William M. Briggs

Statistician to the Stars!

Rise In Violence Linked To Poor Statistics. Or Climate Change

I particularly admire the sciencey shading.

I particularly admire the sciencey shading.

Welcome Der Spiegel readers. See also this post.

The computer revolution has been as bloody, wrenching, and disruptive as any other conflict. But unlike in territorial wars where there are actual body counts, the wounds caused by the proliferation of easy and cheap computing are chiefly psychic. (The most common injury is morbid over-certainty.)

Problem with computers is that they are irredeemably stupid. The computer doesn’t know anything: it can only do what it is told. And if it is told to take this set of numbers and that set of numbers and to mix them in a certain way, it will do it, creating pretty pictures of the result. And as computers get better, it can do these blind operations faster and produce prettier pictures.

That’s where the trouble starts. People start believing in the pictures because they’re so pretty and quantitative. The result is—and I’m sorry for this joke—not a pretty picture.

It is here Yours Truly must accept some of the blame. I and my brother (and sister!) statisticians gleefully create these algorithms the computers chew upon. We do this for fun, for the sheer sake of climbing the mountain because it is there. This wouldn’t be so bad except that we release these algorithms into the wild, where we naively hope they will do no harm.

Forgive us! Because instead they have wreaked havoc on the minds of men (and women!).

Perhaps no clearer example of the devastation can be had than by the Science paper “Quantifying the Influence of Climate on Human Conflict” by Solomon Hsiang, Marshall Burke, and Edward Miguel, all of whom appear to be economists, the Lord bless them. Here is their abstract (those who are squeamish are advised to look away):

…Drawing from archaeology, criminology, economics, geography, history, political science, and psychology, we assemble and analyze the 60 most rigorous quantitative studies…We find strong causal evidence linking climatic events to human conflict across a range of spatial and temporal scales and across all major regions of the world. The magnitude of climate’s influence is substantial: for each 1 standard deviation (1σ) change in climate toward warmer temperatures or more extreme rainfall, median estimates indicate that the frequency of interpersonal violence rises 4% and the frequency of intergroup conflict rises 14%. Because locations throughout the inhabited world are expected to warm 2 to 4σ by 2050, amplified rates of human conflict could represent a large and critical impact of anthropogenic climate change.

Well, you can see it for yourself. Poor men. It’s almost as if they believed what they were writing!

They mixed data from sources as disparate as the MSNBC and Fox News, they compared apples to roller blading, they contrasted black with semiotics. Data from last Tuesday was said to be equal in veracity to that culled from 8000 BC. They dumped into a computer a bunch of numbers lots of people found from all over the place, measuring God knows what, and produced lots of sharp graphics and one big quantitative result that hot, rainy weather is bad for you.

Which is exactly why everybody is moving from Michigan to South Carolina (at least 2σ difference in mean temperature): to get to where the action is and join a gang.

The authors mixed violent personal crime in the USA in one model, with inter-group riots in India in a second model, with redistributive inter-group conflict in Brazil in a third, to global civil conflict onset in a fourth, to civil war incidence in Africa in number five, to rape in the USA in number six, to political leader exit (oh! the violence!) worldwide in seven, to domestic violence in Australia in eight, and then added these to models nine, ten, etc., etc., etc. Sixty—60—in total!

Sometimes temperature at the local level was the “independent” variable, or causative agent, and sometimes it was “jurisdictional” temperature. Still other instances: daily max county (not city) temps, stadium temps (yes: football areas), state rainfall losses, pixel (yes, pixel) temps, municipality rainfall by divisions, pixel standardized precipitation loss, and, naturally, pacific ocean temperature. Oh, and ENSO and the North Atlantic Oscillation, and floods and storm numbers, and (who could leave this out?) the Nile river overflowing.

Whatever weather or climate variable “worked” was the one they used to predict whatever kind of “violence” could be quantified. The whole thing was then duct-taped together and lathered with colorful Bondo to conceal the gaping holes in commonsense. But at least they produced wee p-values (def: less than the magic number, which is what makes it science).

The most charitable way to describe the result is complete and utter nonsense. I do not want to exaggerate, but this paper is not even a mess. My God! the work, the hours the authors must have toiled. The supplementary material alone is thirty-eight pages!

At least journalists, the dears, believed them.


23 Comments

  1. Studies like these are just the beginning. Can you even imagine the possibilities in the future given the advent of Big Data?

  2. Let’s try that HTML anchor once more …

    Studies like these are just the beginning. Can you even imagine the possibilities in the future given the advent of Big Data?

  3. Now I’m mad …

    Let’s try that HTML anchor once more …

    Studies like these are just the beginning. Can you even imagine the possibilities in the future given the advent of Big Data?

  4. Excellent piece, Bill. Even if there are linkages between increased violence and climate change, what troubles me – and I’m no statistician – is the failure to understand causation or the lack thereof in this cause.

  5. “Poor men. It’s almost as if they believed what they were writing!”
    Of course they believe it. As we computer programmers used to joke, garbage in, gospel out.

  6. Vandals. Destroyed. Writing.

    Me know why.

  7. Glad you covered this absurdity. I saw reports in the news a couple days ago, and wondered anew at how anyone could take this seriously – just trying to imagine what kind of data and controls you’d need to even begin to make this claim should set off Star Wars Imperial Cruiser level warning klaxons.

    One thing I’ve noticed: early reports of any doomsday claims made in the name of Science! often give some time to critics, or offer some tidbits of doubt or questioning. But once seized upon by Panic Patrol, all doubts and criticism get suppressed, unless they can be held up to ridicule. Day 1 reports from NBC news included criticism from a Halvard Buhaug, who, as the Research Director and Research Professor at the Peace research Institute Oslo, has not only that default street cred that makes people accept Norwegian’s opinions about who should get Science prizes, but works someplace with ‘peace’ and ‘research’ in its name – well, who can argue with that?

    So, starting in Day 2 news reports, he never comes up again – at least, in the Google news feed I rely on for such things. Since the goal of these studies is never to, you know, figure out the truth as best we can, but rather to move the ball forward toward that unnamed and ineffable future from which only bad people would roll back the clock (something like that), sowing or even acknowledging doubts is counterproductive, reactionary, even.

  8. Noblesse Oblige

    4 August 2013 at 7:24 pm

    Andrew Thomas in the American Thinker has a field day with the garbage being thrown to and eagerly sopped up by “journalists” http://www.americanthinker.com/2013/08/m-global_warming_responsible_for_epidemic_of_rail_disasters.html

  9. How long before some murderer pleads, “It weren’t me, Gov, it woz Climate Change wot made me do it”.

  10. It is interesting that the news media is starting to come around and come down against potoshopped pictures in news stories, but data that has been photshopped for asthetics gets a pass.

  11. Are you saying “…the numbers just don’t add up”?
    :>)

  12. It’s hot and it’s raining here in Germany. I’m fearing for my life.
    I’m tracking the police news. Today, only car crashes and burglaries in the area. The killing spree might start any minute now.

  13. Jim Fedako on 4 August 2013 at 10:07 am said:
    “Now I’m mad …”

    Calm down. It’s global warming. Try to CHILL.

    “Studies like these are just the beginning. Can you even imagine the possibilities in the future given the advent of Big Data?”

    Who would trust data from Google, Amazon, NSA (but I repeat myself)? As all these data collections happen in secret, any “evidence” produced by these entities could just as well be a forgery.
    Do you think Snowden copied powerpoint slides that the NSA really used? Why? I can make a nice Powerpoint slide with the logos of Google, Amazon, NSA, Apple (but I repeat myself). I can even forge you the metadata. And I can write you a script so that you can forge the metadata just as well as I can.

    I know. Journalists will believe it. Trust in journalism is a limited resource, though.

  14. Nicely put. Here is an extract from a recent and relevant and thoughtful article in this broad context: “Science without an object dominates debates about climate science and the impacts of climate change. But the fact that so many activists really don’t know what they’re talking about has barely raised an eyebrow. Science is routinely divorced from its context, and turned into glib soundbytes that journalists, politicians and celebrities reproduce, largely to elevate themselves. But to my knowledge this extraordinary phenomenon is not the subject of many science and technology sociologists, nor of those with expertise in the field of ‘science communication’. Their attention is consumed by the conflict between climate scientists and sceptics. Yet the effect of green pseudoscience is arguably much further-reaching.”
    http://www.climate-resistance.org/2013/08/science-without-an-object.html

    Re-quote ‘..so many activists really don’t know what they are talking about ..’. The paper you review can surely only have ever been intended as a piece of activism, a contribution to their cause.

  15. Authors Burke and Miguel also wrote in 2009 that “Warming increases the risk of civil war in Africa”, based on linear regression. [Comment on this paper by Sutton et al., reply by Burke et al.]

  16. Dr. Briggs, You’ve uncharacteristically missed the point: They almost certainly received a grant of no mean sum, and enhanced their stature by being “published”. Mission accomplished, at certainly less cost than pairing up the requisite number of monkeys with ancient Smith-Coronas, although it might not take the simians long to churn out a paper of at least the same quality.

  17. Steven Shafer

    9 August 2013 at 1:35 pm

    Dr. Briggs:

    Your comments may be correct, and I applaud your critical review of the manuscript in Science. However, I am confident that Science sent the paper for a rigorous statistical review. That is how peer review works.

    Most readers, myself included, do not have the domain expertise to know whether your comments about the Science manuscript are valid. However, your concerns seem sufficiently straightforward that I find it difficult to believe they were overlooked in the peer review process.

    I encourage your succinctly summarizing your concerns in a Letter to the Editor of Science. If your concerns are reasonably meritorious, then the authors will be afforded an opportunity to directly respond to your concerns.

    It is clear from your “About WMB” page that you know how the process works. Please set an example for your readers, who may not understand the difference between blogs and the peer reviewed scientific literature, by submitting your concerns as a Letter to the Editor. You then can summarize the process, and result, in a future blog.

    Respectfully submitted,

    Steven L. Shafer, MD
    Professor of Anesthesiology, Perioperative and Pain Medicine
    Stanford University

  18. Dr Briggs, I have only read the paper in Science, not the supporting info. I came to the same conclusion as you did: this is utter garbage.

    Dr Shafer: The paper under discussion is really awful. The problem, however, is that the AAAS, publisher of Science, Nature and PNAS, are all infected with the politically correct versions of climate change. Any paper with respect to climate change being caused by CAGW will be published, preferentially by members of the academy. And it is this latter category which is labelled “peer reviewed” whilst it is is not. Academy members are allowed to publish semingly peer reviewed papers whilst they are not vetted by peer review.

  19. Follow the electrons … be it in the solar flares lashed out from the sun .. or in the environment coming out from the energy of negative emotions, energy produced in negative thoughts and negative deeds … there is a science for the battle against sin-ions of the electrons

  20. Briggs

    11 August 2013 at 9:32 am

    Steven,

    Thanks for your thoughtful comments.

    I’m as sure as you are that the paper went out for peer review. But that means this is just one more case in which that very weak filter of truth failed. Perhaps the results were just too exciting, or the reviewers too busy, or maybe they didn’t or couldn’t follow the work. Who knows?

    But this paper is so bad and so unreasonable, both statistical and sociologically, that some deeper explanation is called for. And even that is not too far to seek. Research in global warming is often silly, rushed, and biased. Regular readers of this blog will understand this, as I often take apart these papers, each of them peer-reviewed.

    I used to do somewhat as you say, and write the authors of the papers offering them full space for a rebuttal. Only one party ever answered. Lately, I have given up. Most people aren’t interested in discovering they are wrong. Even in this case, after the many criticisms, Hsiang and pals are sticking to their story. Well, that’s human nature.

    Now I could work up the whole critique and cast it into the acceptable standard form and send it to Science, which would almost certainly ignore it. Don’t forget that Science not only published Hsiang’s paper, but accompanied it with a glowing, the-end-is-nigh editorial.

    And here’s the kicker: I’d have to do all this pro bono. I am independent. I hold no grants. I have no income except for the consulting I can glean from this web page. Who’s going to pay for me to write papers? I’ve actually done a few, very formal, criticisms, meaning I paid for them out of my own pocket. What came of them? Nothing.

    Let me ask you this: what difference does it make where a criticism originates? None, of course. It would be a fallacy to say that my critique is false because it is found on a blog.

    I’d very happily allow Hsiang, or probably even anybody (as long as they could write well and put an argument over reasonably), to post a rebuttal to my criticism. Regular readers will know I do this when people ask. And then I would proceed to show just where the rebuttal is wrong, and where I agree with it.

    And isn’t that how science is done?

  21. Some historical views…

    Climate and Crime, 1897….

    http://docs.lib.noaa.gov/rescue/mwr/025/mwr-025-06-0259c.pdf

    Climate and Crime, in Cleveland, Ohio, 1999-2004…

    http://journals.ametsoc.org/doi/full/10.1175/2010WCAS1043.1?prevSearch=crime&searchHistoryKey=

  22. Follow the electrons it is the maker and sustainer of violence… be it in the solar flares lashed out from the sun .. or in the environment coming out from the energy of negative emotions, energy produced in negative thoughts and negative deeds … there is a science for the battle against the sin-ions of electrons

  23. Correlation is not causation… that was drilled into my head in grad school.

Comments are closed.

© 2014 William M. Briggs

Theme by Anders NorenUp ↑