Briggs schools the "Bad Astronomer" on statistics

The Saturnian moon Mimas, photographed by the ...
The AGW Alliance Death Star - cratered from continuous bombardment - Image via Wikipedia

That letter signed by 16 scientists saying there’s “No Need to Panic About Global Warming” to the Wall Street Journal has caused a great disturbance in the farce. At last count there were no less than  19 blog rebuttals plus one new WSJ op ed piece trying to convince the alliance that all is well. It didn’t work.

But, they know the AGW Alliance Death Star has been compromised before its mission can be completed, the Rebellion has seen the plans and the Alliance knows it is only a matter of time before “the consensus” blows apart. Reports are that “Michael Mann has been tweeting furiously“, but the reinforcements he’s bringing in may not be able to stop the Rebellion as its ranks swell with ordinary people.

Here at WUWT, we had our best day ever on January 31st with 229,000 views from ordinary people, exceeding the heady days just after Climategate 1 and Copenhagen. People are coming in out of the cold to embrace the warmth and declare it good, while laughing at the folly of the alliance.

Meanwhile, the Bad Astronomer (Phil Plait er, not Jim Hansen) has been spinning in low orbit trying tell alliance forces that the past 10-15 years of stalled temperature rise are just a statistical illusion.

William Briggs, Statistician to the Stars, schools Plait on what statistics really is and writes:

Remember when I said how you shouldn’t draw straight lines in time series and then speak of the line as if the line was the data itself? About how the starting point made a big difference in the slope of the line, and how not accounting for uncertainty in the starting date translates into over-certainty in the results?

If you can’t recall, refresh your memory: How To Cheat, Or Fool Yourself, With Time Series: Climate Example.

Well, not everybody read those warnings. As an example of somebody who didn’t do his homework, I give you Phil Plait, a fellow who prides himself on exposing bad astronomy and blogs at Discover magazine. Well, Phil, old boy, I am the Statistician to the Stars—get it? get it?1—and I’m here to set you right.

The Wall Street Journal on 27 January 2012 published a letter from sixteen scientists entitled, No Need to Panic About Global Warming, the punchline of which was:

Every candidate should support rational measures to protect and improve our environment, but it makes no sense at all to back expensive programs that divert resources from real needs and are based on alarming but untenable claims of “incontrovertible” evidence.

Plait in response to these seemingly ho-hum words took the approach apoplectic, and fretted that “denialists” were reaching lower. Reaching where he never said. He never did say what a “denialist” was, either; but we can guess it is defined as “Whoever disagrees with Phil Plait.”

The WSJ‘s crew said, “Perhaps the most inconvenient fact is the lack of global warming for well over 10 years now.” This allowed Plait to break out the italics and respond, “What the what?” I would’ve guessed that the scientists’ statement was fairly clear and even true. But Plait said, “That statement, to put it bluntly, is dead wrong.” Was it?

Plait then slipped in a picture, one which he thought was a devastating touché. He was so exercised by his effort that he broke out into triumphal clichés like “crushed to dust” and “scraping the bottom of the barrel.” You know what they say about astronomers. Anyway, here’s the picture:

Global warming

See that red line? It’s drawn on a time series—wait! No it isn’t. Those dots are not what Plait thinks they are. They are not—they most certainly are not—global temperatures.

Read the whole rebuttal here, well worth your time.

0 0 votes
Article Rating

Discover more from Watts Up With That?

Subscribe to get the latest posts sent to your email.

156 Comments
Inline Feedbacks
View all comments
Camburn
February 1, 2012 6:48 pm

Allesandro Filipeppi says:
February 1, 2012 at 6:36 pm
This site is a wonderful site. It actually allows discussion!!!!! Some other sites allow one way drivel, so they are basically worthless.
Thank You Anthony for your policy.

Gneiss
February 1, 2012 6:51 pm

rep49 writes,
“Only GISS thinks 2010 was the hottest on record. UAH and CRU seem to disagree”
No, NCDC agrees also that 2010 was hottest. CRU probably will too once the new version comes out, in which they finally add an arctic to their globe. As for UAH and RSS, the upper-troposphere estimates are batted around more by El Nino, so you’re right they still show that “super El Nino” year 1998 as a spike.
BEST goes only to 2009 but as a land-only record it’s not much impressed by El Nino and ’98 is way down on the list.

pouncer
February 1, 2012 7:00 pm

‘The WSJ‘s crew said, “Perhaps the most inconvenient fact is the lack of global warming for well over 10 years now.” ‘
Please note that “inconvenient” whether used by Al Gore or Burt Rutan is not term of art in science or statistics. The adjective characterizes the persuasive and political power of the fact. The fact is that for 10 years or so the best measure (or perhaps, estimates or models) of this concept called “global temperatures” has shown a relatively flat trend. This, while all the while the amount of CO2 (called “carbon” in the intended-to-be persuasive claims) have trended ever upwards. This is another divergence problem and is inconvenient to anyone who would like to assert that the simply basic incontrovertible physics is somehow settled.

Gneiss
February 1, 2012 7:06 pm

James Sexton writes,
“English your first language or interpretive skills a bit diminished?
Here’s what he said, “Actually, of course, an average is a model—at least if you want to attach any meaning to it. It at least assumes the data that went into the model is measured without error.””
Briggs is a terrible writer but my interpretive skills could be poor as well. Help me out here – in Briggs’ last sentence above, what do you think is the antecedent for the pronoun “it”? I think the antecedent is “average.”
In many applications people actually use averages because things are measured with error. Briggs statement simply is false, unless it depends in some tricky way on what “it” means?

Frank Kotler
February 1, 2012 7:16 pm

Glenn Tamblyn says:
February 1, 2012 at 3:02 pm
… The point when looking at data is to know what time scale one should be looking at for the conclusion one wishes to draw…
—————————————-
You just said a mouthful!
If the question is, “No warming for ten years, true or false?”, the appropriate time scale is obviously ten years.
I prefer a much longer time scale – say 300,000,000 years or so. The planet is obviously cooling off and running out of CO2. Something must be done!
What conclusion do you wish to draw, Glenn? Do you get my point?

Andy Clark
February 1, 2012 7:16 pm

“disturbance in the farce” . . . brilliant!
Keep up the good work, Anthony!

Editor
February 1, 2012 7:18 pm

Gneiss says: February 1, 2012 at 6:51 pm
No, NCDC agrees also that 2010 was hottest.
Is this the source of your statement?
http://lwf.ncdc.noaa.gov/sotc/service/global/global-land-ocean-mntp-anom/201001-201012.gif
Doesn’t look like NCDC agrees.
CRU probably will too once the new version comes out, in which they finally add an arctic to their globe.
Yeah, they’ll adjust those temperatures no matter what it takes.

February 1, 2012 7:40 pm

I think some people are losing sight of the actual sceptical position if they keep ‘reminding’ sceptics that 2010 was ‘the hottest year on record’. The majority of sceptics accept and expect warming in the .5C to 1.5C range, with a best estimate of probably 1C. So every decade or so most of us are expecting to see a record broken. (Although sceptics are not certain of this. There could be time spans of 30 years or longer where there is no significant warming or even a negative trend.)
A reminder: it is perfectly consistent with the sceptical position that we cannot see any climate crisis occurring over the remaining 88 years. It’s consistent with the expectation that there will be long stretching of no warming, even cooling. It’s consistent with the notion that natural variability will tend to drown out the influence of CO2 over decadal time scales. So if some here want to remind readers that “2010 was the hottest” in the sense that it may have been hotter than 1998 by some statically insignificant amount, you are not affirming anything that most of us don’t already agree with.
It would be preferable if warmists could attempt a defence of a claim that is actually in dispute…

James Sexton
February 1, 2012 8:10 pm

Gneiss says:
February 1, 2012 at 7:06 pm
James Sexton writes,
“English your first language or interpretive skills a bit diminished?
Here’s what he said, “Actually, of course, an average is a model—at least if you want to attach any meaning to it. It at least assumes the data that went into the model is measured without error.”
…….In many applications people actually use averages because things are measured with error. Briggs statement simply is false, unless it depends in some tricky way on what “it” means?
===========================================================
Indeed. I interpret the “it” as to meaning averages as well. And, averaging does assume data is without error. For instance….. When I state the average of 9 and 17 is13, there are no errors in the input of 9 or 17. But, that isn’t what our temp records are doing, is it? In an extreme simplified hypothetical, our temp record is stating 1 (+/- 3) averaged with 3 (+/-4) is equal to 2! then the next year is 1.1 (+/-3) and 3.4 (+/-4) and that averages 2.2! So the trend is 0.2/yr!! And that, isn’t an average of anything. It isn’t a trend of anything. It’s madness. If you want a good example of this, go look at some dendro graphs.
I believe that’s the thought he was trying to convey.

James Sexton
February 1, 2012 8:23 pm

Gneiss says:
February 1, 2012 at 6:29 pm
James Sexton writes.
“Friend, were I name calling, I can assure you, you would have no question. I simply use that as a descriptive term for people alarmed by CO2 and global temps.”
[SNIP: You are pushing it. We DO mind. Refresh yourself with regard to site policy here. -REP]
==========================================
Gneiss, honestly, I’m not using it as a pejorative. If you’ve another term descriptive of people alarmed by such, let’s hear it. I’m open to more apt descriptions. Truly, I don’t wish you to fall out of favor with our moderators. Provocative can be fun, but let’s ensure an open dialogue. Don’t feel bad, I’ve been snipped a few times myself.

GregO
February 1, 2012 9:07 pm

Will Nitschke says:
February 1, 2012 at 7:40 pm
“I think some people are losing sight of the actual skeptical position…”
Totally agree with your post with one caveat – I am getting less and less comfortable with reference to the term “natural variability” as it applies to climate; here’s why: It (I think) suggests that there is this thing in the climate system called “natural variability” and that when we use these words, we think we know something about that system.
It’s a word/semantics thing and I think it masks a more clear description, that is, rather than “natural variability” I would suggest we make reference to “unknowns” in the climate system. We just don’t know why we have ice ages; mini ice ages; nice warm times like right now; and these climate parameter spaces shift for reasons we don’t fully understand; and the parts we don’t fully understand should have no name but “unknown” or, it is conjectured that…CO2 blah, blah or solar barycenter blah blah, or heck; we just don’t know.
We have some pretty good ideas, some pretty good observations and measurements – no doubt, but we need to be careful of false certainty.
Oh incidentally, not picking on you, I have been thinking about the “natural variability” term for awhile and I liked the wording of your post so I jumped in.

February 1, 2012 9:28 pm

Glenn Tamblyn says: February 1, 2012 at 2:23 pm
Just a repost of what I put up for Briggs. I notice WUWT has copied his bit of plagiarism.
————–
No plagiarism. Nobody with more than an inkling of statistical comprehension would pretend that it was their work.
Attribution was sufficient to identify the incompetent.
Statistics is not just plotting points and drawing lines; but to understand when and if those points and lines mean anything real or are just a fiction; a construct of the imagination/self-deception.

February 1, 2012 10:23 pm

BTW: Briggsy’s blog is definite worth a bookmark. His blog is one of the few to which I link from my blog. Not that that means much to anybody but me.
He’s enhanced (corrected) some of my thinking over the past year or so and provided sane commentary on the prevailing insanity supported by the inappropriate/careless ab-/use of statistics.
As inappropriate as using a screwdriver as a chisel. It’s the wrong tool because the results are doomed to be poor and the screwdriver soon becomes useless as a screwdriver.

February 1, 2012 10:33 pm

Michael Tobis says:
February 1, 2012 at 2:05 pm
“Are you for real? Stick ya head out the window and have a look.”
Hmm. That’s not an especially sound way to do science. But it’s amusing that you say so right now.
I take it you are not in New York City, where the current temperature is 61 F (normal high for the date is 38 F). And you’re not here in Austin, where it’s 83 F (normal high 62 F). In fact pretty much the whole US except California and Alaska appears quite warm, and in some places extraordinarily warm, today.

*looks out of window*
And yet here in Japan, we’re having a most brutal winter, with temperatures WAY below normal, lots of winter-related accidents and deaths, and some parts have houses buried in over 3 meters of snow.
Here’s a picture I took of the view outside my window, for your benefit…

Please send some of your alleged CO2-caused global warming over here – we need it badly.

February 1, 2012 10:37 pm

I hate that WUWT is limited in how comments can have embedded photos in them or not… (thanks due to being hosted at WordPress).. here’s the picture…
From my window right now…

Christopher Hanley
February 1, 2012 11:31 pm

Dr Roy Spencer always adds a rider to his monthly UAH satellite reports that the 3rd order polynomial fit overlay has no predictive value — “… is for entertainment purposes only…”.
Trenberth’s statement, variations of which have appeared a lot recently, that the past decade “..was the warmest decade on record..” is not inconsistent with the statement that there has been a “..lack of warming for more than a decade..”.
“…climate experts know that the long-term warming trend has not abated in the past decade…” (Trenberth).
Alarmists seem to be saying that the least squares linear fit for the past 30+ years does have predictive value.

DirkH
February 2, 2012 12:26 am

Gneiss says:
February 1, 2012 at 7:06 pm
“In many applications people actually use averages because things are measured with error. Briggs statement simply is false, unless it depends in some tricky way on what “it” means?”
If people do use averages because they think it helps against the measurement error, they are right only insofar as the amplitude of the error is reduced by the root of the number of measurements; assuming a normal distribution of the error. BUT one would expect that they know that, mention it, mention the original error and the reduced error after the averaging, and I don’t recall ever having seen that.
If scientists average such error-ridden measurements and then treat the average as error-free, and then come to a result that they also treat as error-free, it is up to you as the reader to ADD the error back in again in the end – in other words; treat the conclusion of such a paper as uncertain, erroneous, false, your pick. Because in that case, the authors simply forgot about that important last step.

February 2, 2012 12:44 am

Sad isn’t it when one discovers people talk science without the faintest idea of what measurements are.

Allan MacRae
February 2, 2012 1:43 am

I like William Briggs – I think he is an honorable man and a capable statistician.
He wrote this in 2008
http://wmbriggs.com/blog/?s=macrae
Excerpt:
The question we hope to answer is, given the limitations of these data sets, with this small number of years, and ignoring the measurement error of all involved (which might be substantial), does (Hypothesis 1) increasing CO2 now predict positive temperature change later, or does (Hypothesis 2) increasing temperatures now predict positive CO2 change later? …
All I am confident of saying is, conditional on this data and its limitations etc., that Hypothesis 2 is more probable than Hypothesis 1, but I won’t say how much more probable.
(end of excerpt)
Mr. Briggs, for good reasons, looked only at annual (12 month) lags. My previous conclusion was that dCO2/dt changes contemporaneously with temperature, and atmospheric CO2 lags temperature by 9 months. I expect that Briggs conclusion would be stronger in favor of Hypo 2 (increasing temperature change now predicts positive CO2 change later) if he were able to accept a methodology that examined a 9-month delay rather than a 12-month one.

John Brookes
February 2, 2012 2:27 am

“I think some people are losing sight of the actual sceptical position if they keep ‘reminding’ sceptics that 2010 was ‘the hottest year on record’. The majority of sceptics accept and expect warming in the .5C to 1.5C range, with a best estimate of probably 1C. ”
Come on! The “skeptical” position is to argue about everything, and never concede anything.
If Anthony would like to put a post up here where the facts that “skeptics” agree on are listed, I would be most grateful. But I suspect the list would be too short to be statistically significant….

Chris Wright
February 2, 2012 3:39 am

I’m still not sure exactly how that graph was constructed, but it’s clearly not a graph of global warming. Compare it with the Crutem3 land global mean:
http://www.woodfortrees.org/plot/crutem3vgl/from:1970/mean:1
I think the fact that many believers obstinately claim that the global temperature is still going up (or ‘going up fast’ as the New Scientist stated a couple of years ago) speaks volumes.
The great tragedy is that the vast proportion of ordinary people will assume everything they hear from climate scientists is true.
Or maybe not. Despite these endless lies the opinion polls show that ordinary people are becoming increasingly sceptical.
Chris

John Mason
February 2, 2012 4:10 am

John Brookes says: “Come on! The “skeptical” position is to argue about everything, and never concede anything. If Anthony would like to put a post up here where the facts that “skeptics” agree on are listed, I would be most grateful. But I suspect the list would be too short to be statistically significant….”
This is something I struggle with at times too. I think it boils down to:
a) there is no global warming;
or b) it’s warming a little bit but that’s nothing to do with us (sun, cosmic rays, even gravity (!!!));
or c) it’s warming a little bit and it’s to do with us but the little bit is too tiddly to worry about (e.g. Monckton, WUWT posts passim)
There are probably more but these seem to be the three main themes as argued on blogs like this one. Are you ever going to decide which one will do as a mission-statement, or is that not the point?
I think we would all be interested to know.

banjo
February 2, 2012 4:34 am

John Brookes says:
If Anthony would like to put a post up here where the facts that “skeptics” agree on are listed, I would be most grateful. But I suspect the list would be too short to be statistically significant….
I`m sure he could.
However if it`s information you `would be most grateful for`(really?) you`re sitting in front of
of a wonderful utility that could get you that information at the press of a few keys.
Please feel free to waste as much of your time as you wish.Unless of course,as i suspect you were just being facetious.
How many skeptics have you converted with that so far?

banjo
February 2, 2012 4:44 am

Maybe a better post would be “The Ineffectiveness of Trolls and Trolling`

Chris
February 2, 2012 6:52 am

Wow, Phil Plait is a bad man. He’s posted a rebuttal
http://blogs.discovermagazine.com/badastronomy/2012/02/02/a-case-study-of-the-tactics-of-climate-change-denial-in-which-i-am-the-target/
using evidence, facts and logic to make us deniers look incompetent. Shame on him.

Verified by MonsterInsights