Seeing trends
The danger of dual trending


Many times by adding an extra dimension to a chart, the designer unwittingly confuses his audience.  The rectangle plot is useful in very specialized situation but as used here, I still haven't figured out this chart.

Part of the problem is my own ignorance of this subject matter.  I cannot understand how 0-100 constitutes "poverty level" and if it represents percentiles, then the reader needs to know of what?

The biggest problem is that the widths of the rectangles are not labeled.  The labels on the y-axis are categories and most definitely not widths.

These rectangles draw our attention to the areas and yet it isn't clear what is being measured.  It appears to be the number of dead people in thousands who belong to some poverty-defined demographic.  In any case, the human eye is also not trained to compare the area of a fat, short rectangle with that of a tall, slim rectangle.

RedohealthThe junkart version is a simple scatter plot.  Since I don't fully understand this chart, I'm sure some readers will have better suggestions. 

Reference: "The People's Epidemiologists", Harvard Magazine, March-April 2006.


Feed You can follow this conversation by subscribing to the comment feed for this post.

Geoff Urland

0-100 just means the percentage of people in a census tract that are below the poverty line. So the 0-4.9 bin represents census tracts that have very few people in poverty. The width tells us how many people in the state live in such tracts, but I think having that width there with no explanatory number is very confusing. I'd much rather see this data in a scatterplot, graphing each individual tract by poverty rate and infant mortality.

Keyvan N.

Isn't that a MariMekko chart (albeit with a missing axis) ?


Madeline Drexer’s article (“The People’s Epidemiologists,” March – April 2006) mixes a description of some traditional and scientifically noncontroversial public health measures (such as cleaning the home environment to reduce asthma symptoms), with a credulous look at some broad and contentious critiques of society, notably Dr. Nancy Krieger’s claim that the stress of today’s racism is directly causing much of blacks’ increased hypertension and other health problems.

While some critiques of Krieger were referenced, they have since, according to Drexler, “fizzled out” due to Krieger’s “massive foundation of empirical research and methods to support her vaulting theories” and her “scientifically validated research instrument.” But the fact that Krieger’s critics are not as interested as she is in perennially remaking the same points does not mean that they would concede the argument to her. Further, Krieger’s questionnaire of racism was “scientifically validated” in terms of consistency (e.g., a subject, when retested a few weeks later, tended to report about the same amount of discrimination as he or she had reported previously), but her conclusion that racism directly causes disease has not been so validated.

Indeed, as Drexer’s article only hinted (“the findings were very complex” and contained “the hint that repressing the anger and humiliation of racial discrimination exacts a physical toll”), Krieger’s 1996 study of hypertension in young working class adults could have been titled “Discrimination Eases High Blood Pressure” – since blacks who reported more incidents of racial discrimination (especially those who had challenged the racism) actually had somewhat lower blood pressure than those reporting no discrimination.

Krieger explains this negative correlation by arguing that those who reported no discrimination must have been mistaken or in denial about the racism she knows they must all have experienced, and were stressed due to their “suppressed or internalized anger.” This is certainly possible, but as Dr. Sally Satel pointed out in a 2001 interview, “Such a possibility requires justification by independent evidence, because otherwise it is just an assumption invoked selectively to save the original hypothesis from the disconfirming data.” The validity of Satel’s skepticism is shown in Krieger’s more recent (2004) premature birth study. This showed the opposite result (i.e., more reported discrimination correlated with worsened health effect), and yet Krieger also declared that that study showed that racism caused the medical problem. Krieger also wrote in 2005 that reported discrimination correlates positively with psychological distress.

Krieger no doubt holds the worthy aim of helping the disempowered and sick minorities by convincing people to eliminate racism and other social ills. But stretching the facts to suggest that black people with heart disease may be sick because they were blind to, or didn’t complain enough about, racism, not only smacks of blaming the victim, it is unlikely to improve race relations in this country.

The comments to this entry are closed.