More on equal-area histograms

Today, I'm returning to those "equal-area histograms" that Andrew wrote about last month. I have two previous posts about this. The first post introduces the concept: in a traditional histogram, the columns have the same bin width while the column heights can represent a variety of metrics, such as counts, relative frequencies (i.e. proportion of the data) and densities; in the equal-area histogram, the columns have varying widths while the area of each column is constant, and determined by the number of bins (columns).

Here is a comparison of the two types of histograms.

In a second post, I explained the differences between using counts, frequencies and densities in the vertical axis. The underlying issue is that the histogram is not merely a column chart, in which the width of the columns is arbitrary and data-free - in the histogram, both the heights and widths of columns carry meaning. One feature of the histogram that almost everyone expects is that the area of the columns sum up to 1. This aligns with a desired interpretation of probabilities of data falling into specified ranges, as we'd like the amount of data in the entire range to add up to 100%. Unfortunately, the two items are usually incompatible with each other.

If the height of the columns represents the probability of data falling into the range as indicated by its width, then the sum of the column heights is 1, which implies that the sum of the column areas cannot be 1. On the other hand, if the column areas add up to 1, then the column heights will not add up to 1, and thus, in this scenario, we cannot interpret the column heights to be probabilities. As explained in the second post, the column heights in this situation are densities, which can be defined as the proportion of data divided by the bin width. Intuitively, it gives information on how dense or sparse the data are within the specified range.

***

Today's post start with a toy dataset, containing randomly generated values from a normal distribution (bell curve) centered at 4 and with standard deviation 1.

Here is the traditional histogram of the dataset, using 100 equal-width bin. (I generated 10,000 values)

Next, I created a panel of four equal-area histograms, with increasingly number of bins. Each is built from the same underlying dataset.

The first histogram divides the data into 4 bins; then 10 bins, 20 bins and 100 bins.

In the 4-bin case, each column contains 1/4 = 25% of the data. The middle two columns contain 50% of the data, and they have high densities, as the widths of these columns are low. It's a crude approximation of the familiar bell curve.

As we increase the number of bins, the columns in the middle of the distribution, where most of the data are concentrated, become narrower. In the sparse regions, the column width doesn't necessarily grow because each column must contain 1/n of the data, where n is the number of columns. As the number of columns increases, each column contains less of the data.

The bottom chart is the "percentogram", which is what Andrew's correspondent proposed. The number of bins is set to 100, so each column contains exactly 1 percent of the data. For a normal distribution, the columns in the middle are very tall and thin.

The reason why the middle of the percentogram looks faded is that I asked for a white border around each column. But when the columns are so thin, even if one sets the border width very small, what readers see is a mixture of orange and white.

With high number of bins, we notice a few things: a) the outline of the histogram becomes "ragged" (the more bins there are), b) the middle columns become razor-thin c) the width conceded by the middle columns is absorbed not by the columns at the edges but those between the peak and the edge.

I'm struggling a bit to justify this percentogram versus the typical, equal-width histogram.

Let me go down a different path.

***

In "principled" histograms, the column heights represent data densities, while the total area of the columns add up to 1. This leads us to a new understanding of the relationship between the equal-width histogram and the equal-area histogram.

We start with data density defined by (proportion of data) / (bin width). Those two values are not independent - one is fully determined by the other, given the underlying dataset. In a traditional equal-width histogram, the question is: how much of the data is found in a column of fixed width? In the new equal-area histogram, the question is: how wide is the bin that contains a fixed amount of data? In the former, the denominator is fixed while the numerator varies; the opposite occurs in the latter.

***

We also recognize that given the range of the data, there is a relationship between the the set of bin widths in the two types of histograms. In the traditional histogram, all bin widths have the same value, equal to the range of the data divided by the number of bins. Think of this as the average bin width. In an equal-area histogram, the set of bin widths varies: however, the sum of the bin widths must still add up to the range of the data. For two comparable histograms with the same number of bins, the average of the bin widths must be the same for both sets. (I'm ignoring any rounding situations in which the range of the histogram is larger than the range of the data.)

Now, consider the middle of the normal distribution where the data are dense. In the traditional histogram, the column in the middle still has width equal to the average bin width. In the equal-area histogram, the middle column has width much smaller than the average bin width. In other words, we can think of the column in the traditional histogram being broken up into many thin and slim columns in the equal-area histogram, each containing 1% of the data in the case of the percentogram.

The height of the column is the data density. In the traditional histogram, the middle column is the pooled sample of larger size; in the equal-area histogram, each of those thin and slim columns is a partition of the sample. This explains observation (a) above in which the outline of the equal-area histogram is more ragged - it's because each column contains fewer data from which to estimate the data density.

But this raggedness is artificial, sampling noise.

***

The sparse areas are more complicated still. It's also the reverse of the above. On the edges of the normal distribution, the columns of the new histogram are wider than those of the traditional histogram. So, we can think of breaking up the edge column of the new histogram into multiple columns of the traditional histogram.

The interpretation is more complicated because the data are sparse in this region. Obviously, the estimates of density on the traditional histogram in sparse regions are poor because not enough data reside in there. The density estimate on the new histogram is based on a larger sample size.

However.

Yes, however, whether the new histogram's density estimate is better depends on the shape of the tail of the distribution. A normal distribution has exponential tails, which means that the data density declines quite drastically the further we go into the tail. Therefore, the new histogram averages the data densities across a large part of the tail, wiping out the exponential shape while the traditional histogram preserves that shape - at the expense of greater sampling variability due to smaller sample sizes.

***

For what it's worth, let's look at some histograms for an exponential random variable.

Here is the traditional histogram:

The data are extremely dense on the left side while it has a long tail on the right side.

Here are the four equal-area histograms for 4, 10, 20 and 100 bins.

The four-bin version gives a nice summary of the shape. As the number of bins goes up, as before, the denser regions now have tall, thin spikes. Again, because of the white borders, the last histogram with 100 bins is faded where the data are densest. (So obviously, don't follow my lead, and eliminate borders if you want to use it.)

The 100-bin version looks almost the same as the traditional histogram.

***

At this stage of the exploration, I still haven't found a compelling reason to switch to equal-area hist0grams. In the denser regions, it's adding sampling noise. If I don't care about the sparser areas, specifically, the shape of the tails, maybe they provide a cleaner presentation.

 

Parsons Student Projects

I had the pleasure of attending the final presentations of this year's graduates from Parsons's MS in Data Visualization program. You can see the projects here.

***

A few of the projects caught my eye.

A project called "Authentic Food in NYC" explores where to find "authentic" cuisine in New York restaurants. The project is notable for plowing through millions of Yelp reviews, and organizing the information within. Reviews mentioning "authentic" or "original" were extracted.

During the live presentation, the student clicked on Authentic Chinese, and the name that popped up was Nom Wah Tea Parlor, which serves dim sum in Chinatown that often has lines out the door.

Curiously, the ranking is created from raw counts of authentic reviews, which favors restaurants with more reviews, such as restaurants that have been operating for a longer time. It's unclear what rule is used to transfer authenticity from reviews to restaurants: does a single review mentioning "authentic" qualify a restaurant as "authentic", or some proportion of reviews?

Later, we see a visualization of the key words found inside "authentic" reviews for each cuisine. Below are words for Chinese and Italian cuisines:

These are word clouds with a twist. Instead of encoding the word counts in the font sizes, she places each word inside a bubble, and uses bubble sizes to indicate relative frequency.

Curiously, almost all the words displayed come from menu items. There isn't any subjective words to be found. Algorithms that extract keywords frequently fail in the sense that they surface the most obvious, uninteresting facts. Take the word cloud for Taiwanese restaurants as an example:

The overwhelming keyword found among reviews of Taiwanese restaurants is... "taiwanese". The next most important word is "taiwan". Among the remaining words, "886" is the name of a specific restaurant, "bento" is usually associated with Japanese cuisine, and everything else is a menu item.

Getting this right is time-consuming, and understandably not a requirement for a typical data visualization course.

The most interesting insight is found in this data table.

It appears that few reviewers care about authenticity when they go to French, Italian, and Japanese restaurants but the people who dine at various Asian restaurants, German restaurants, and Eastern European restaurants want "authentic" food. The student concludes: "since most Yelp reviewers are Americans, their pursuit of authenticity creates its own trap: Food authenticity becomes an americanized view of what non-American food is."

This hits home hard because I know what authentic dim sum is, and Nom Wah Tea Parlor it ain't. Let me check out what Yelpers are saying about Nom Wah:

1. Everything was so authentic and delicious - and cheap!!!
2. Your best bet is to go around the corner and find something more authentic.
3. Their dumplings are amazing everything is very authentic and tasty!
4. The food was delicious and so authentic, and the staff were helpful and efficient.
5. Overall, this place has good authentic dim sum but it could be better.
6. Not an authentic experience at all.
7. this dim sum establishment is totally authentic
8. The onions, bean sprouts and scallion did taste very authentic and appreciated that.
9. I would skip this and try another spot less hyped and more authentic.
10. I would have to take my parents here the next time I visit NYC because this is authentic dim sum.

These are the most recent ten reviews containing the word "authentic". Seven out of ten really do mean authentic, the other three are false friends. Text mining is tough business! The student removed "not authentic" which helps. As seen from above, "more authentic" may be negative, and there may be words between "not" and "authentic". Also, think "not inauthentic", "people say it's authentic, and it's not", etc.

One thing I learned from this project is that "authentic" may be a synonym for "I like it" when these diners enjoy the food at an ethnic restaurant. I'm most curious about what inauthentic onions, bean sprouts and scallion taste like.

I love the concept and execution of this project. Nice job!

***

Another project I like is about tourism in Venezuela. The back story is significant. Since a dictatorship took over the country, the government stopped reporting tourism statistics. It's known that tourism collapsed, and that it may be gradually coming back in recent years.

This student does not have access to ready-made datasets. But she imaginatively found data to pursue this story. Specifically, she mentioned grabbing flight schedules into the country from the outside.

The flow chart is a great way to explore this data:

A map gives a different perspective:

I'm glad to hear the student recite some of the limitations of the data. It's easy to look at these visuals and assume that the data are entirely reliable. They aren't. We don't know that what proportion of the people traveling on those flights are tourists, how full those planes are, or the nationalities of those on board. The fact that a flight originated from Panama does not mean that everyone on board is Panamanian.

***

The third project is interesting in its uniqueness. This student wants to highlight the effect of lead in paint on children's health. She used the weight of lead marbles to symbolize the impact of lead paint. She made a dress with two big pockets to hold these marbles.

It's not your standard visualization. One can quibble that dividing the marbles into two pockets doesn't serve a visualziation purpose, and so on. But at the end, it's a memorable performance.

The one thing you're afraid to ask about histograms

In the previous post about a variant of the histogram, I glossed over a few perplexing issues - deliberately. Today's post addresses one of these topics: what is going on in the vertical axis of a histogram?

The real question is: what data are encoded in the histogram, and where?

***

Let's return to the dataset from the last post. I grabbed data from a set of international football (i.e. soccer) matches. Each goal scored has a scoring minute. If the goal is scored in regulation time, the scoring minute is a number between 1 and 90 minutes. Specifically, the data collector applies a rounding up: any goal scored between 0 and 60 seconds is recorded as 1, all the way up to a goal scored between 89 and 90th minute being recorded as 90. In this post, I only consider goals scored in regulation time so the horizontal axis is between 1-90 minutes.

The kneejerk answer to the posed question is: counts in bins. Isn't it the case that in constructing a histogram, we divide the range of values (1-90) into bins, and then plot the counts within bins, i.e. the number of goals scored within each bin of minutes?

The following is what we have in mind:

Let's call this the "count histogram".

Some readers may dislike the scale of the vertical axis, as its interpretation hinges on the total sample size. Hence, another kneejerk answer is: frequencies in bins. Instead of plotting counts directly, plot frequencies, which are just standardized counts. Just divide each value by the sample size. Here's the "frequency histogram":

The count and frequency histograms are identical except for the scale, and appear intuitively clear. The count and frequency data are encoded in the heights of the columns. The column widths are an afterthought, and they adhere to a fixed constant. Unlike a column chart, typically the gap width in a histogram is zero, as we want to partition the horizontal range into adjoining sections.

Now, if you look carefully at the histogram from the last post, reproduced below, you'd find that it plots neither counts nor frequencies:

The numbers on the axis are fractions, and suggest that they may be frequencies, but a quick check proves otherwise: with 9 columns, the average column should contain at least 10 percent of the data. The total of the displayed fractions is nowhere near 100%, which is our expectation if the values are relative frequencies. You may have come across this strangeness when creating histograms using R or some other software.

The purpose of this post is to explain what values are being plotted and why.

***

What are the kinds of questions we like to answer about the distribution of data?

At a high level, we want to know "where are my data"?

Arguably these two questions are fundamental:

• what is the probability that the data falls within a given range of values? e.g., what is the probability that a goal is scored in the first 15 minutes of a football match?
• what is the relative probability of data between two ranges of values? e.g. are teams more likely to score in last 5 minutes of the first half or the last five minutes of the second half of a football match?

In a histogram, the first question is answered by comparing a given column to the entire set of columns while the second question is answered by comparing one column to another column.

Let's see what we can learn from the count histogram.

In a count histogram, the heights encode the count data. To address the relative probability question, we note that the ratio of heights is the ratio of counts, and the ratio of counts is the same as the ratio of frequencies. Thus, we learn that teams are roughly 3000/1500 = 1.5 times more likely to score in the last 5 minutes of the second half than during the last 5 minutes of the first half. (See the green columns).

[For those who follow football, it's clear that the data collector treated goals scored during injury time of either half as scored during the last minute of the half, so this dataset can't be used to analyze timing of goals unless the real minutes were recorded for injury-time goals.]

To address the range probability question, we compare the aggregate height of the three orange columns with the total heights of all columns. Note that I said "height", not "area," because the heights directly encode counts. It's actually taxing to figure out the total height!

We resort to reading the total area of all columns. This should yield the correct answer: the area is directly proportional to the height because the column widths are fixed as a constant. Bear in mind, though, if the column widths vary (the theme of the last post), then areas and heights are not interchangable concepts.

Estimating the total area is still not easy, especially if the column heights exhibit high variance. What we need is the proportion of the total area that is orange. It's possible to see, not easy.

You may interject now to point out that the total area should equal the aggregate count (sample size). But that is a fallacy! It's very easy to make this error. The aggregate count is actually the total height, and because of that, the total area is the aggregate count multiplied by the column width! In my example, the total height is 23,682, which is the number of goals in the dataset, while the total area is 23,682 times 5 minutes.

[For those who think in equations, the total area is the sum over all columns of height(i) x width(i). When width is constant, we can take it outside the sum, and the sum of height(i) is just the total count.]

***

The count histogram is hard to use because it requires knowing the sample size. It's the first thing that is produced because the raw data are counts in bins. The frequency histogram is better at delivering answers.

In the frequency histogram, the heights encode frequency data. We can therefore just read off the relative probability of the orange column, bypassing the need to compute the total area.

This workaround actually promotes the fallacy described above for the count histogram. It is easy to fall into the trap of thinking that the total area of all columns is 100%. It isn't.

Similar to before, the total height should be the total frequency but the total area is the total frequency multipled by the column width, that is to say, the total area is the reciprocal of the bin width. In the football example, using 5-minute intervals, the total area of the frequency histogram is 1/(5 minutes) in the case of equal bin widths.

How about the relative probability question? On the frequency histogram, the ratio of column heights is the ratio of frequencies, which is exactly what we want. So long as the column width is constant, comparing column heights is easy.

***

One theme in the above discussion is that in the count and frequency histograms, the count and frequency data are encoded in the column heights but not the column areas. This is a source of major confusion. Because of the convention of using equal column widths, one treats areas and heights as interchangable... but not always. The total column area isn't the same as the total column height.

This observation has some unsettling implications.

As shown above, the total area is affected by the column width. The column width in an equal-width histogram is the range of the x-values divided by the number of bins. Thus, the total area is a function of the number of bins.

Consider the following frequency histograms of the same scoring minutes dataset. The only difference is the number of bins used.

Increasing the number of bins has a series of effects:

• the columns become narrower
• the columns become shorter, because each narrower bin can contain at most the same count as the wider bin that contains it.
• the total area of the columns become smaller.

This last one is unexpected and completely messes up our intuition. When we increase the number of bins, not only are the columns shortening but the total area covered by all the columns is also shrinking. Remember that the total area whether it is a count or frequency histogram has a factor equal to the bin width. Higher number of bins means smaller bin width, which means smaller total area.

***

What if we force the total area to be constant regardless of how many bins we use? This setting seems more intuitive: in the 5-bin histogram, we partition the total area into five parts while in the 10-bin histogram, we divide it into 10 parts.

This is the principle used by R and the other statistical software when they produce so-called density histograms. The count and frequency data are encoded in the column areas - by implication, the same data could not have been encoded simultaneously in the column heights!

The way to accomplish this is to divide by the bin width. If you look at the total area formulas above, for the count histogram, total area is total count x bin width. If the height is count divided by bin width, then the total area is the total count. Similarly, if the height in the frequency histogram is frequency divided by bin width, then the total area is 100%.

Count divided by some section of the x-range is otherwise known as "density". It captures the concept of how tightly the data are packed inside a particular section of the dataset. Thus, in a count-density histogram, the heights encode densities while the areas encode counts. In this case, total area is the total count. If we want to standardize total area to be 1, then we should compute densities using frequencies rather than counts. Frequency densities are just count densities divided by the total count.

To summarize, in a frequency-density histogram, the heights encode densities, defined as frequency divided by the bin width. This is not very intuitive; just think of densities as how closely packed the data are in the specified bin. The column areas encode frequencies so that the total area is 100%.

The reason why density histograms are confusing is that we are reading off column heights while thinking that the total area should add up to 100%. Column heights and column areas cannot both add up to 100%. We have to pick one or the other.

Comparing relative column heights still works when the density histogram has equal bin widths. In this case, the relative height and relative area are the same because relative density equals relative frequencies if the bin width is fixed.

The following charts recap the discussion above. It shows how the frequency histogram does not preserve the total area when bin sizes are changed while the density histogram does.

***

The density histogram is a major pain for solving range probability questions because the frequencies are encoded in the column areas, not the heights. Areas are not marked out in a graph.

The column height gives us densities which are not probabilities. In order to retrieve probabilities, we have to multiply the density by the bin width, that is to say, we must estimate the area of the column. That requires mapping two dimensions (width, height) onto one (area). It is in fact impossible without measurement - unless we make the bin widths constant.

When we make the bin widths constant, we still can't read densities off the vertical axis, and treat them as probabilities. If I must use the density histogram to answer the question of how likely a team scores in the first 15 minutes, I'd sum the heights of the first 3 columns, which is about 0.025, and then multiply it by the bin width of 5 minutes, which gives 0.125 or 12.5%.

At the end of this exploration, I like the frequency histogram best. The density histogram is useful when we are comparing different histograms, which isn't the most common use case.

***

The histogram is a basic chart in the tool kit. It's more complicated than it seems. I haven't come across any intro dataviz books that explain this clearly.

Most of this post deals with equal-width histograms. If we allow bin widths to vary, it gets even more complicated. Stay tuned.

***

For those using base R graphics, I hope this post helps you interpret what they say in the manual. The default behavior of the "hist" function depends on whether the bins are equal width:

• if the bin width is constant, then R produces a count histogram. As shown above, in a count histogram, the column heights indicate counts in bins but the total column area does not equal the total sample size, but the total sample size multiplied by the bin width. (Equal width is the default unless the user specifies bin breakpoints.)
• if the bin width is not constant, then R produces a (frequency-)density histogram. The column heights are densities, defined as frequencies divided by bin width while the column areas are frequencies, with the total area summing to 100%.

Unfortunately, R does not generate a frequency histogram. To make one, you'd have to divide the counts in bins by the sum of counts. (In making some of the graphs above, I tricked it.) You also need to trick it to make a frequency-density histogram with equal-width bins, as it's coded to produce a count histogram when bin size is fixed.

 

P.S. [5-2-2023] As pointed out by a reader, I should clarify that R and I use the word "frequency" differently. Specifically, R uses frequency to mean counts, therefore, what I have been calling the "count histogram", R would have called it a "frequency histogram", and what I have been describing as a "frequency histogram", the "hist" function simply does not generate it unless you trick it to do so. I'm using "frequency" in the everyday sense of the word, such as "the frequency of the bus". In many statistical packages, frequency is used to mean "count", as in the frequency table which is just a table of counts. The reader suggested proportion which I like, or something like weight.

 

 

 

 

 

Finding the story in complex datasets

In CT Mirror's feature about Connecticut, which I wrote about in the previous post, there is one graphic that did not rise to the same level as the others.

This section deals with graduation rates of the state's high school districts. The above chart focuses on exactly five districts. The line charts are organized in a stack. No year labels are provided. The time window is 11 years from 2010 to 2021. The column of numbers show the difference in graduation rates over the entire time window.

The five lines look basically the same, if we ignore what looks to be noisy year-to-year fluctuations. This is due to the weird aspect ratio imposed by stacking.

Why are those five districts chosen? Upon investigation, we learn that these are the five districts with the biggest improvement in graduation rates during the 11-year time window.

The same five schools also had some of the lowest graduation rates at the start of the analysis window (2010). This must be so because if a school graduated 90% of its class in 2010, it would be mathematically impossible for it to attain a 35% percent point improvement! This is a dissatisfactory feature of the dataviz.

***

In preparing an alternative version, I start by imagining how readers might want to utilize a visualization of this dataset. I assume that the readers may have certain school(s) they are particularly invested in, and want to see its/their graduation performance over these 11 years.

How does having the entire dataset help? For one thing, it provides context. What kind of context is relevant? As discussed above, it's futile to compare a school at the top of the ranking to one that is near the bottom. So I created groups of schools. Each school is compared to other schools that had comparable graduation rates at the start of the analysis period.

Amistad School District, which takes pole position in the original dataviz, graduated only 58% of its pupils in 2010 but vastly improved its graduation rate by 35% over the decade. In the chart below (left panel), I plotted all of the schools that had graduation rates between 50 and 74% in 2010. The chart shows that while Amistad is a standout, almost all schools in this group experienced steady improvements. (Whether this phenomenon represents true improvement, or just grade inflation, we can't tell from this dataset alone.)

The right panel shows the group of schools with the next higher level of graduation rates in 2010. This group of schools too increased their graduation rates almost always. The rate of improvement in this group is lower than in the previous group of schools.

The next set of charts show school districts that already achieved excellent graduation rates (over 85%) by 2010. The most interesting group of schools consists of those with 85-89% rates in 2010. Their performance in 2021 is the most unpredictable of all the school groups. The majority of districts did even better while others regressed.

Overall, there is less variability than I'd expect in the top two school groups. They generally appeared to have been able to raise or maintain their already-high graduation rates. (Note that the scale of each chart is different, and many of the lines in the second set of charts are moving within a few percentages.)

One more note about the charts: The trend lines are "smoothed" to focus on the trends rather than the year to year variability. Because of smoothing, there is some awkward-looking imprecision e.g. the end-to-end differences read from the curves versus the observed differences in the data. These discrepancies can easily be fixed if these charts were to be published.

Thoughts on Daniel's fix for dual-axes charts

I've taken a little time to ponder Daniel Z's proposed "fix" for dual-axes charts (link). The example he used is this:

In that long post, Daniel explained why he preferred to mix a line with columns, rather than using the more common dual lines construction: to prevent readers from falsely attributing meaning to crisscrossing lines. There are many issues with dual-axes charts, which I won't repeat in this post; one of their most dissatisfying features is the lack of connection between the two vertical scales, and thus, it's pretty easy to manufacture an image of correlation when it doesn't exist. As shown in this old post, one can expand or restrict one of the vertical axes and shift the line up and down to "match" the other vertical axis.

Daniel's proposed fix retains the dual axes, and he even restores the dual lines construction.

How is this chart different from the typical dual-axes chart, like the first graph in this post?

Recall that the problem with using two axes is that the designer could squeeze, expand or shift one of the axes in any number of ways to manufacture many realities. What Daniel effectively did here is selecting one specific way to transform the "New Customers" axis (shown in gray).

His idea is to run a simple linear regression between the two time series. Think of fitting a "trendline" in Excel between Revenues and New Customers. Then, use the resulting regression equation to compute an "estimated" revenues based on the New Customers series. The coefficients of this regression equation then determines the degree of squeezing/expansion and shifting applied to the New Customers axis.

The main advantage of this "fix" is to eliminate the freedom to manufacture multiple realities. There is exactly one way to transform the New Customers axis.

The chart itself takes a bit of time to get used to. The actual values plotted in the gray line are "estimated revenues" from the regression model, thus the blue axis values on the left apply to the gray line as well. The gray axis shows the respective customer values. Because we performed a linear fit, each value of estimated revenues correspond to a particular customer value. The gray line is thus a squeezed/expanded/shifted replica of the New Customers line (shown in orange in the first graph). The gray line can then be interpreted on two connected scales, and both the blue and gray labels are relevant.

***

What are we staring at?

The blue line shows the observed revenues while the gray line displays the estimated revenues (predicted by the regression line). Thus, the vertical gaps between the two lines are the "residuals" of the regression model, i.e. the estimation errors. If you have studied Statistics 101, you may remember that the residuals are the components that make up the R-squared, which measures the quality of fit of the regression model. R-squared is the square of r, which stands for the correlation between Customers and the observed revenues. Thus the higher the (linear) correlation between the two time series, the higher the R-squared, the better the regression fit, the smaller the gaps between the two lines.

***

There is some value to this chart, although it'd be challenging to explain to someone who has not taken Statistics 101.

While I like that this linear regression approach is "principled", I wonder why this transformation should be preferred to all others. I don't have an answer to this question yet.

***

Daniel's fix reminds me of a different, but very common, chart.

This chart shows actual vs forecasted inflation rates. This chart has two lines but only needs one axis since both lines represent inflation rates in the same range.

We can think of the "estimated revenues" line above as forecasted or expected revenues, based on the actual number of new customers. In particular, this forecast is based on a specific model: one that assumes that revenues is linearly related to the number of new customers. The "residuals" are forecasting errors.

In this sense, I think Daniel's solution amounts to rephrasing the question of the chart from "how closely are revenues and new customers correlated?" to "given the trend in new customers, are we over- or under-performing on revenues?"

Instead of using the dual-axes chart with two different scales, I'd prefer to answer the question by showing this expected vs actual revenues chart with one scale.

This does not eliminate the question about the "principle" behind the estimated revenues, but it makes clear that the challenge is to justify why revenues is a linear function of new customers, and no other variables.

Unlike the dual-axes chart, the actual vs forecasted chart is independent of the forecasting method. One can produce forecasted revenues based on a complicated function of new customers, existing customers, and any other factors. A different model just changes the shape of the forecasted revenues line. We still have two comparable lines on one scale.

 

 

 

 

 

All about Connecticut

This dataviz project by CT Mirror is excellent. The project walks through key statistics of the state of Connecticut.

Here are a few charts I enjoyed.

The first one shows the industries employing the most CT residents. The left and right arrows are perfect, much better than the usual dot plots.

The industries are sorted by decreasing size from top to bottom, based on employment in 2019. The chosen scale is absolute, showing the number of employees. The relative change is shown next to the arrow heads in percentages.

The inclusion of both absolute and relative scales may be a source of confusion as the lengths of the arrows encode the absolute differences, not the relative differences indicated by the data labels. This type of decision is always difficult for the designer. Selecting one of the two scales may improve clarity but induce loss aversion.

***

The next example is a bumps chart showing the growth in residents with at least a bachelor's degree.

This is more like a slopegraph as it appears to draw straight lines between two time points 9 years apart, omitting the intervening years. Each line represents a state. Connecticut's line is shown in red. The message is clear. Connecticut is among the most highly educated out of the 50 states. It maintained this advantage throughout the period.

I'd prefer to use solid lines for the background states, and the axis labels can be sparser.

It's a little odd that pretty much every line has the same slope. I'm suspecting that the numbers came out of a regression model, with varying slopes by state, but the inter-state variance is low.

In the online presentation, one can click on each line to see the values.

***

The final example is a two-sided bar chart:

This shows migration in and out of the state. The red bars represent the number of people who moved out, while the green bars represent those who moved into the state. The states are arranged from the most number of in-migrants to the least.

I have clipped the bottom of the chart as it extends to 50 states, and the bottom half is barely visible since the absolute numbers are so small.

I'd suggest showing the top 10 states. Then group the rest of the states by region, and plot them as regions. This change makes the chart more compact, as well as more useful.

***

There are many other charts, and I encourage you to visit and support this data journalism.

 

 

 

Yet another off radar plot 2

In the last post, I described my experience reading the radar plot, by Bloomberg Graphics, that compares countries in terms of their citizens' post-retirement lives.

I used a different approach:

Instead of focusing on the actual time points (ages), my chart highlights the variance from the OECD averages.

The chart compares countries along three metrics: total life expectancy (including healthy and unhealthy periods), effective retirement age, and the number of healthy years in retirement, which is the issue of greatest interest.

From the above chart, France and Luxembourg have the same profiles. Their citizens live a year or two above the average life expectancy. They retire about 5 years earlier than average, and enjoy about 5 more years of healthy retirement.

Meanwhile, the life expectancy of Americans is about the same as the average OECD resident. Retirement also occurs around the same age as the OECD average. Nevertheless, Americans end up with fewer years of healthy retirement than the OECD average.

 

 

The blue mist

The New York Times printed several charts about Twitter "blue checks," and they aren't one of their best efforts (link).

Blue checks used to be credentials given to legitimate accounts, typically associated with media outlets, celebrities, brands, professors, etc. They are free but must be approved by Twitter. Since Elon Musk acquired Twitter, he turned blue checks into a revenue generator. Yet another subscription service (but you're buying "freedom"!). Anyone can get a blue check for US$8 per month.

[The charts shown here are scanned from the printed edition.]

The first chart is a scatter plot showing the day of joining Twitter and the total number of followers the account has as of early November, 2022. Those are very strange things to pair up on a scatter plot but I get it: the designer could only work with the data that can be pulled down from Twitter's API.

What's wrong with the data? It would seem the interesting question is whether blue checks are associated with number of followers. The chart shows only Twitter Blue users so there is nothing to compare to. The day of joining Twitter is not the day of becoming "Twitter Blue", almost surely not for any user (Nevetheless, the former is not a standard data element released by Twitter). The chart has a built-in time bias since the longer an account exists, one would assume the higher the number of followers (assuming all else equal). Some kind of follower rate (e.g. number of followers per year of existence) might be more informative.

Still, it's hard to know what the chart is saying. That most Blue accounts have fewer than 5,000 followers? I also suspect that they chopped off the top of the chart (outliers) and forgot to mention it. Surely, some of the celebrity accounts have way over 150,000 followers. Another sign that the top of the chart was removed is that an expected funnel effect is not seen. Given the follower count is cumulative from the day of registration, we'd expect the accounts that started in the last few months should have markedly lower counts than those created years ago. (This is even more true if there is a survivorship bias - less successful accounts are more likely to be deleted over time.)

The designer arbitrarily labelled six specific accounts ("Crypto influencer", "HBO fan", etc.) but this feature risks sending readers the wrong message. There might be one HBO fan account that quickly grew to 150,000 followers in just a few months but does the data label suggest to readers that HBO fan accounts as a group tend to quickly attain high number of followers?

***

The second chart, which is an inset of the first, attempts to quantify the effect of the Musk acquisition on the number of "registrations and subscriptions". In the first chart, the story was described as "Elon Musk buys Twitter sparking waves of new users who later sign up for Twitter Blue".

The second chart confuses me. I was trying to figure out what is counted in the vertical axis. This was before I noticed the inset in the first chart, easy to miss as it is tucked into the lower right corner. I had presumed that the axis would be the same as in the first chart since there weren't any specific labels. In that case, I am looking at accounts with 0 to 500 followers, pretty inconsequential accounts. Then, the chart title uses the words "registrations and subscriptions." If the blue dots on this chart also refer to blue-check accounts as in the first chart, then I fail to see how this chart conveys any information about registrations (wbich presumably would include free accounts). As before, new accounts that aren't blue checks won't appear.

Further, to the extent that this chart shows a surge in subscriptions, we are restricted to accounts with fewer than 500 followers, and it's really unclear what proportion of total subscribers is depicted. Nor is it possible to estimate the magnitude of this surge.

Besides, I'm seeing similar densities of the dots across the entire time window between October 2021 and 2022. Perhaps the entire surge is hidden behind the black lines indicating the specific days when Musk announced and completed the acquisition, respectively. If the surge is hiding behind the black vertical lines, then this design manages to block the precise spots readers are supposed to notice.

Here is where we can use the self-sufficiency test. Imagine the same chart without the text. What story would you have learned from the graphical elements themselves? Not much, in my view.

***

The third chart isn't more insightful. This chart purportedly shows suspended accounts, only among blue-check accounts.

From what I could gather (and what I know about Twitter's API), the chart shows any Twitter Blue account that got suspended at any time. For example, all the black open circles occurring prior to October 27, 2022 represent suspensions by the previous management, and presumably have nothing to do with Elon Musk, or his decision to turn blue checks into a subscription product.

There appears to be a cluster of suspensions since Musk took over. I am not sure what that means. Certainly, it says he's not about "total freedom". Most of these suspended accounts have fewer than 50 followers, and only been around for a few weeks. And as before, I'm not sure why the analyst decided to focus on accounts with fewer than 500 followers.

What could have been? Given the number of suspended accounts are relatively small, an interesting analysis would be to form clusters of suspended accounts, and report on the change in what types of accounts got suspended before and after the change of management.

***

The online article (link) is longer, filling in some details missing from the printed edition.

There is one view that shows the larger accounts:

While more complete, this view isn't very helpful as the biggest accounts are located in the sparsest area of the chart. The data labels again pick out strange accounts like those of adult film stars and an Arabic news site. It's not clear if the designer is trying to tell us that most of Twitter Blue accounts belong to those categories.

***
See here for commentary on other New York Times graphics.

 

 

 

 

Finding the right context to interpret household energy data

Bloomberg's recent article on surging UK household energy costs, projected over this winter, contains data about which I have long been intrigued: how much energy does different household items consume?

A twitter follower alerted me to this chart, and she found it informative.

***
If the goal is to pick out the appliances and estimate the cost of running them, the chart serves its purpose. Because the entire set of data is printed, a data table would have done equally well.

I learned that the mobile phone costs almost nothing to charge: 1 pence for six hours of charging, which is deemed a "single use" which seems double what a full charge requires. The games console costs 14 pence for a "single use" of two hours. That might be an underestimate of how much time gamers spend gaming each day.

***

Understanding the design of the chart needs a bit more effort. Each appliance is measured by two metrics: the number of hours considered to be "single use", and a currency value.

It took me a while to figure out how to interpret these currency values. Each cost is associated with a single use, and the duration of a single use increases as we move down the list of appliances. Since the designer assumes a fixed cost of electicity (shown in the footnote as 34p per kWh), at first, it seems like the costs should just increase from top to bottom. That's not the case, though.

Something else is driving these numbers behind the scene, namely, the intensity of energy use by appliance. The wifi router listed at the bottom is turned on 24 hours a day, and the daily cost of running it is just 6p. Meanwhile, running the fridge and freezer the whole day costs 41p. Thus, the fridge&freezer consumes electricity at a rate that is almost 7 times higher than the router.

The chart uses a split axis, which artificially reduces the gap between 8 hours and 24 hours. Here is another look at the bottom of the chart:

***

Let's examine the choice of "single use" as a common basis for comparing appliances. Consider this:

• Continuous appliances (wifi router, refrigerator, etc.) are denoted as 24 hours, so a daily time window is also implied
• Repeated-use appliances (e.g. coffee maker, kettle) may be run multiple times a day
• Infrequent use appliances may be used less than once a day

I prefer standardizing to a "per day" metric. If I use the microwave three times a day, the daily cost is 3 x 3p = 9 p, which is more than I'd spend on the wifi router, run 24 hours. On the other hand, I use the washing machine once a week, so the frequency is 1/7, and the effective daily cost is 1/7 x 36 p = 5p, notably lower than using the microwave.

The choice of metric has key implications on the appearance of the chart. The bubble size encodes the relative energy costs. The biggest bubbles are in the heating category, which is no surprise. The next largest bubbles are tumble dryer, dishwasher, and electric oven. These are generally not used every day so the "per day" calculation would push them lower in rank.

***

Another noteworthy feature of the Bloomberg chart is the split legend. The colors divide appliances into five groups based on usage category (e.g. cleaning, food, utility). Instead of the usual color legend printed on a corner or side of the chart, the designer spreads the category labels around the chart. Each label is shown the first time a specific usage category appears on the chart. There is a presumption that the reader scans from top to bottom, which is probably true on average.

I like this arrangement as it delivers information to the reader when it's needed.

 

 

 

People flooded this chart presented without comment with lots of comments

The recent election in Italy has resulted in some dubious visual analytics. A reader sent me this Excel chart:

In brief, an Italian politician (trained as a PhD economist) used the graph above to make a point that support of the populist Five Star party (M5S) is highly correlated with poverty - the number of people on RDC (basic income). "Senza commento" - no comment needed.

Except a lot of people noticed the idiocy of the chart, and ridiculed it.

The chart appeals to those readers who don't spend time understanding what's being plotted. They notice two lines that show similar "trends" which is a signal for high correlation.

It turns out the signal in the chart isn't found in the peaks and valleys of the "trends".  It is tempting to observe that when the blue line peaks (Campania, Sicilia, Lazio, Piedmonte, Lombardia), the orange line also pops.

But look at the vertical axis. He's plotting the number of people, rather than the proportion of people. Population varies widely between Italian provinces. The five mentioned above all have over 4 million residents, while the smaller ones such as Umbira, Molise, and Basilicata have under 1 million. Thus, so long as the number of people, not the proportion, is plotted, no matter what demographic metric is highlighted, we will see peaks in the most populous provinces.

***

The other issue with this line chart is that the "peaks" are completely contrived. That's because the items on the horizontal axis do not admit a natural order. This is NOT a time-series chart, for which there is a canonical order. The horizontal axis contains a set of provinces, which can be ordered in whatever way the designer wants.

The following shows how the appearance of the lines changes as I select different metrics by which to sort the provinces:

This is the reason why many chart purists frown on people who use connected lines with categorical data. I don't like this hard rule, as my readers know. In this case, I have to agree the line chart is not appropriate.

***

So, where is the signal on the line chart? It's in the ratio of the heights of the two values for each province.

Here, we find something counter-intuitive. I've highlighted two of the peaks. In Sicilia, about the same number of people voted for Five Star as there are people who receive basic income. In Lombardia, more than twice the number of people voted for Five Star as there are people who receive basic income. 

Now, Lombardy is where Milan is, essentially the richest province in Italy while Sicily is one of the poorest. Could it be that Five Star actually outperformed their demographics in the richer provinces?

***

Let's approach the politician's question systematically. He's trying to say that the Five Star moement appeals especially to poorer people. He's chosen basic income as a proxy for poverty (this is like people on welfare in the U.S.). Thus, he's divided the population into two groups: those on welfare, and those not.

What he needs is the relative proportions of votes for Five Star among these two subgroups. Say, Five Star garnered 30% of the votes among people on welfare, and 15% of the votes among people not on welfare, then we have a piece of evidence that Five Star differentially appeals to people on welfare. If the vote share is the same among these two subgroups, then Five Star's appeal does not vary with welfare.

The following diagram shows the analytical framework:

What's the problem? He doesn't have the data needed to establish his thesis. He has the total number of Five Star voters (which is the sum of the two yellow boxes) and he has the total number of people on RDC (which is the dark orange box).

As shown above, another intervening factor is the proportion of people who voted. It is conceivable that the propensity to vote also depends on one's wealth.

So, in this case, fixing the visual will not fix the problem. Finding better data is key.