Newer posts are loading.
You are at the newest post.
Click here to check if anything new just came in.

August 15 2013

The vanishing cost of guessing

If you eat ice cream, you’re more likely to drown.

That’s not true, of course. It’s just that both ice cream and swimming happen in the summer. The two are correlated — and ice cream consumption is a good predictor of drowning fatalities — but ice cream hardly causes drowning.

These kinds of correlations are all around us, and big data makes them easy to find. We can correlate childhood trauma with obesity, nutrition with crime rates, and how toddlers play with future political affiliations.

Just as we wouldn’t ban ice cream in the hopes of preventing drowning, we wouldn’t preemptively arrest someone because their diet wasn’t healthy. But a quantified society, awash in data, might be tempted to do so because overwhelming correlation looks a lot like causality. And overwhelming correlation is what big data does best.

It’s getting easier than ever to find correlations. Parallel computing, advances in algorithms, and the inexorable crawl of Moore’s Law have dramatically reduced how much it costs to analyze a data set. Consider an activity we do dozens of times a day, without thinking: a Google search. The search is farmed out to thousands of machines, and often returns hundreds of answers in less than a second. Big data might seem esoteric, but it’s already here.

Google’s search results aren’t the right results; they’re those that are most likely to be related to what you searched for. Similarly, Watson, IBM’s Jeopardy-winning software, mined millions of records to guess at the right answer. Today, an abundance of cheap, simple tools makes it trivial for organizations to guess rather than to know about everything from employee honesty to the spread of disease to the optimal delivery of car parts in a snow-bound city to whether a teenager is pregnant.

Tomorrow’s data-driven society is both smarter and dumber, more just and more merciless. The ethical implications of this shift are only now becoming clear: at some point, innocent-until-proven-guilty looks a lot like innocent-until-likely-to-be guilty.

What the big data revolution is really about is predicting the future. Whether it’s choosing the right ad to show a web visitor, or setting the optimal insurance premium, or helping an inner-city student learn better, we crunch reams of data to try to predict what will happen.

Proponents see this as a boon to humanity. Big data makes us smart: we can anticipate a flu outbreak or where charitable donations do the most good. It also makes us just: transparent, open information and the tools to analyze it shine the harsh light of data on corruption, replacing opinions with facts.

On the other hand, critics charge that big data will make us stick to constantly optimizing what we already know, rather than thinking out of the box and truly innovating. We’ll rely on machines for evolutionary improvements, rather than revolutionary disruption. An abundance of data means we can find facts to support our preconceived notions, polarizing us politically and dividing us into “filter bubbles” of like-minded intolerance. And it’s easy to mistake correlation for causality, leading us to deny someone medical coverage or refuse them employment because of a pattern over which they have no control, taking us back to the racism and injustice of Apartheid or Redlining.

Big data isn’t a magical tool for predicting the future. It’s not a way to peer into someone’s soul or decide what’s going to happen, even though it’s often frighteningly good at guessing. Just because the cost of guessing is dropping quickly to zero doesn’t mean we should treat a guess as the truth. As we become an increasingly data-driven society, it’s critical that we remember we can no more predict tomorrow with today’s data than we can prevent drowning by banning ice cream.

May 06 2013

Another Serving of Data Skepticism

I was thrilled to receive an invitation to a new meetup: the NYC Data Skeptics Meetup. If you’re in the New York area, and you’re interested in seeing data used honestly, stop by!

That announcement pushed me to write another post about data skepticism. The past few days, I’ve seen a resurgence of the slogan that correlation is as good as causation, if you have enough data. And I’m worried. (And I’m not vain enough to think it’s a response to my first post about skepticism; it’s more likely an effect of Cukier’s book.) There’s a fundamental difference between correlation and causation. Correlation is a two-headed arrow: you can’t tell in which direction it flows. Causation is a single-headed arrow: A causes B, not vice versa, at least in a universe that’s subject to entropy.

Let’s do some thought experiments–unfortunately, totally devoid of data. But I don’t think we need data to get to the core of the problem. Think of the classic false correlation (when teaching logic, also used as an example of a false syllogism): there’s a strong correlation between people who eat pickles and people who die. Well, yeah. We laugh. But let’s take this a step further: correlation is a double headed arrow. So not only does this poor logic imply that we can reduce the death rate by preventing people from eating pickles, it also implies that we can harm the chemical companies that produce vinegar by preventing people from dying. And here we see what’s really happening: to remove one head of the double-headed arrow, we use “common sense” to choose between two stories: one that’s merely silly, and another that’s so ludicrous we never even think about it. Seems to work here (for a very limited value of “work”); but if I’ve learned one thing, it’s that good old common sense is frequently neither common nor sensible. For more realistic correlations, it certainly seems ironic that we’re doing all this data analysis just to end up relying on common sense.

Now let’s look at something equally hypothetical that isn’t silly. A drug is correlated with reduced risk of death due to heart failure. Good thing, right? Yes–but why? What if the drug has nothing to do with heart failure, but is really an anti-depressant that makes you feel better about yourself so you exercise more? If you’re in the “correlation is as good as causation” club, doesn’t make a difference: you win either way. Except that, if the key is really exercise, there might be much better ways to achieve the same result. Certainly much cheaper, since the drug industry will no doubt price the pills at $100 each. (Tangent: I once saw a truck drive up to an orthopedist’s office and deliver Vioxx samples with a street value probably in the millions…) It’s possible, given some really interesting work being done on the placebo effect, that a properly administered sugar pill will make the patient feel better and exercise, yielding the same result. (Though it’s possible that sugar pills only work as placebos if they’re expensive.) I think we’d like to know, rather than just saying that correlation is just as good as causation, if you have a lot of data.

Perhaps I haven’t gone far enough: with enough data, and enough dimensions to the data, it would be possible to detect the correlations between the drug, psychological state, exercise, and heart disease. But that’s not the point. First, if correlation really is as good as causation, why bother? Second, to analyze data, you have to collect it. And before you collect it, you have to decide what to collect. Data is socially constructed (I promise, this will be the subject of another post), and the data you don’t decide to collect doesn’t exist. Decisions about what data to collect are almost always driven by the stories we want to tell. You can have petabytes of data, but if it isn’t the right data, if it’s data that’s been biased by preconceived notions of what’s important, you’re going to be misled. Indeed, any researcher knows that huge data sets tend to create spurious correlations.

Causation has its own problems, not the least of which is that it’s impossible to prove. Unfortunately, that’s the way the world works. But thinking about cause and how events relate to each other helps us to be more critical about the correlations we discover. As humans we’re storytellers, and an important part of data work is building a story around the data. Mere correlations arising from a gigantic pool of data aren’t enough to satisfy us. But there are good stories and bad ones, and just as it’s possible to be careful in designing your experiments, it’s possible to be careful and ethical in the stories you tell with your data. Those stories may be the closest we get ever get to an understanding of cause; but we have to realize that they’re just stories, that they’re provisional, and that better evidence (which may just be correlations) may force us to retell our stories at any moment. Correlation is as good as causation is just an excuse for intellectual sloppiness; it’s an excuse to replace thought with an odd kind of “common sense,” and to shut down the discussion that leads to good stories and understanding.

Older posts are this way If this message doesn't go away, click anywhere on the page to continue loading posts.
Could not load more posts
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
Just a second, loading more posts...
You've reached the end.

Don't be the product, buy the product!

Schweinderl