost nothing to see:

Redo_ieeesalaries_sufficiencytest

***

Mid-Atlantic managers are the winners.

Redo_jc_ieeesalaries
 


Another simple Excel chart needs help

Twitter friend Jimmy A. asked if I can help Elon Musk make this chart "more readable".

Elonmusk_commerciallaunch

Let's start with a couple of things he did right. Placing SpaceX, his firm's data, at the bottom of the chart is perfect, as the bottom part of a stacked column chart is the only part that is immediately readable. Combining all of Europe into one category and Other U.S. into one group reduce the number of necessary colors.

Why is this chart unreadable? Here is a line-up of the culprits:

  • Red Russia is stealing the thunder
  • SpaceX is sharing the blues with Japan/China/Other U.S.
  • The legend is sorted in the opposite way as the column segments (courtesy of Excel defaults)
  • Axis labels given to two decimal places for market share split only a small number of ways
  • It's unclear what "market share" means: is it share of the number of launches or the revenues generated by those launches? Is the "base" of the market share changing over time?
  • The last two columns are speculative and these are the two years in which SpaceX has a noticeable advantage (unless they are talking about contracts already concluded)

 According to the underlying data, there are some very big changes at foot. The following small-multiples chart shows what is going on:

Redo_elonmusk_launches