Weather or Not People are Bayesians

A new paper by Tatyana Deryugina finds that people make inferences about global warming from local weather but, given that they use local information, their inferences are mostly consistent with rational updating with some deviations in the very short run. Much more important than local weather, however, are other factors such as education and ideology.

…a Bayesian who is perfectly informed about world weather and science should
not give signicant weight to recent weather in his county when updating his beliefs. However, I
find that some forms of temperature and precipitation abnormalities have an effect over short time
scales of 1-2 days. Average weekly deviations and extreme events such as heat waves or droughts
weeks or months before the survey have no effect on beliefs, suggesting that the short run effects
are temporary and due to psychological heuristics.

Unlike previous studies, I also consider the effects of prolonged periods (1-12 months) of
abnormal weather. I find that abnormally low precipitation and abnormally high temperatures are
signicant predictors of the degree to which people believe the effects of global warming have
already begun to happen. The estimated patterns are consistent with how a Bayesian who only
observes local information would update his beliefs, but I cannot rule out that informed individuals
simply overweight their local weather.

…The marginal effects of education, relative to high school [on “the effects of global warming have already begun to happen”]  is 0.045 for “some college”, 0.101 for “college”, and 0.166 for “graduate school” A day on which precipitation is 2.5 standard deviations above normal would produce a change
in beliefs about the timing of global warming comparable to the estimated correlation between beliefs and “some college”. Precipitation would have to be 8 standard deviations above normal to produce a change in beliefs comparable to the coefcient of “graduate school”…In addition, the [weather] effects are short-lived because the average standard deviation over the past week does not change beliefs.

Hat tip: @jzilinksy via @bryan_caplan.

Addendum: Yes, the title of the post was on purpose!


However, a period of intense heat can hit home the potential impact of global warming on your life. i.e. the short burst may not prove global warming, but it may make you think of the consequences if the theory is true. The more you fear the consequences of global warning the more you adjust your risk perception of the threat of global warming.

Of course, for people around here (Chicago), after cold years, it just gets a "you just spent four years saying "weather is not climate", asshole"

(This is not a comment on global warming, but on the fact that the advocates shoot themselves between their feet and their faces all the time in their eagerness to convince the masses)

I did not take a stand on global warming. I just said that if people are given a brief, intense exposure to something it can change perceptions. Call it the Scrooge effect if you want. Exposure to ghosts changed perceptions. In the case of global warming assume that the person is 50/50 on his belief in global warming and his perception is that the potential damage to his climate quality is a -5%. The exposure to a brief intense negative weather pattern changes his perception to the view that global warming has the potential to damage his climate quality by -40%. His fear or perception of global warming has increased. He has a greater fear of a negative outcome. That might move perceptions of the risk.

The same with global flu. People can have very different perceptions of the danger (a combination of the possibility and the impact). For such rare events, people can have very different perspectives.

This paper is not about global warming. it's classic sociology with math on top (a time-honored academic sub-disipline for people wanting to marry an economist or minor physicist.)

Perhaps this paper is providing evidence that belief in the wisdom of "experts" increases with education.

ARGH. I was going to write "INB4 'It's 'whether,' dude'!"...but I was pre-empted by the OP. Curses.

I thought "global warming" was caused by Al Gore.
Is Al Gore a Bayesian?

All I know for sure is that it's been exceptionally above average here in the DC area starting in May. Looking at the heat map here: seems to indicate to me that this is a general phenomenon across a great swath of the country. You don't need to be schooled in Bayesian statistics to realize that something is going on.

"something is going on"

Yes, but what? It's probably the worst heat wave since the 1930's (haven't seen any good analysis, but it seems a lot of daily records from the 30's are being broken but a lot are still standing). But that does not tell us whether or not an 80-year break between this kind of weather is a normal length of time.

"You don’t need to be schooled in Bayesian statistics to realize that something is going on."

You need to be schooled in statistics to realize that the current heat wave may just be an outlier and not 'proof' of global warming. Though the obvious point that this is the worst heat wave 'since' the 1930's should be a clue that if we are experiencing global warming then it's a very gradual process.

Weather, not climate. As written above, the global warming activists have pissed all over themselves in eagerness to jump on a hot year after a number of cold ones

It doesn't mean they're wrong (and, broadly speaking, I don't think they are), it means they're willing to deceive in order to press their case.

I'd be much more inclined to buy the argument that abnormally hot weather proves AGW if advocates would concede abnormally cold weather disproves it.

Humans are bad at perspective, and even worse at estimating how bad they are.

Who or what is better at perspective, and estimating its/their perspective, than humans?

"Humans are bad at perspective, and even worse at estimating how bad THEY are."

Well played, sir.

Having lived on and off in Southern California for the last half century, I've often thought of whether I can detect any secular trends in the climate from evidence of daily life. Are hillsides browner or greener than when I was a child? Does the June Gloom last longer or shorter?

I have not been able to notice any persuasive evidence with my own eyes. This doesn't mean that global warming isn't happening, just that year to year noise is swamping it. For example, this and the previous two summers in L.A. have been exceptionally cool. Is that evidence for Global Cooling? Probably not -- it's likely just randomness.

It could be that in other parts of the country, people have noticed evidence for a secular warming trend in their own lives. But, I suspect most people who are fervent believers in Global Warming are particularly ardent because the changes are too subtle for them to notice. They strongly _want_ to believe in Things Unseen as proclaimed by Those Who Know. It's more prestigious to believe in something

In contrast, it's easy for me to note all sorts of interesting demographic changes in Los Angeles over my lifetime. For example, when I was a kid in the San Fernando Valley in the 1960s and 1970s, Jewish kids almost always went to public school. They considered us Catholic school kids kind of disloyal and maybe unAmerican. These days, however, Jewish kids in the same neighborhoods almost alway go to private schools.

Now, demographic changes like that are easy to notice with your own eyes, but, you'll also notice, that it's extremely unprestigious to mention in public that you've noticed them, much less that you believe that thinking rigorously about such changes could lead to other important insights. It's much more prestigious to believe in the Evidence of Things Unseen.

Thought the title said "WEALTHIER people are Bayesians". Anybody know if they are? Studies?

People /cannot/ be Bayesians. Bayesianism requires that one be able to observe the data directly, without bias and then use bayesian updating to update our priors. We can't do that because our data is filtered through a bayesian filter that contains our priors already, before it reaches the bayesian updating portion of our thought processes.

Byline to this should be mood affiliation. Especially in regard to the comments.

From what I understand the warming due to AGW is about 1 degree. So the hottest days a 1 degree hotter and coldest nights are about 1 degree warmer. What non climatologist could notice such a small change? I think none.

AVERAGE temperatures are a couple of degrees higher. Wild unpredictable swings in daily temperature are also predicted due to significant change in global weather patterns while still expecting average temperatures to increase. These wild swings can easily include warm winters and cool summers or extremely hot summers and extremely cold winters, each averaging out, worldwide, to a degree or two increase. Since it is worldwide, the US could entirely be colder on average while Asia is warmer on average.

If AGW is not happening, does that mean the opposite of everything concluded by Tatyana Deryugina? I can see the paper now:

The marginal effects of education, relative to high school, indicate that (a) subjects are more likely to be led into faith-based error by people sharing similar credentials and cultural self-regard/other-derision; (b) subjects bossed around and condescended to by educated elites visualized AGWers as a millenarian cult demanding repentance and fear, ritualistic purification and sacrifice, and obeisance and more funding in sandwich boards on a street corner; and (c) subjects who read Katja Vogt or Calvin ("When I see 10 troubles coming down the road, I do nothing and 9 end up in the ditch") Coolidge whimsically wondered whether any cohort, but especially the East Anglia clowns, could do what no other science has: translate spotchy raw data by reference to sensitive, incipient and untested proxies into a comprehensive model of a coupled nonlinear dynamic system, all within one generation of the endeavour's birth.

I want AGW to be wrong not just for my kids, but to witness the coping mechanisms we've witnessed with other fans of fads (socialism, peak oil, high waisted pants, coming plagues, roller disco, stimulus).

Comments for this post are closed