Causes of Death

There are many ways to die. Cancer. Infection. Mental. External. The Centers for Disease Control and Prevention classifies the ways into 113 causes, which are grouped into 20 categories of disease and external causes. The CDC’s Underlying Cause of Death database provides estimates for the number of people who die due to each of the causes.

As you’d expect, some causes of death are more common than others. For example, about a third of people die from diseases of the respiratory system (like the flu), but less than three percent die from infectious or parasitic diseases (like Tuberculosis).

Then take age into account. It’s much more likely for older people to get cancer than it is for younger people.

Finally, look at cause across different groups of people and you see different distributions.

The chart below shows how cause of death varies across sex and race, based on mortality data from 2005 through 2014. Select a group to see the changes. Select causes to see them individually.

The height of any strip in the chart represents the percentage of people who died of a cause out of those who died at that age. For example, of the females who died at age 60, about 40 percent of them died from cancer.

When you select races, you might notice that the smaller groups, American Indian and Asian, appear to be more jagged, whereas cause of death for the larger groups, black and white, appear to be smoother. This is likely due to population size more than anything else. It’s a smaller sample, and there’s higher variance.

So focus on the overall trends and how they change by group.

For example, compare cause of death for female versus male, and you see a big difference for external causes. For females, it accounts for about 5 percent of deaths. It’s twice as common for males, and mostly at a young age pre-40s.

Keep in mind that this shows percentages and not absolute counts. So while the percentage for cancer decreases with age, it doesn’t necessarily mean that people grow impervious. It’s much more likely that with age comes higher susceptibility to other diseases.

How You Will DieHow You Will Die

That’s how people die at various ages. Now here’s a simulation to see how this applies to you.

Nerd Notes

  1. The chart above is a stacked area graph inspired by the now-classic charts from the New York Times on time usage and from Martin Wattenberg on baby names.
  2. I used 2005-2014 data for a more up-to-date view, but the CDC provides data that goes back to 1999. If I had gone back farther, the areas for American Indian and Asian would probably be smoother.
  3. I thought about filters for sex and race at the same time, so that you could compare say, black female versus black male. But I liked the simplicity of one filter at a time better.
  4. The interactive was made with d3.js. Data processing and analysis was in R, which is the main language I think in statistically.

Become a member. Support an independent site. Make great charts.

See What You Get

Learn to Visualize Data See All →

How to Make a Grid Map with Histograms in R, with ggplot

Layout multiple charts in a single view. Then adjust the scales appropriately for maximum comparability and a unified graphic.

How to Make a Heatmap – a Quick and Easy Solution

A heatmap is a literal way of visualizing a table of numbers, where you substitute the numbers with colored cells. This is a quick way to make one in R.

How to Make Stacked Area Charts in R

From the basic area chart, to the stacked version, to the streamgraph, the geometry is similar. Once you know how to do one, you can do them all.

How to Visualize Proportions in R

There are many ways to show parts of a whole. Here are quick one-liners for the more common ones.

Favorites

How Much Minimum Wage Changed in Each State

Minimum wage has increased over the years, but by how much depends on where you live.

Cuisine Ingredients

What are the ingredients that make each cuisine? I looked at 40,000 recipes spanning 20 cuisines and 6,714 ingredients to see what makes food taste different.

The Stages of Relationships, Distributed

Everyone’s relationship timeline is a little different. This animation plays out real-life paths to marriage.

Guessing Names Based on What They Start With

I’m terrible at names, but maybe data can help. Put in your sex, the decade when you were born, and start putting in your name. I’ll try to guess before you’re done.