Where the Data Points
“Why Data is Never Raw” is an article written by Nick Barrowman. In it, he argues that the data we collect can often tell more about the collector than the subject. Barrowman writes,
Assumptions inevitably find their way into the data and color the conclusions drawn from it. Moreover, they reflect the beliefs of those who collect the data. As economist Ronald Coase famously remarked, “If you torture the data enough, nature will always confess.” And journalist Lena Groeger, in a 2017 ProPublica story on the biases that visual design-ers inscribe into their work, soundly noted that “data doesn’t speak for itself — it echoes its collectors.”
Curiously enough, the words of these quotes, coming from an economist and a journalist respectively, say a lot about the pen which wrote them. Journalists, Economists, and Barrowman himself as a Statistician all act as interpreters of facts with hidden meanings. Barrowman specifically shows his bias by his description of science. While he mentions hard sciences such as physics and chemistry, Barrowman focuses the bulwark of his weight behind social sciences such as psychology or economics.
Within these fields, Bias plays a vital role in understanding information because the information is simply too complex to be understood on its own. Asking what drives market shifts or crime rates are both complicated questions. Drawing conclusions from a reality that doesn’t lend itself to a double-blind controlled white coat experiment is extremely challenging; however, to conflate the reality of this bias with all science is misleading.
When testing a medication, bias must not play an essential role. When it does, human lives will surely be lost in the process. This is why medications are thoroughly tested for both short-term and long-term effects. I can only use double-blind experiments as hyperbole because they exist.
While data always comes with spin attached to it, many scientists would argue that designing experiments that mitigate the effect of human bias is one of the most important parts of their job.
Data bias is one of the many challenges scientists face every day. But like poverty, the reality that it is never leaving by no means suggests that it should be accepted. Scientists in all disciplines must strive for better accuracy and less bias constantly.
But in this, an inconsistency is created. Do we rely on science on the basis that it is “getting there” or do we reject it simply because it “isn’t there yet”?
