This Excel chart looks standard but gets everything wrong

The following CNBC chart (link) shows the trend of global car sales by region (or so we think).

Cnbc zh global car sales

This type of chart is quite common in finance/business circles, and has the fingerprint of Excel. After examining it, I nominate it for the Hall of Shame.

***

The chart has three major components vying for our attention: (1) the stacked columns, (2) the yellow line, and (3) the big red dashed arrow.

The easiest to interpret is the yellow line, which is labeled "Total" in the legend. It displays the annual growth rate of car sales around the globe. The data consist of annual percentage changes in car sales, so the slope of the yellow line represents a change of change, which is not particularly useful.

The big red arrow is making the point that the projected decline in global car sales in 2019 will return the world to the slowdown of 2008-9 after almost a decade of growth.

The stacked columns appear to provide a breakdown of the global growth rate by region. Looked at carefully, you'll soon learn that the visual form has hopelessly mangled the data.

Cnbc_globalcarsales_2006

What is the growth rate for Chinese car sales in 2006? Is it 2.5%, the top edge of China's part of the column? Between 1.5% and 2.5%, the extant of China's section? The answer is neither. Because of the stacking, China's growth rate is actually the height of the relevant section, that is to say, 1 percent. So the labels on the vertical axis are not directly useful to learning regional growth rates for most sections of the chart.

Can we read the vertical axis as global growth rate? That's not proper either. The different markets are not equal in size so growth rates cannot be aggregated by simple summing - they must be weighted by relative size.

The negative growth rates present another problem. Even if we agree to sum growth rates ignoring relative market sizes, we still can't get directly to the global growth rate. We would have to take the total of the positive rates and subtract the total of the negative rates.  

***

At this point, you may begin to question everything you thought you knew about this chart. Remember the yellow line, which we thought measures the global growth rate. Take a look at the 2006 column again.

The global growth rate is depicted as 2 percent. And yet every region experienced growth rates below 2 percent! No matter how you aggregate the regions, it's not possible for the world average to be larger than the value of each region.

For 2006, the regional growth rates are: China, 1%; Rest of the World, 1%; Western Europe, 0.1%; United States, -0.25%. A simple sum of those four rates yields 2%, which is shown on the yellow line.

But this number must be divided by four. If we give the four regions equal weight, each is worth a quarter of the total. So the overall average is the sum of each growth rate weighted by 1/4, which is 0.5%. [In reality, the weights of each region should be scaled to reflect its market size.]

***

tldr; The stacked column chart with a line overlay not only fails to communicate the contents of the car sales data but it also leads to misinterpretation.

I discussed several serious problems of this chart form: 

  • stacking the columns make it hard to learn the regional data

  • the trend by region takes a super effort to decipher

  • column stacking promotes reading meaning into the height of the column but the total height is meaningless (because of the negative section) while the net height (positive minus negative) also misleads due to presumptive equal weighting

  • the yellow line shows the sum of the regional data, which is four times the global growth rate that it purports to represent

 

***

PS. [12/4/2019: New post up with a different visualization.]


This chart tells you how rich is rich - if you can read it

Via twitter, John B. sent me the following YouGov chart (link) that he finds difficult to read:

Yougov_whoisrich

The title is clear enough: the higher your income, the higher you set the bar.

When one then moves from the title to the chart, one gets misdirected. The horizontal axis shows pound values, so the axis naturally maps to "the higher your income". But it doesn't. Those pound values are the "cutoff" values - the line between "rich" and "not rich". Even after one realizes this detail, the axis  presents further challenges: the cutoff values are arbitrary numbers such as "45,001" sterling; and these continuous numbers are treated as discrete categories, with irregular intervals between each category.

There is some very interesting and hard to obtain data sitting behind this chart but the visual form suppresses them. The best way to understand this dataset is to first think about each income group. Say, people who make between 20 to 30 thousand sterling a year. Roughly 10% of these people think "rich" starts at 25,000. Forty percent of this income group think "rich" start at 40,000.

For each income group, we have data on Z percent think "rich" starts at X. I put all of these data points into a heatmap, like this:

Redo_junkcharts_yougovuk_whoisrich

Technical note: in order to restore the horizontal axis to a continuous scale, you can take the discrete data from the original chart, then fit a smoothed curve through those points, and finally compute the interpolated values for any income level using the smoothing model.

***

There are some concerns about the survey design. It's hard to get enough samples for higher-income people. This is probably why the highest income segment starts at 50,000. But notice that 50,ooo is around the level at which lower-income people consider "rich". So, this survey is primarily about how low-income people perceive "rich" people.

The curve for the highest income group is much straighter and smoother than the other lines - that's because it's really the average of a number of curves (for each 10,000 sterling segment).

 

P.S. The YouGov tweet that publicized the small-multiples chart shown above links to a page that no longer contains the chart. They may have replaced it due to feedback.

 

 


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)


Tennis greats at the top of their game

The following chart of world No. 1 tennis players looks pretty but the payoff of spending time to understand it isn't high enough. The light colors against the tennis net backdrop don't work as intended. The annotation is well done, and it's always neat to tug a legend inside the text.

Tableautennisnumberones

The original is found at Tableau Public (link).

The topic of the analysis appears to be the ages at which tennis players attained world #1 ranking. Here are the male players visualized differently:

Redo_junkcharts_no1tennisplayers

Some players like Jimmy Connors and Federer have second springs after dominating the game in their late twenties. It's relatively rare for players to get to #1 after 30.


Choosing between individuals and aggregates

Friend/reader Thomas B. alerted me to this paper that describes some of the key chart forms used by cancer researchers.

It strikes me that many of the "new" charts plot granular data at the individual level. This heatmap showing gene expressions show one column per patient:

Jnci_genemap

This so-called swimmer plot shows one bar per patient:

Jnci_swimlanes

This spider plot shows the progression of individual patients over time. Key events are marked with symbols.

Jnci_spaghetti

These chart forms are distinguished from other ones that plot aggregated statistics: statistical averages, medians, subgroup averages, and so on.

One obvious limitation of such charts is their lack of scalability. The number of patients, the variability of the metric, and the timing of trends all drive up the amount of messiness.

I am left wondering what Question is being addressed by these plots. If we are concerned about treatment of an individual patient, then showing each line by itself would be clearer. If we are interested in the average trends of patients, then a chart that plots the overall average, or subgroup averages would be more accurate. If the interpretation of the individual's trend requires comparing with similar patients, then showing that individual's line against the subgroup average would be preferred.

When shown these charts of individual lines, readers are tempted to play the statistician - without using appropriate tools! Readers draw aggregate conclusions, performing the aggregation in their heads.

The authors of the paper note: "Spider plots only provide good visual qualitative assessment but do not allow for formal statistical inference." I agree with the second part. The first part is a fallacy - if the visual qualitative assessment is good enough, then no formal inference is necessary! The same argument is often made when people say they don't need advanced analysis because their simple analysis is "directionally accurate". When is something "directionally inaccurate"? How would one know?

Reference: Chia, Gedye, et. al., "Current and Evolving Methods to Visualize Biological Data in Cancer Research", JNCI, 2016, 108(8). (link)

***

Meteoreologists, whom I featured in the previous post, also have their own spider-like chart for hurricanes. They call it a spaghetti map:

Dorian_spaghetti

Compare this to the "cone of uncertainty" map that was featured in the prior post:

AL052019_5day_cone_with_line_and_wind

These two charts build upon the same dataset. The cone map, as we discussed, shows the range of probable paths of the storm center, based on all simulations of all acceptable models for projection. The spaghetti map shows selected individual simulations. Each line is the most likely trajectory of the storm center as predicted by a single simulation from a single model.

The problem is that each predictive model type has its own historical accuracy (known as "skill"), and so the lines embody different levels of importance. Further, it's not immediately clear if all possible lines are drawn so any reader making conclusions of, say, the envelope containing x percent of these lines is likely to be fooled. Eyeballing the "cone" that contains x percent of the lines is not trivial either. We tend to naturally drift toward aggregate statistical conclusions without the benefit of appropriate tools.

Plots of individuals should be used to address the specific problem of assessing individuals.


This Wimbledon beauty will be ageless

Ft_wimbledonage


This Financial Times chart paints the picture of the emerging trend in Wimbledon men’s tennis: the average age of players has been rising, and hits 30 years old for the first time ever in 2019.

The chart works brilliantly. Let's look at the design decisions that contributed to its success.

The chart contains a good amount of data and the presentation is carefully layered, with the layers nicely tied to some visual cues.

Readers are drawn immediately to the average line, which conveys the key statistical finding. The blue dot  reinforces the key message, aided by the dotted line drawn at 30 years old. The single data label that shows a number also highlights the message.

Next, readers may notice the large font that is applied to selected players. This device draws attention to the human stories behind the dry data. Knowledgable fans may recall fondly when Borg, Becker and Chang burst onto the scene as teenagers.

 

Then, readers may pick up on the ticker-tape data that display the spread of ages of Wimbledon players in any given year. There is some shading involved, not clearly explained, but we surmise that it illustrates the range of ages of most of the contestants. In a sense, the range of probable ages and the average age tell the same story. The current trend of rising ages began around 2005.

 

Finally, a key data processing decision is disclosed in chart header and sub-header. The chart only plots the players who reached the fourth round (16). Like most decisions involved in data analysis, this choice has both desirable and undesirable effects. I like it because it thins out the data. The chart would have appeared more cluttered otherwise, in a negative way.

The removal of players eliminated in the early rounds limits the conclusion that one can draw from the chart. We are tempted to generalize the finding, saying that the average men’s player has increased in age – that was what I said in the first paragraph. Thinking about that for a second, I am not so sure the general statement is valid.

The overall field might have gone younger or not grown older, even as the older players assert their presence in the tournament. (This article provides side evidence that the conjecture might be true: the author looked at the average age of players in the top 100 ATP ranking versus top 1000, and learned that the average age of the top 1000 has barely shifted while the top 100 players have definitely grown older.)

So kudos to these reporters for writing a careful headline that stays true to the analysis.

I also found this video at FT that discussed the chart.

***

This chart about Wimbledon players hits the Trifecta. It has an interesting – to some, surprising – message (Q). It demonstrates thoughtful processing and analysis of the data (D). And the visual design fits well with its intended message (V). (For a comprehensive guide to the Trifecta Checkup, see here.)


SCMP's fantastic infographic on Hong Kong protests

In the past month, there have been several large-scale protests in Hong Kong. The largest one featured up to two million residents taking to the streets on June 16 to oppose an extradition act that was working its way through the legislature. If the count was accurate, about 25 percent of the city’s population joined in the protest. Another large demonstration occurred on July 1, the anniversary of Hong Kong’s return to Chinese rule.

South China Morning Post, which can be considered the New York Times of Hong Kong, is well known for its award-winning infographics, and they rose to the occasion with this effort.

This is one of the rare infographics that you’d not regret spending time reading. After reading it, you have learned a few new things about protesting in Hong Kong.

In particular, you’ll learn that the recent demonstrations are part of a larger pattern in which Hong Kong residents express their dissatisfaction with the city’s governing class, frequently accused of acting as puppets of the Chinese state. Under the “one country, two systems” arrangement, the city’s officials occupy an unenviable position of mediating the various contradictions of the two systems.

This bar chart shows the growth in the protest movement. The recent massive protests didn't come out of nowhere. 

Scmp_protestsovertime

This line chart offers a possible explanation for burgeoning protests. Residents’ perceived their freedoms eroding in the last decade.

Scmp_freedomsurvey

If you have seen videos of the protests, you’ll have noticed the peculiar protest costumes. Umbrellas are used to block pepper sprays, for example. The following lovely graphic shows how the costumes have evolved:

Scmp_protestcostume

The scale of these protests captures the imagination. The last part in the infographic places the number of protestors in context, by expressing it in terms of football pitches (as soccer fields are known outside the U.S.) This is a sort of universal measure due to the popularity of football almost everywhere. (Nevertheless, according to Wikipedia, the fields do not have one fixed dimension even though fields used for international matches are standardized to 105 m by 68 m.)

Scmp_protestscale_pitches

This chart could be presented as a bar chart. It’s just that the data have been re-scaled – from counting individuals to counting football pitches-ful of individuals. 

***
Here is the entire infographics.


A chart makes an appearance in my new video

Been experimenting with short videos recently. My latest is a short explainer on why some parents are willing to spend over a million dollars to open back doors to college admissions. I even inserted a chart showing some statistics. Click here to see the video.

 

Also, subscribe to my channel to see future episodes of Inside the Black Box.

***

Here are a couple of recent posts related to college admissions.

  • About those so-called adversity scores (link)
  • A more detailed post on various college admissions statistics (link)

Clarifying comparisons in censored cohort data: UK housing affordability

If you're pondering over the following chart for five minutes or more, don't be ashamed. I took longer than that.

Ft_ukgenerationalhousing

The chart accompanied a Financial Times article about inter-generational fairness in the U.K. To cut to the chase, a recently released study found that younger generations are spending substantially higher proportions of their incomes to pay for housing costs. The FT article is here (behind paywall). FT actually slightly modified the original chart, which I pulled from the Home Affront report by the Intergenerational Commission.

Uk_generational_propincomehousing

One stumbling block is to figure out what is plotted on the horizontal axis. The label "Age" has gone missing. Even though I am familiar with cohort analysis (here, generational analysis), it took effort to understand why the lines are not uniformly growing in lengths. Typically, the older generation is observed for a longer period of time, and thus should have a longer line.

In particular, the orange line, representing people born before 1895 only shows up for a five-year range, from ages 70 to 75. This was confusing because surely these people have lived through ages 20 to 70. I'm assuming the "left censoring" (missing data on the left side) is because of non-existence of old records.

The dataset is also right-censored (missing data on the right side). This occurs with the younger generations (the top three lines) because those cohorts have not yet reached certain ages. The interpretation is further complicated by the range of birth years in each cohort but let me not go there.

TL;DR ... each line represents a generation of Britons, defined by their birth years. The generations are compared by how much of their incomes did they spend on housing costs. The twist is that we control for age, meaning that we compare these generations at the same age (i.e. at each life stage).

***

Here is my version of the same chart:

Junkcharts_redo_ukgenerationalhousing_1

Here are some of the key edits:

  • Vertical blocks are introduced to break up the analysis by life stage. These guide readers to compare the lines vertically i.e. across generations
  • The generations are explicitly described as cohorts by birth years
  • The labels for the generations are placed next to the lines
  • Gridlines are pushed to the back
  • The age axis is explicitly labeled
  • Age labels are thinned
  • A hierarchy on colors
  • The line segments with incomplete records are dimmed

The harmful effect of colors can be seen below. This chart is the same as the one above, except for retaining the colors of the original chart:

Junkcharts_redo_ukgenerationalhousing_2

 

 


Visually exploring the relationship between college applicants and enrollment

In a previous post, we learned that top U.S. colleges have become even more selective over the last 15 years, driven by a doubling of the number of applicants while class sizes have nudged up by just 10 to 20 percent. 

Redo_pewcollegeadmissions

The top 25 most selective colleges are included in the first group. Between 2002 and 2017, their average rate of admission dropped from about 20% to about 10%, almost entirely explained by applicants per student doubling from 10 to almost 20. A similar upward movement in selectivity is found in the first four groups of colleges, which on average accept at least half of their applicants.

Most high school graduates however are not enrolling in colleges in the first four groups. Actually, the majority of college enrollment belongs to the bottom two groups of colleges. These groups also attracted twice as many applicants in 2017 relative to 2002 but the selectivity did not change. They accepted 75% to 80% of applicants in 2002, as they did in 2017.

***

In this post, we look at a different view of the same data. The following charts focus on the growth rates, indexed to 2002. 

Collegeadmissions_5

To my surprise, the number of college-age Americans  grew by about 10% initially but by 2017 has dropped back to the level of 2002. Meanwhile, the number of applications to the colleges continues to climb across all eight groups of colleges.

The jump in applications made selectivity surge at the most selective colleges but at the less selective colleges, where the vast majority of students enroll, admission rate stayed put because they gave out many more offers as applications mounted. As the Pew headline asserted, "the rich gets richer."

Enrollment has not kept up. Class sizes expanded about 10 to 30 percent in those 15 years, lagging way behind applications and admissions.

How do we explain the incremental applications?

  • Applicants increasing the number of schools they apply to
  • The untapped market: applicants who in the past would not have applied to college
  • Non-U.S. applicants: this is part of the untapped market, but much larger