The Uncertainty of the Numbers

Here’s an odd thing.  You know how we are deluged with statistics and studies and surveys, endless streams of numbers and percentages and comparisons?  You know how we can’t so much as glance at a screen or tune in to any news or entertainment programming without finding out way too much about celebrity shopping preferences, the dating habits of world leaders or some purportedly groundbreaking new technology?  How according to our ever-breathless media-istas, every moment of every day, the world undergoes a monumental game change, embraces yet another new frontier, crosses some magical information barrier?   Just look at the numbers, they say.   Then they invite us to text and tweet about how it makes us feel to witness such history.  It’s a survey of a survey about a survey — and it’s exhausting.  And probably premature, if not actually downright silly.

The thing is, all these numbers, all these stats, all these dramatic conclusions, are not coming from impeccable sources.  In fact, good data are notoriously hard to find.  Just ask the statisticians at the World Health Organization (WHO).  This group, representing 194 member countries, is tasked with analyzing the state of the world’s health — a seriously consequent mission.  Billions upon billions of dollars are allocated based on their findings, along with the work of other United Nations agencies such as UNICEF and the World Bank.  Global policy shifts are set in motion based on their figures.  And yet,  a full two-thirds of deaths in the world are not registered.  A third of all births worldwide are not registered.  Here we are, trying to generate reports to make a global health estimate and we don’t even know who’s living or dying or where or why.

Think about it.  Our political leaders and candidates toss off numbers and percentages as often as they can.  Numbers can’t lie, they promise.  Governments offer up comparisons and conclusions, claiming victories they cannot hope to prove.  Advocacy groups come up with data on everything from rates of measles and AIDS incidence to the percentage of women dying in childbirth to the numbers of healthcare providers and social workers in one country compared to another.  Then the sets of data are promptly disputed, undermined, challenged.

For example, WHO figures suggest that about 600,000 people worldwide die each year from malaria.  A study by the highly regarded US Institute for Health Metrics and Evaluation (IHME) published in February found that the disease kills 1.2 million per year – about twice the WHO estimate.  Which group has got it right?

Many diseases affect the poor and marginalized, making it that much harder to get good information.  And there are political considerations, too.  There are incentives for countries to over-estimate (large numbers of disease cases of  one sort or another could mean extra funding) or to under-estimate (in order to demonstrate that a policy or program is effective).

So here’s the good part.  The WHO and others who are educated to understand how numbers really work embrace uncertainty. Really. In fact,  they have dedicated a sizeable portion of their global health reports to precisely that, uncertainty.  Ties Boerma, the WHO’s director of health statistics and information systems, says that ranges of uncertainty need to be clearly published.  And he means not only statistical uncertainty, but also possible systemic biases: for example, making clear the extent to which one group of individuals within a nation may or may not be representative of the nation as a whole.  Another international health leader, Sweden’s Hans Rosling, believes embracing this uncertainty, rather than banishing it, is absolutely vital to coping with global health data.  It all boils down to the fact that some things are really easy to measure, say, fertility rates, while others (malaria deaths),  are really hard.

Interesting, isn’t it.  The world just won’t stay black or white, good or bad, sick or healthy, rich or poor, right or wrong, us or them.  It would be so much easier if it were just one or the other – but it isn’t.  In fact, nothing is that easy, that clean and self-evident, that obvious.   We might do well to keep this in mind about everything, from managing obesity and heart disease to coping with energy conservation and aging with grace and dignity.  Perhaps we could cooperate and coordinate and not simply confront and challenge.

There’s a whole lot at stake, here.  Remember:  good data are really hard to find.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s