All 4 books by Edward Tufte now in
paperback editions, $100 for all 4
Visual Display of Quantitative Information
Envisioning Information
Visual Explanations
Beautiful Evidence
Paper/printing = original clothbound books.
Only available through ET's Graphics Press:
catalog + shopping cart
Edward Tufte e-books
Immediate download to any computer
connected to the internet:
La Representación Visual de Información
Cuantitativa, (200 páginas) $12
Visual and Statistical Thinking, $2
The Cognitive Style of Powerpoint, $2
Seeing Around + Feynman Diagrams, $2
Data Analysis for Politics and Policy, $2
catalog + shopping cart
Edward Tufte one-day course,
Presenting Data and Information
San Jose, May 5, 6, 6
San Francisco, May 7, 8, 9
Bethesda, June 3
Arlington, June 5, 6
Portland, August 4
Seattle, August 5, 6
Cancer survival rates: tables, slopegraphs, barcharts

-- Edward Tufte

Showing data about cancer survival rates

Many papers reported the recent findings concerning long-term survival rates of cancer patients that indicated an alternative
method of looking at the data yielded more favorable rates. Some of the news stories compared the old and new estimates
for a few types of cancers. But the important issue is: What are the new estimates? The original article provided this table of
relative survival rate (and standard error) for various types of cancer.

The survival cohorts consist of different people and so there are wobbles in the data, as indicated by the standard errors in the table.
Thus thyroid cancer, for example, is not the road to eternal life. The journalistic allergy to tables of data in the news
section (not in the sports or financial section however) denied their readers some interesting information.

Here is that table:

Source: Hermann Brenner, "Long-term survival rates of cancer patients achieved by the end of the 20th century:
a period analysis," The Lancet, 360 (October 12, 2002), 1131-1135.

-- Edward Tufte

Some redesigns by ET

The original table can be redesigned to express particular aspects of the data.
Here the types of cancer are ordered by 5-year survival rates:

For most presentations, this table with its structure and reporting of standard errors will be the best way to see
the cancer data. The table-graphic below, however, gives an idea of survival time gradients for each cancer. In
the table-graphic and in the original table, every visual element contributes directly to understanding.

To begin to think about variability in mortality, see the essential article Stephen Jay Gould here at our site

On to some other data display methods.

Applying the widely-used default designs for statistical graphics in PowerPoint to this nice straightforward table yields these analytical disasters below. "Sweet songs never last too long on broken radios," as John Prine wrote. The data explode into 6 separate chaotic slides, consuming several times the area of the table. Everything is wrong with these smarmy, nearly unreadable graphs: incoherent, uncomparative, low data-density, encoded legends, color without content, logotype branding, chartjunk, indifference to content and evidence. Chartjunk is a clear sign of statistical stupidity; use these designs in a presentation and your audience will rightly conclude that you don't know all that much about statistical data. Poking a finger into the eye of thought, these graphics would turn into a particularly nasty prank if ever used for a serious purpose, such as cancer patients seeking to assess their survival chances. To deal with a product that clutters and corrupts data with such systematic intensity must require an enormous insulation from statistical reasoning by Microsoft PP executives and programmers, PP textbook writers, and presenters of such chartjunk.

PP-style graphical chartjunk shows up in evidence presentations in scientific journals. Below, the clutter half-conceals thin data with some vibrating pyramids framed by an unintentional Necker illusion, as the 2 back planes optically flip to the front:

For such small data sets, usually a simple table shows the data more effectively than a graph, let alone a chartjunk graph. Source of graph: N. T. Kouchoukos, et al., "Replacement of the Aortic Root with a Pulmonary Autograft in Children and Young Adults with Aortic-Valve Disease," New England Journal of Medicine, 330 (January 6, 1994), p. 4. On chartjunk, see Edward R. Tufte, The Visual Display of Quantitative Information (Cheshire, CT, 1983; second edition, 2001), chapter 5.

-- Edward Tufte

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

As a cancer survivor myself, I agree with Mr. Tufte that the Power Point charts are almost maliciously bad and a torment to worried patients. I shudder at the thought that physicians who make treatment decisions are using such bad tools.

-- Paul Sampson (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

I've experienced the same wonderful "chart-junk" that the rest of you do.

Our company uses the 3-D charts and graphs with the company color scheme. The 3-D graphs are not clear and they actually obfuscate the true value of what's being presented.

I'd like to see another option for creating a graph or chart in PowerPoint. The good thing is that you can always create them yourself, if you're a programmer.

I think that people who are presenting all too often think that their audience needs to be entertained. They just need to get better to get better content.

If you want an interesting take on what Microsoft has as "Ten tips for creating effective PowerPoint presentations", follow the link. http://www.microsoft.com/office/using/column08.asp The interesting thing is that I only see one principle that Mr. Tufte advocates. Practice.

-- Sean Gerety (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

The most useful of PowerPoint's default options is to start your presentation with a blank page. (As with any other endeavor of graphic design, the most useful creative tool is the clean slate.) Used as a vector-and-text drawing program, PowerPoint can be used to develop perfectly readable and useful info-graphics that are optimized for digital projection.

-- Bill Reader (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

Apple now has Keynote. http://www.apple.com/keynote/charts.html has examples of some charts. No false third dimensions. Graphs start at 0 and have a clean look. Apple appreciates good design. A complimentary copy of ET's The Visual Display of Quantitative Information might do a lot of good, though Steve Jobs may have read it already.

Shadowing is one feature that is advertised on the page as available for more punch. Perhaps not as bad as gratuitous dimensions. Any thoughts?

-- Steve (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

Alas the Keynote examples are as data-thin as PowerPoint. Only a few data points, no multivariate examples. Both Keynote and PP are tinker toyish.

By the way, real scientists don't show the zero point; they show the data. In general, the zero point should only be shown if it occurs reasonably near the range of the actual data. Instead of empty space vertically reaching down to a number which never occurs empirically, the way to show context is more data horizontally. Note that The Visual Display of Quantitative Information never recommends showing zero-points. See pp. 74-75 for a seqeuence of displays that provide increasing context by showing more data horizontally rather than reaching down to a zero point.

-- Edward Tufte

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

Interesting reply, as I expected. In biology serum pH would never sensibly include 0 in a graph. One would be dead shortly after dipping below 7.0. Perhaps we should be appreciative of graphs with thin data. That way we can see when conclusions are being drawn with insufficient data! One of the most expensive parts of a research enterprise is the gathering of the data. Ironic, isn't it, that when the analysis is well done the presentation becomes smaller and simultaneously more lucid. Perhaps there is a psychological need to display lots of graphs just to make it look like a lot has been done.

My son is now in grade school. In 4th grade he now is doing a lot of graphs of data. I just started using ET's Visual Guide to the Display of Quantitative Data in discussing the designs he is learning about. Thanks for having written so well about good design.


-- Steve (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

While I have a strong preference for a chart over a table, especially if someone is trying to convey trend(s) in a lot of data, this is a case that falls into the grey zone, because there is no easy way to meaningfully graph all these data on a single plot, without the plot becoming more confusing than the table. One risk with using a table, however, is that the message can become merely that there are a lot of data, at the expense of revealing any significant trends among the data.

To this point, I agree that the original table, as shown, is not the optimal way to present the data, because the author has invested no effort in adding value to a seemingly random collection of facts. Unless I had a real need to, I would never take the time to extract underlying data trends from the original table. Merely sorting the entries by survivability adds enormous value to the table and makes it much easier to digest by perusal.

For the case in question, and in general, there does remain the option of further processing the data, to make them more easily digested by the reader -- by basically doing some of the digestion for the reader. I read a lot of scientific journal articles, and this is very rarely done, I am sorry to report. In this particular case, a table of 4 columns (8 if we count the standard deviation values) could be reduced to just two if we consider the initial 5-year survival and then the slope across time out to 20 years. These data are such that the slopes are reasonably linear, so this would be a fair, accurate, and meanigful way to add value to the raw data, and thereby convey the same amount of information with less ink.

-- Mark Timmins (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

I concur with the comment of David Nash. The spacing between values in the five-year survival rate column is not proportional, resulting a visual element inconsistent with the actual values. In some cases a difference of just one percent results in a larger gap than one of as much as six percent. Perhaps an additional column with the initial survival rates plotted proportionally could be added while preserving the elegance of the original graphic.

-- Jack Raglin (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

I disagree.

Conveying proportional relationships between the types of Cancer is extraneous to the intent of the graphic. The graphic needs to merely show survival time gradients for each Cancer type no matter how gravely low their numbers may be.

The data stacking in order of starting percentage variables at 5 years seems incidental and an echo from the first redraw of the orginal table. In the first redraw the white space does not hint anywhere that it should convey information, so the stacking order manifests itself as convenience rather than significant data. It is difficult to guess how the original by Hermann Brenner determined its stacking order. I wondered if it was by number of patients. Such a stacking order might be more important to the trend information in terms of lives lost.

Using the percentage variable at 5 years as a stacking order could cause confusion (and it seems it has?) that the graphic should convey more than it does. The graphic could list the Cancer types alphabetically for a more impartial trend analysis where the starting percentage variable is moot.

-- Jeffrey berg (email)

Response to Cancer survival rates: tables, graphics, PP

A consistent scale does create a cumbersome chart, full of overlapping points and crossing lines:

The original table's order suggests groupings for multiples that invite further comparisons:

Many overlapping points and crossing lines disappear, and the remaining ones are clearer. Still, the cancers of the colon and rectum require additional labels.

-- Dave Nash (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

The severity-drop graphs are really interesting. Which program would you use to draw one?

-- nixon (email)

Response to Graphic of the Day: Cancer Survival Rates and Redesigns, including PowerPoint

Adobe Illustrator

-- Edward Tufte

Response to Cancer survival rates: tables, graphics, PP

Wow. Or more accurately, taking a cue from the Princeton acceptance letter dialogue:


An elegant balance between complex content -- still readily available for the looking -- and an economy of form that actually adds content. Genuinely empathetic ... it comes across as a trustworthy invitation to learn a lot very quickly about a truly forbidding subject.

It's hard to imagine that Dave Nash's most recent treatment could be much improved.

-- Doug Cleveland (email)

Response to Cancer survival rates: tables, graphics, PP

This is excellent, particularly the upper panel.

In the upper panel, could Kindly Contributor Dave Nash put the names of each cancer type at the righthand end (20 year relative mortality rate) of the lines at the right? This will make it easier to track the overlapping lines and, more importantly, show the ordering by the 20-year survival. This new column of names should be flush left. The repetitive labels, left and right, are not a problem since the ordering changes.

I prefer the flush left type of the left column, as in the original. Also the Gill Sans (tracked out) of the original reads more clearly and the Gill numbers are better. There's an investigation of Gill vs. other fonts for tabular material in the sparklines essay, posted at this board.

The gray lines should be thinner. Note the balance of weights for the numbers and the lines in the original.The underlines for the column years should be thinner and lighter.



-- Edward Tufte

Response to Cancer survival rates: tables, graphics, PP

I see now that the flush-left labels in the table-graphic make it easier to find the cancers, just as it would in an ordinary table. The recommendations all improve the legibility.

-- Dave Nash (email)

Response to Cancer survival rates: tables, graphics, and PP

Dear Edward,

I like your graphical presentation of teh survival curves - what is not obvious is how did you create it?

Regards Elizabeth

-- Elizabeth Tracey (email)

Response to Cancer survival rates: tables, graphics, and PP

Done in Adobe Illustrator by my design assistant based on a sketch modeled after my design on page 158 in The Visual Display of Quantitative Information, which I did 25 years on the typewriter with pencil rulings and later paste-down rules. These days, it could probably be done in a low-end word-processing program or a low-end drawing program with a little bit of hacking.

Adobe Illustrator is a big serious program that can do almost anything on the visual field (other than Photoshop an image). Most of my sparkline work was done in Illustrator. Fortunately all graphic designers and graphic design students have the program and know how to use it, so find a colleague who knows about graphic design.

-- ET

Response to Cancer survival rates: tables, graphics, and PP

Dear ET,

I'm sitting here in a bit of the Diane Keaton moment she had in "Something's Gotta Give" -- crying and working. Working because I have to, and crying to get my mind off someone who pulled a JN on me. Ordinarily I wouldn't share that on such a serious page as this one except that when I scrolled to the PP section, I started laughing . . . and I really needed to laugh. Thank you.

Enough of that.

I, too, am a cancer survivor, and realize the point of displaying these graphs is to illustrate (I think), the difference between quality graphing and chartjunk graphing. Perhaps I'm out of line in being nitpicky, but there's something missing from the quality graphs that a cancer survivor's eyes would search for: the specific type of cancer. For example, breast cancer includes many types of cancers.

Five+ years ago when researching to help me make decisions, I didn't know that. I'd see charts like those shown here and get hysterical. I know there were more reasons for that than just the quality of graphing; however, my plea to anyone doing graphing is to include a footnote to clarify the data.

Thank you for providing this forum.


-- Pati (email)

Response to Cancer survival rates: tables, graphics, and PP

To this discussion of these beautiful, supremely legible charts of cancer survival data, I will add just one thought: if one colored the data for cancers most frequently associated with smoking (say, in red), one would achieve a potent visual argument against the habit. Cancers of the lung, esophagus, oral cavity, and larynx are all highly correlated with tobacco use--and they have some of the worst survival rates (and some of the most precipitous drops in long-term surival rates) of all the cancers displayed, except for multiple myeloma and breast cancer.

-- V. Brandt (email)

Response to Cancer survival rates: tables, graphics, and PP

I work closely with English Cancer Treatment Networks and am an health information analyst, and this thread is like fresh air. The missing dimension in these cancer survival graphs however is the frequency/ incidence of these cancers, and known causes.

Some of those with very high survival rates are also very common (breast cervix and prostate), whilst some of the most deady are also thankfully very rare (pacreas, and liver). Others are both common and deadly (lung). The survival rates graphic presents all tumour sites as equally likely, which they are not.

From a communication perspective we need dimensions that articulates the commonality/ survival axis by the lifestyle component that creates the risk factor.

The viewer of the graphical information has an unarticulated question: "How likely am I to develop these cancers"? and then and only then, "How likely am I to survive them"?

Not only are a good half dozen commonly related to smoking behaviour,others are related to alcohol consumption.Others are lifestyle "blameless". To enable the graphic to go beyond graphical integrity and become useful to ordinary people to facilitate the process of change, we need some ideological dimensions too.

-- Andrew Wilk (email)

Frequency of occurrence, more specificity as to cancer type, differential rates by subgroups, and possible causes belong in follow-up text, tables, and graphics--with viewers to go to in accord with their interests.The redesigned table and graphic (the second and third displays at the top of this thread) are already carrying a substantial message. After that, readers might want to see mortality distributions over time, as in Gould's essential essay on facing a diagnosis of cancer


or information about treatments, causes, specialized sources, and so on.

In talking about cancer, it is particularly important to have a clean, crisp, epidemiological, policy-relevant language concerning causality--and to blame the cause, not the particular cancer patient.

When I hear an overly definitive analysis of medical causality applied to a single individual, I ask the analyst "Where, then, is your Nobel Prize in Medicine?" Even cancers blamed on "lifestyle" (an awful euphemism) now sometimes appear to be a product of the blamed behavior interacting with certain inherent genetic factors specific to the patient. Also, as a result of triage by blame, a blamed patient may receive lower quality medical care than an unblamed patient.

In having had all too many dogs treated for cancer, I have noticed among veterinarians and in most of the writings on the subject a wonderful absence of blame, punitive metaphors, accusation, and guilt-provocation. Instead, cancer at the level of treating the dog patient is simply a very nasty problem to be thought through deeply and rationally--and, if possible, solved.

-- Edward Tufte

Response to Cancer survival rates: tables, graphics, and PP

In part because of a lack of good tools (and of course the low data density of current display devices), we have not seen an explosion of statistical graphs and tables and charts which take advantage of the interactive nature of the internet. When I read Dr. Gould's essay (one of my favorites), the charts presented by our host and contributor Dave Nash cry out for interactive hyperlinks. Imagine clicking on the name of the cancer and being taken to a chart dedicated to that cancer, which shows all the sub-types of cancer and other data which would provide the answers to the types of questions asked by Dr. Gould. Displaying all that information would overwhelm the original chart's purpose, but the additional data is crucial to someone suddenly experiencing cancer (e.g. what are the statistics at different ages of detection?). While this could be done in printed form, with cross-references to later pages, the hyperlink would provide greater convenience.

-- Patrick Martin (email)

Gould's long tail of the distribution is exactly that, a long tail that contains only a few percent of those with cancer. And only those few are candidates for writing about the promise of the long tail of the death distribution.

For an account of some mortality over-estimates, see David Brown, Washington Post, April 1, 2007

-- Edward Tufte

Response to Cancer survival rates: tables, graphics, and PP


(Horsepower ?? Weight) x 10,000 ?? Price Point x 100,000 = SpD

"It occurred to me that enthusiasts could use a new equation to better quantify a vehicle's capabilities in view of its cost--something like horsepower-per-pound-per-dollar, a metric that more artfully balances power, weight, and financial outlay. Thus, the "Speed per Dollar" concept was born."

Chris Paukert

SOURCE [ http://news.windingroad.com/gadgets/a-new-performance-paradigm-the-speed-per-dollar-index/ ]

-- Tchad (email)

Response to " FROM WINDING ROAD"

Setting aside questions about this calculation and ordinal v scalar display, should we choose the order that minimizes the changes in rank? Reversing the order of the horsepower column gives a clearer picture of the horsepower-to-weight relationship and highlights the exceptions:

Swapping the horsepower and weight columns reveals the stratified horsepower-to-price relationship, though at the loss of weight-to-price (but we're not looking at scrap metal):

Justifying the column text and numbers reveals the values and lets the line slope represent only the change in rank and not the length of the vehicle name. The simplified chart could let us have less eccentric colors, but I leave them in for comparison to the original.

-- Dave Nash (email)

Response to Cancer survival rates: tables, graphics, and PP

I stumbled upon this thread quite by accident. I goggled "20 yr survival rates cancer" and this was right at the top. And so I read it all, except for the last couple of entries when the content switched to car engines. You see, I am a recent breast cancer survivor and I am only 45. So when I learn that my 5-yr. survival rate is 98% (I'm Stage I), that's not very meaningful to me. Everyone expects me to go "Whoopie" and all I can think is, but I'll only be 50. If I survive for 10 years, for which there is a decent, though lower, chance, I get to see my son graduate from high school. But I was having a hard time finding survival rates that go out beyond 10 years; hence, the google search. I have learned more from this thread in 5 minutes than I have learned in reading 1000s of pages of books and journal articles on cancer. I was a little shaken by the steepness of the breast cancer curve, but once I recovered from my dismay, I was in awe of how informative the information in the initial table became when displayed in the right way. I also very much appreciated the link to the Washington Post article by David Brown, which I had not seen before. Thank you so much! Please find a way to get the graphic on some mainstream cancer sites such the American Cancer Society. It is exactly the kind of information most cancer survivors want to know and we shouldn't have to wade through pages and pages and more pages of stuff before we, in desperation, do a google search. Could you please make it available as a PDF?

-- Wendy Rahn (email)

Response to Cancer survival rates: tables, graphics, and PP

The graphical representation emphasizes something strange in the data. Shouldn't the survival rates be monotonically decreasing? Yet for "Liver, bile duct" the data seem to imply that survival rates are higher at 20 years than at either 10 or 15 years.

Is this a statistical anomaly, an error, or am I misunderstanding the data?

-- Zuil Serip (email)

Response to Cancer survival rates: tables, graphics, and PP

Kindly Contributor "Zuil Serip" asks <<shouldn't the survival rates be monotonically decreasing? Yet for "Liver, bile duct" the data seem to imply that survival rates are higher at 20 years than at either 10 or 15 years.>>

All other things being equal, we would not expect a 2% resurrection rate. However, these are presumably not data for the same cohort, but %age of patients alive from those treated 5, 10, 15, and 20 year ago. Time of treatment is a covariant!

I am not a doctor or medical historian, the following is purely speculative.

The anomaly could mean that treatment outcomes for these cancers were better for those treated 20 years ago compared to 15 years ago, after insurance cost containment / HMO's kicked in. If this is the ONLY disease with better 20yr survival than 10 or 15 year, the cost containment has been less malign than widely suspected.

Conversely, *if* there was a particularly aggressive chemo/radio therapy in vogue for Liver/bile cancers 10-15 years ago, it might have done more harm than good, compared to prior practice (and hopefully current?).

The anomaly could also be statistical contamination. If some non-life-threatening disease X was 20 years ago bundled under "Liver Cancer", the blended cohort of cancer survivors and X "survivors" would have a combined mortality better than a pure cohort. Perhaps 20 years ago Cirrhosis was billed to insurers as Liver Cancer due to ignominy of Cirrhosis. Perhaps differential diagnosis is better today: some patients / cases formerly diagnosed with and treated under "Cancer [Liver, bile duct]" are now coded under a non-malignant DX code. This would result in a surge in cases (with 90%+ survival) in the new code, a reduction number of cases in that cancer code -- all of which are removed from survival %age. And drop in number of cases might be masked by rise in detection/treatment.

Many other anomalies due to improved diagnostic practice and insurance incentives to vary coding or use preferred treatments could drive a change between cohorts.

-- Bill Ricker (email)

Response to Cancer survival rates: tables, graphics, and PP

While discussing cancer survival data in today's seminar in Raleigh, ET mentioned that Google often returns hits from Wikipedia. This is no accident. In a recent Computerworld article, reputation management companies complain about difficulties pushing harmful Wikipedia stories off the first page of Google searches. See "Online reputation management is hot -- but is it ethical?" in Computerworld, 2/12/2008, at http://www.computerworld.com/action/article.do?command=viewArticleBasic&articleId=9060960.

Google is a wonderful research tool, but its results can be sponsored or manipulated.

-- Phillip Julian (email)

Response to Cancer survival rates: tables, graphics, and PP

Dear Professor Tufte,

After having suffered through endless data constructs and attempts at re-phrasing the keyword searches for the information I sought, I happened upon your site.

How refreshing.

It seemed as if a clear mind and simple presentation were extinct in this incarnation of the Brave New World.

The only academic conclusion I can draw regarding the obscure presentation of data is that it is willfully obscure - otherwise EVERY presentation would be as clear as yours.

Thank you.

-- Adam Gold (email)

Response to Cancer survival rates: tables, graphics, and PP

Gradient tables are amazing storehouse of information. BUT, the reader is left to assume we are talking percents.

I find units are often left out of tables and graphs. Very irritating because a nice set of data is rendered helpless to give perspective without the units.

Also, how should we go about indicating the total number of people studied in each cancer? Seems very important to display. Can it be done with line thicknesses?


-- J.P. Chauhan (email)

Response to Cancer survival rates: tables, graphics, and PP

Another superb example of information design about a life-or-death issue is this gem from National Geographic. Lots of data presented in parallel. No chartjunk or fluff. Print this out on 8x11 paper and begin an intelligent conversation about the #1 public policy issue of our day.


-- Curt (email)

Response to Cancer survival rates: tables, graphics, and PP

I don't think it's superb, because it's an Inselberg-style parallel coordinates graph with *only two coordinates*. The obvious thing to do when you only have two coordinates is to make a scatter graph: parallel coordinates are for when you have two many coordinates for a scatter graph, or even a small multiple of scatter graphs, to work. The designers of the graph weren't thinking it through.

Jon Peltier of PTS Blog has redesigned it for orthogonal coordinates.

-- Derek Cotter (email)

Response to Cancer survival rates: tables, graphics, and PP

National Geographic Magazine (NGM) Blog Central - Design Reasoning

On the NGM Blog Central, Oliver Uberti discusses the reasoning behing the design of this graphic. He points out: "...our parallel plot (which I anchored around the spending and life-expectancy averages) calls the reader's attention to discrepancies between spending and life expectancy--the story I wanted to tell.

Suggested Improvements

While I agree the graphic clearly communicates the correlation between spending and life expectancy I propose it can be improved to help the viewer more quickly realize what the graphic is about.

I believe the main flaw of the graphic is unfortunate mixing of legend and axis titles. If the legend elements are relocated away from the axis titles, and the axis titles are horizontally aligned, the viewer can more readily understand the chart.

Finally, I propose that the Life Expectancy scale be taller to make better use of the vertical space.

Proposed Graphic

  • Relocated the 3 legend elements to keep them from being confused with the axis titles.
  • Horizontally aligned the two vertical axis titles.
  • Stretched the Life Expectancy axis to fill the vertical space below the titles. Unfortunately my Photoshop manipulation of the chart resulted in the unintended consequence of fatter lines on the right-hand side.

-- Steven Chalmers (email)

Response to Cancer survival rates: tables, graphics, and PP

The medical spending charts are useless for any serious analysis of health care issues in the United States (or any other country). For one, it's possible that differences in reporting requirements lead to some significant disparities in the infant mortality rate (the U.S. attempts to save more very early pre-term births than other countries, which just report similar births as still-born). This CDC report discusses the possibility, though its authors don't themselves think it has a really large impact.

Most people who pay attention to the issue are, I think, already aware that the U.S. may have both higher health care costs and lower life expectancy because we have less healthy lifestyles... diet, exercise, smoking, drug abuse, etc. The chart merely tells us that we spend a lot of money on health care and that we don't live quite as long as other countries. It does not in any way even suggest causation. If you look at the top 9-spending countries (except for the U.S.), 5 of them have downward-sloping lines, suggesting that there's no real correlation between healthcare expenditures and life expectancy. Nor, as best I can tell from looking at the graphic, does there appear to be much correlation between number of annual doctor visits and life expectancy.

Finally, this graph, like much popular and political discussion of the issue, treats "health care" as one lump sum number, without analyzing crucial differences in spending on different kinds of health care. For example, it may be that the U.S. spends a great deal of money on end-of-life care, including nursing homes, while in other countries, less medical intervention is provided at the end of life, and many more people live out their lives cared for by relatives rather than state-funded nursing homes. How end-of-life care is and should be provided and paid for is a very different question from how, for example, treatment for cancer and other major illnesses is treated (the data I have seen, by the way, suggest that U.S. survival rates for most cancers is significantly higher than in other countries), which is a very different question from how best to provide and pay for care for injury or accident, or care for chronic illnesses like diabetes.

In short, it's a useless chart, a political stunt illustration rather than a serious analysis of anything at all.

-- Patrick Martin (email)

Response to Cancer survival rates: tables, graphics, and PP

I disagree. I find this graphic to be very compelling. The graphic doesn't try to make any claim of causality. Only its readers do.

The authors have made their point very clear: there is a ballpark figure for what healthcare should cost and it's probably less than $5000. There is one country that is way, way, way out of bounds with that (as illustrated metaphorically by the country's position on the Y-axis as being out of the boundary demarcated by the legend and caption). The degree to which it is out of the norm in terms of cost is displayed perfectly by it's height on this axis. Yet, there are only modest differences in terms of life expectancy.

There are many reasons for this: price gouging by pharm companies and drug makers, hospital and physician charged propped up to counter against those who will not pay, defensive medicine, etc... But it is pretty obvious that there is at least one whopping difference between the one outlier and its peers -- universal coverage.

If nothing else, this graphic should make the readers question whether or not Americans are getting their money's-worth. (As a physician myself, I can tell you: they're not.) It should also make the reader question anyone's assertion that universal coverage would represent a harmful, financial boondoggle.

I would be curious to see where those states with some form of expanded coverage (i.e. Hawaii, Massachussetts) would fall on a plot like this, or against their historical norms.

-- Gene (email)

Response to Cancer survival rates: tables, graphics, and PP

Dear ET

Here are two recent and thought provoking pieces on cancer.


A summary of the period 1971-present describing Nixons' 'War on Cancer' http://www.csicop.org/si/show/war_on_cancer_a_progress_report_for_skeptics/


A discussion of changes in cancer theory that seek to explain multiple paradoxes. In particular the tissue organisation field theory (TOFT) model which proposes that cancer is a tissue-based disease. This theory has been developed and championed over the past 10 years or so by Ana Soto and Carlos Sonnenschein at Tufts medical school.



-- matt r (email)

Response to Cancer survival rates: tables, graphics, and PP

This is a belated response to Zuil's and Bill's questions about the survival rates for some cancers going up. Although my sole exposure to health statistics was a summer job in the National Center for Health Services Research many years ago, I believe the important thing here is that these are relative survival rates. I don't know the methodology, but I presume a relative survival rate is obtained by dividing the survival rate for those diagnosed with the cancer by that of a control group. I assume that the control group would be demographically the same as those diagnosed with the cancer. That would explain why the relative survival rate for prostate cancer is so high; most of those diagnosed with it are older men. When a relative survival rate goes up, it doesn't mean that cancer victims are coming back to life; it just means that some of those in the control group have died.

I found the table of survival rates to be just fine. I took a parochial interest in it two years ago this month, when I was diagnosed with non-Hodgkin's lymphoma. I looked at the survival rate and wished it was higher: it was lower than the survival rate for colon cancer, which had just killed Tony Snow. I envied a high school classmate of mine who had come down with Hodgkin's lymphoma in college and had survived it. I underwent chemotherapy (R+CHOP) from August 2008 to January 2009 and have had several negative scans since then.

-- Robert O'Rourke (email)

Response to Cancer survival rates: tables, graphics, and PP

Hi Professor Tufte, I'm an academic primary care doc and took your undergraduate class more than a quarter century ago (yikes!)

For accuracy's sake, charts on cancer survival rates ought to include a comparison group showing the overall survival for people w similar characteristics and disease risk factors. Cancer stage at diagnosis is also critically important.

For example, a chart on cancer X survival would be most meaningful if it subdivided patients by age, smoking, and diabetes status. If I were counseling a newly diagnosed 70 yr old poorly controlled diabetic smoker w cancer X, I'd want to know the comparable survival rate for other 70 yr old poorly controlled diabetic smokers. (Age, smoking and diabetes are big mortality risk factors and this group is also at increased risk of dying of infection, lung, and vascular disease, for example).

Not showing survival by stage at diagnosis is also hugely misleading. Women w stage 1 breast cancer, for example, have a far higher 5 yr survival rate compared to women w stage 4 disease.

I also question the utility of comparing cancer survival by organ of origin. A newly diagnosed 60 year old smoker with cancer x would gain more insight by comparing his or her survival to the overall population of 60 year old smokers, instead of comparing his or her survival to the overall group of people w cancer Y.

-- ENMarcus MD MPH (email)

Threads relevant to PowerPoint:
Don't get your hopes up.
A look at a rich and complex question: What are the the causes of presentations?

An intriguing but under-explored topic.
Account of the role of PP in the shuttle Columbia accident, followed by many good alternative methods and examples for technical presentations.
Mainly recent examples of leaked PP slides in the Iraq war.