What does statistically mean in sentences like this? Strictly speaking, nothing at all. If airplane travel is safer than driving, then that's just a fact. (It is true on an hour-by-hour basis). There's no statistically about it. A fact can't be somehow statistically true, but not really true. Indeed, if anything, it's the opposite: if there are statistics proving something, it's more likely to be true than if there aren't any.But we often treat the word statistically as a qualifier, something than makes a statement less than really true. This is because psychologically, statistical truth is often different to, and less real than, other kinds of truth. As everyone knows, Joseph Stalin said that one death is a tragedy, but a million deaths is a statistic. Actually, Stalin didn't say that, but it's true. And if someone has a fear of flying, then all the statistics in the world probably won't change that. Emotions are innumerate.
*
Another reason why statistics feel less than real is that, by their very nature, they sometimes seem to conflict with everyday life. Statistics show that regular smoking, for example, greatly raises your risk of suffering from lung cancer, emphysema, heart disease and other serious illnesses. But it doesn't guarantee that you will get any of them, the risk is not 100%, so there will always be people who smoke a pack a day for fifty years and suffer no ill effects.
In fact, this is exactly what the statistics predict, but you still hear people referring to their grandfather who smoked like a chimney and lived to 95, as if this somehow cast doubt on the statistics. Statistically, global temperatures are rising, which predicts that some places will be unusually cold (although more will be unusually warm), but people still think that the fact that it's a bit chilly this year casts doubt on the fact of global warming.
*
Some people admit that they "don't believe in statistics". And even if we don't go that far, we're often a little skeptical. There are lies, damn lies, and statistics, we say. Someone wrote a book called How To Lie With Statistics. Few of us have read it, but we've all heard of it.Sometimes, this is no more than an excuse to ignore evidence we don't like. It's not about all statistics, just the inconvenient ones. But there's also, I think, a genuine distrust of statistics per se. Partially, this reflects distrust towards the government and "officialdom", because most statistics nowadays come from official sources. But it's also because psychologically, statistical truth is just less real than other kinds of truth, as mentioned above.
*
I hope it's clear that I do believe in statistics, and so should you, all of them, all the time, unless there is a good reason to doubt a particular one. I've previously written about my doubts concerning mental health statistics, because there are specific reasons to think that these are flawed.
But in general, statistics are the best way we have of knowing important stuff. It is indeed possible to lie with statistics, but it's much easier to lie without them: there are more people in France than in China. Most people live to be at least 110 years old. Africa is richer than Europe. Those are not true. But statistics are how we know that.
[BPSDB]
14 comments:
"Statistically, global temperatures are rising,..": or, rather, they are if we ignore the last decade.
Hmmmmm...
So what kind of "statistics" are we talking about here?
Fisherian "clasical" statistics in the thrall of the standard error of arbitary notions of statistical significance and fit as oppossed to substantive significance?
Or something more powerful like Bayesian or Neyman-Pearson based stats?
I mean if we are looking at "statistical facts" in terms of being significant at whatever arbitary level then I can understand peoples disatisfaction with them. Bring me power calculations, confidence intervals and perhaps even odds ratios... Then perhaps we can talk of statistical fact...
That far apart from the fact that models built from statistical inference are just models. They may be the best models we have but thats no reason not to doubt them (nor is it room to fit in any fairy story you see fit in their place though granted).
How neurosceptically would you view this, oh blogger?
http://entertainment.timesonline.co.uk/tol/arts_and_entertainment/the_tls/article6864376.ece
What does statistically mean in sentences like this? Strictly speaking, nothing at all.
actually the way you phrased the statements (e.g. "statistically, flying is more dangerous than driving), the adverb "statistically" could be seen as shorthand for "according to the statistics," in which case it doesn't designate a kind of truth-value (statistical truth, as opposed to some other kind of truth), but a source for the information. since the construction you chose is a common one, you are really misrepresenting a figure of speech. likewise, when we say "statistically its true that (whatever)", we are expressing skepticism as to whether the statistics are reliable or necessarily applicable to the present instance.
when I say "I don't believe in statistics," what I mean is that I think that there are a number of attributes of statistical reasoning that lend themselves to distortion and manipulation of truth; that historically, these properties of statistics have frequently been exploited by members of the scientific and corporate establishments; that even when such manipulation has not occurred, reliance on statistics can lead to confirmation bias or other distortions; and that these facts make any invocation of statistics inherently suspect.
I think people usually have a much firmer intuitive grasp of statistical reasoning and of the problems with it (which are themselves statistical) than they do of deductive logic and rhetoric. (I conducted some research to this effect as an undergrad.) people's skepticism towards the flagrant use of statistics is usually well founded, although they do not understand and cannot articulate their reasons. so when you approach them with a deconstruction of what were actually good intuitions, articulated in the unfamiliar language of formal logic, they are more likely than not to concede the point, despite having been in the right.
dearieme:
It's the statistics that make it clear that global temperatures are still rising.
Noisy signals require statistical processing to extract the signal from the noise. In the case of global temperature, the noise is shorter term variability, over a few years, such as that associated with the El Nino.
5 or 10 year running averages make the trend clear.
http://www.globalwarmingart.com/wiki/File:Instrumental_Temperature_Record_png
If statistics make it clear that the temperature is rising when it isn't, the statistics is rubbish. Hell, with climate we don't even know whether it's meaningful to talk about signal and noise.
Put otherwise, could moving averages mean that the great stock market collapse didn't happen?
Having treated fear of flying for twenty-eight years, I can tell you that statistics don't help. But how could they? When you are on a plane, whether a crash happens to one in a million or one in ten million, you don't know if yours is or isn't that one.
One is a very real number. We can identify with it. A million is not very easy to identify with (unless you happen to be a millionaire, perhaps); it is just an abstraction, so whether there is an abstraction at a level of ten (one crash in ten million flights) or at a level of on (one crash in one million flights), that doesn't help emotionally. There is still the "one" to deal with.
There are some remarkably effective ways to deal with this anxiety. If interested, search using the terms "fear of flying library" and you'll find many articles on this.
andyourelectronmicroscope: Sure, when it comes to statistical inference, there are complexities. I'm certainly not suggesting people should slavishly follow the p=0.05 convention.
But a lot of statistics are much more straightforward than that. Flying is safer than driving: that's not inference, it's just counting the deaths and dividing by the number of passengers.
Likewise, global temperatures are rising, on average. Not every year in every place, but, the trend is up more than it is down.
dearieme: "could moving averages mean that the great stock market collapse didn't happen?" - Well, if they did, it would mean that the stock markets recovered fast enough that in the grand scheme of things it wasn't important to long-term stock prices. 9/11 for example hit stock prices hard but they bounced back fast - in the long run, 9/11 was a blip. It didn't wreck the economy. There are cold years and warm years, but if you look at the moving average (and 5 years is hardly a long time!) the trend is clear.
"One is a very real number. We can identify with it. A million is not very easy to identify with (unless you happen to be a millionaire, perhaps)" - That's exactly my point. :)
dearieme:
I'm still not sure where you get this idea from that temperatures are not rising. Even if you think that statistics lie, and that anecdotal evidence is the real truth, then the last decade has been record-breaking:
http://climateprogress.org/2009/10/13/the-bbc-hudson-what-happened-to-global-warming-hottest-decade-in-recorded-history/
dearieme:
I'm still not sure where you get this idea from that temperatures are not rising. Even if you think that statistics lie, and that anecdotal evidence is the real truth, then the last decade has been record-breaking:
http://climateprogress.org/2009/10/13/the-bbc-hudson-what-happened-to-global-warming-hottest-decade-in-recorded-history/
NickyVB - Sorry for delayed reply.
My feeling is that when people say "statistically, X" this often carries the implication "...but not really". Maybe that's just me, and actually no-one means that, in which case yes I'm misinterpreting the phrase. But that's how it seems to me. I guess readers will have judge how right I am.
non-formally educated people for the most part have good intuitions about statistics and the ways that statistics are employed because statistical reasoning is one of the more basic components of cognition. I can tell you with little reflection, for instance, that you are not likely to find a deer in my neighborhood, but that you could most likely locate a drug dealer.
the intuition that someone is pulling your leg when they tell you that 1 in 4 people is mentally ill is a good one, even if the resulting assertion ("bah, I don't believe in statistics") is false and doesn't address the real issue. but saying that people are deluded for dismissing statistics overlooks the fact that they dismiss many statistics not because they don't understand but because they do; it is because they are such good reasoners that they know how to spot BS even if they aren't articulate enough to explain why it is BS.
Post a Comment