Are you more likely to die by god or The Man?

Somebody posts this comment somewhere on Fb and I see it in my feed: “Because you are more likely to be killed by lightning then police.”

To which I immediately call bullshit. I don’t find this absurd because of the specific nature of the things being compared (police- versus lightning-caused deaths), but because of the stupidity of the statistics involved. Note that this is a post about statistics, not police killings.

The attached graphic shows NOAA data ( on lightning deaths by state for a period of 10 years from 2005-2014. You can see that in Delaware, New Hampshire, North Dakota, Washington DC, Alaska, Hawaii, Puerto Rico, the Virgin Islands, and Washington there are no lightning caused deaths. This means that if there were any killings by police in any of those states during any year in that time frame, YOU WERE INFINITELY MORE LIKELY TO BE KILLED BY POLICE THAN BY LIGHTNING in those states during that timeframe.

lightning deaths by state 2005-2014

Wow. Infinitely more likely…that’s major. Except, it probably isn’t because it’s not descriptive of anything that people should actually care about nor is it at all predictive. For example (and this is just a hypothetical example that is meant to be plausible but is not described herein as true), if you live in Florida but you make a point of never being outside when there is a storm, then you are probably never going to have any chance of dying from a lightning strike.

People generally seem to think that: if X people die from some activity (in some place, for some period of time), and there are Y people in the target demographic, then X/Y is the probability of some other person dying from the same activity. But this is not at all what anybody actually cares about (and it’s wrong, but more on the wrong-ness in the next paragraph). Because as individuals at risk of death we don’t care about the aggregate; in as much as we think about it at all, we care about our own particular situation in any given place at any given time.

The notion that X/Y is the probability of some other person dying from some cause for which X people did die is completely wrong. Why is it wrong? Part (or all) of the reason most (or all) death rate statistics are wrong/meaningless, is that we have absolutely no notion of the frequency of attempts of the death causing activity on any particular individual’s life. If you get a kick out of playing golf during thunderstorms in Florida, regardless of whatever X/Y is, you’re more likely to get struck by lightning than anybody who stays inside during storms. As a scientist, I want to specify all of the parameters that go into a particular calculation (X/Y). As soon as I do that for an individual death, however, what I discover is that I have described only how an individual died. X/Y no longer tells me anything about how some other person in some other situation (similar though it might be) may die.

-JD Cross


Scalia nails it. I would say that SCOTUS has failed, except failed is putting it infinitely too mildly.

Is Scalia Chuck Silberman? It’s the same dysfunctional world they both find themselves in, and us, too. Words, alas, no longer have any meaning.

Note that this commentary is NOT about whether the ACA is good or bad or whatever. It’s just about language and whether language is important or not.

-JD Cross

Unintended Consequences: campaign finance reform failure

George Will writes about campaign finance reform (Citizens United) and includes this gem at the end:

The limits the reformers hoped would decrease cynicism about politics are increasing it, which is just another unpleasant surprise for reformers who are repeatedly surprised by their own consequences. Someday even they might understand the wisdom of choosing what the Constitution, properly construed, actually requires: unregulated politics.

Senator Beal is repeatedly surprised by the consequences of her and Commissioner McGrady’s actions. They never learn or understand any wisdom, but they are forced to live with the consequences of what they’ve built.

-JD Cross

How to be misled by polls, pols edition

The NYT has this fairly trivial piece on Hilary Clinton’s polling numbers post-Emailgate. I know I’m nitpicking here, but this paragraph bothers me a lot:

This approach is misleading for two reasons. First, CNN gives its own poll too much weight compared with polling averages, creating a perception of decline in Mrs. Clinton’s ratings that could be a result of sampling error.

What bothers me most is that the article continues. Why does this bother me? Because if there is sampling error, then no other reason matters. The poll should be thrown out. Period. End of story.

Furthermore, the author suggests that there could be sampling error. Ok…but is there sampling error? Is this a baseless accusation? If we’re lining up a bunch of “coulds” for why the polling could be incorrect, then the article could go on for dozens of pages. This strikes me as ridiculously sloppy and poorly thought out.

Is there sampling error? Or not? That’s the real story.

-JD Cross

Complex systems are complex

I use the previous phrase often and in many circumstances. While it seems redundant, trivial, and self-descriptive in an obvious way, the connotation that I have when I use it is that people often recognize that systems are complex in the inner workings and/or relationships with things other than themselves, but that they don’t really understand what it means for something to have complex relationships. For example: you recognize that a car is a complex mechanical object, but you don’t really have any idea what it means for it to be complex, nor how complex it is; Complex is often a trivially useless descriptor.

My connotation in saying that complex systems are complex is that there are profound things about such systems that are not currently understood (by anybody, even, in the example above, a skilled auto mechanic), and, in some stronger and very important cases, things about such systems that cannot ever be understood.

In introductory physics, you solve a lot of problems having to do with ropes falling off of tables and objects accelerating from rest. You might even do a fun momentum problem in which a running back collides with a linebacker. But do you ever do problems with more than two objects interacting? No. That’s a many-body problem and it is saved for physics majors to tackle in mechanics or advanced mechanics. But how many bodies constitute solvable problems versus very hard or impossible problems?

Here’s an apocryphal story of Daniel Patrick Moynihan asking a Harvard chemist this question. (also, see here.)

A while back, one of Harvard’s great chemists was discoursing on what he called the “many-body problem,” a condition in which the number of variables interacting with one another in any given situation makes that situation extraordinarily complicated and difficult to fathom. I asked in what range of numbers this “many-body problem” begins. A somewhat suspicious glance was returned. Did I really not know? Apparently not. “Three,” he replied.

In the physical sciences, complexity starts at around 3 interacting objects. I always maintain that any system that involves humans is complex. Why? Because humans don’t even understand how themselves, let alone how one human interacts with any number of other humans. We don’t understand our own behavior; sociologists don’t understand our behavior, psychologists don’t understand our behavior, and certainly politicians don’t. We don’t know what policies will work in advance, and it’s rare, and we’re exceptionally lucky if we even can collect the data to understand what policies have worked a posteriori.

-JD Cross


The sugar industry and the US government were in bed with each other and the loser was everybody’s teeth.

It is not surprising to me that there are people who want to influence (lobby) what the government does, what it regulates, how it taxes certain things, what kinds of recommendations it makes. Such is the nature of power and influence. It is inevitable.

What is surprising to me is that most people that I know think the government is good and want more of it while at the same time decrying lobbying. People: problems of power and influence (lobbying) happen BECAUSE there is government. To the extent that there is more government with more power, the problems can only get worse. There is no other option.

It’s dramatized in reality in the link above, and in fiction in Evolve.

-JD Cross

Stock picking

The future is hard to predict, especially if you pretend that you can see it.

The blind forecaster beats a panel of industry “experts“. This isn’t really news, as reports like this are published as articles or books quite regularly. It is good, though, to always remind oneself of how most of economics and all of sociology is NOT at all like physics. There is no determinism. There are no equations of motions.

People, as the actors in the system, mess everything up. Second, are at least equally important, is that the number of variables in the system is fantastically large.

Can you think of any other systems with fantastically large numbers of variables for which people regularly make headlines for predicting the future?

-JD Cross


Get every new post delivered to your Inbox.

Join 161 other followers

%d bloggers like this: