Bad Astronomer Does Bad Statistics: That Wall Street Journal Editorial

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. Each dot instead is an estimate of global temperature: worse, most dots are also different kinds of estimates from each other. That is, the first dot was estimated using data X and method A, and the second dot was estimated using data Y and method B, and so forth. Well, maybe the first and second dot were the same, but older dots are different than the newer ones.

With me so far? All you have to remember is these dots are estimates, results from statistical models. The dots are not raw data. That means the dots are uncertain. At the least, Plait should have shown us some “error bars” around those dots; some kind of measure of uncertainty.

Now—here’s the real tricky part—we do not want the error bars from the estimates, but from the predictions. Remember, the models that gave these dots tried to predict what the global temperature was. When we do see error bars, researchers often make the mistake of showing us the uncertainty of the model parameters, about which we do not care, we cannot see, and are not verifiable. Since the models were supposed to predict temperature, show us the error of the predictions.

I’ve done this (on different but similar data) and I find that the parameter uncertainty is plus or minus a tenth of degree or less. But the prediction uncertainty is (in data like this) anywhere from 0.1 to 0.5 degrees, plus or minus. That is, prediction uncertainty is about five times larger.

I don’t know what the prediction uncertainty is for Plait’s picture. Neither does he. I’d be willing to bet it’s large enough so that we can’t tell with certainty greater than 90% whether temperatures in the 1940s were cooler than in the 2000s. And also such that, just as the WSJ‘s scientists claim, we can’t say with any certainty that the temperatures have been increasing this past decade.

In other words, the scientists were right and Plait was wrong. Or, as he might phrase it, he blatantly misinterpreted long term trends. Notice old Phil (his source, actually) starts, quite arbitrarily, with 1973, a point which is lower than the years preceding this date. If he would have read the post linked above, he would have known this is a common way that cheaters cheat. Not saying you cheated, Phil, old thing. But you didn’t do yourself any favors.

Somewhat amusingly, Plait ends his semi-random venting by telling us that Michael Mann has been “tweeting furiously” about this. Good grief! This isn’t helping his case. Mann’s understanding of statistics may be likened to an overly enthusiastic undergraduate who left the lecture early.


1I’m here all week.

P.S. Hey, Phil. Since you brought it up: the total consideration I’ve received for my work in global warming from Big Oil (or anybody) is number so small that dividing by it is forbidden. How much do you get for your blog or other environmental work, including government funds?

P.P.S. I didn’t forget about that “warmest years on record” stuff. Those “warmest years” are still estimates and have to be compared to the old data, which itself must be accompanied by uncertainty measures. And anyway, it has been much hotter in the past than it is now. Jurassic anybody?

Update Thanks for all the comments, everybody! 100+ and no signs of slowing. I will read them in all, in time, but for now, since many of them repeat odd claims and misunderstanding of statistical methods, let me point you to the BEST project posts (here and here). BEST had parameter-based error bars, but not predictive ones. But some acknowledgment of uncertainty is better than none! Also look under the Start Here tab and pay attention to the smoothing time series posts, the homogenization of temperature series posts, and read this weeks’ All of Statistics series. You may also read, inter alia, the Probability Leakage post which describes the Bayesian predictive approach I am using. A lot of confusion and frank unfamiliarity for some of you.

Update to the Update See this brand-spanking new post that clarifies some of the statistics some of you couldn’t be troubled to look up.

Update See this cartoon which shows that the IPCC has been known to employ the technique of variable start dates.

Update It is imperative that all read this series, where I describe just how so many people make mistakes. Those below who have been shouting the loudest are most in need.


Bad Astronomer Does Bad Statistics: That Wall Street Journal Editorial — 150 Comments

  1. @Rob Ryan

    You obviously have a very limited range of experience with real-world engineering disciplines, including product reliability, quality assurance, manufacturing and industrial engineering. 30 years with a BSME in these fields trains one not to make rash generalizations.

    But of course that’s why AGW alarmists must attack reputations rather than simply prove the science and statistics.

  2. Pingback: Briggs: Bad Astronomer Does Bad Statistics |

  3. To all:

    I don’t sneer or sniggle at the B.S. degree – it’s what I have and it’s in mathematics and I’m proud of it. I don’t sneer at and demean engineers – the ones I know and the ones I employ are bright, eager, engaged, highly ethical, and produce excellent work within tight time frames on a regular basis. I don’t demean Rutan – in the field of aircraft design and aeronautical engineering. I don’t know him personally (though I do personally know a close friend of his) but I’m reasonably sure he would not make the claim that he’s a scientist. I suppose he’d say that what he does (or did actually, having retired) involved scientific principles and used science but my reading of him is that he thinks he’s a designer and an engineer, not a scientist, and rightfully damn proud of it.

    To the nitwit who felt it was necessary to point out that Nastran, ANSYS, ABAQUS, etc, utilize advanced mathematical algorithms, I say “thank you Captain Obvious.” To the claim that “the results are checked”: yes, they’re checked for plausibility, they may be checked for extreme and degenerate cases, etc. But if you mean that the sparse matrices are analyzed by hand or anything similar, I’d call you clueless.

    I’m sure there are many engineers who have kept up with the cutting edge developments in engineering, particularly in the quickly developing areas of materials science, bioengineering, etc. but, as I said, I’m very familiar with the day to day tasks undertaken by many dozens of engineers encompassing the fields of civil, structural, mechanical, and geotechnical (not aeronautical however) and they do little by hand and what they do is trivial from a mathematical point of view (some algebra, some trigonometry). Few of them program using anything other than Excel. A few use MathCad.

    I certainly agree that it matters not if someone is a scientist, an engineer, an accountant, a plumber, or a janitor. It only matters who’s correct. But the WSJ article proclaimed “16 scientists…” It did not proclaim “16 smart people we believe to be correct….” so the term must be considered to have meaning by someone, mustn’t it?

    As to correctness, a cursory review of Rutan’s massive pdf entitled “An Engineers Critique of Global Warming ‘Science’” (scare quotes his) located at:

    shows it’s both fraught with errors and shoddy analysis and follows the typical “it’s not happening and if it is it’s not harmful and if it is we didn’t cause it and if we did we can’t do anything about it and if we can it would cost too much and anyway we landed on the moon and we fly around at subzero temperatures in rarefied air and we can adapt” line of reasoning.

    Rutan is a wonderful aircraft designer, one of the most creative, productive, and financially successful of our time or any time and clearly a brilliant man. But that doesn’t make him an expert on whatever subject in which he decides to dabble. His “Engineer’s Critique” shows that admirably.

  4. Eric (Sceptic)

    This paragraph from the article you linked rather telling:
    “The following figure shows a calculation of straight temperature averages for all of the reporting stations for 1950 to 2000 []. While a straight average is not meaningful for global temperature calculation (since areas with more stations would have higher weighting), it illustrates that the disappearance of so many stations may have introduced an upward temperature bias. As can be seen in the figure, the straight average of all global stations does not fluctuate much until 1990, at which point the average temperature jumps up. ”

    The writer of this post obviously doesn’t know how the temperature products are calculated. None of them average temperatures (area weighted or not) for the obvious reason that such a method WOULD be vulnerable to all sorts of station bias issues. Temperatures changes are reported as anomalies. This is not simply a case of averaging temperatures, seeing how the average has changed an calling that an anomaly. The temperature records first calculate the anomally for each single station relative to its own long term average value, producing an anomaly value for each station. Only then do they do an area weighted average of the anomalies.

    This makes the calculation substantially more robust wrt to station biases etc. And there aren’t any significant coverage issues. If the station count world wide dropped low enough, yes. But the current number of stations adequately covers the Earth.

    I discuss this in more detail in a 4 part series that starts here:

    Since you are a regular commenter at SkS I thought you might have read it.

    As for error margins etc. Go to the original sources – BEST, GISS etc and they do include all that.

    This graphic, being called the Escalator is a reference to the TACTICS used by skeptics to misrepresent information.

  5. Today we will get treated to an annual climate prediction from another Phil in Punxsutawney, PA. Not sure of his track record but he undoubtedly enjoys his subsidy. One of his relatives who lives under my garage rarely makes comments on the weather.

  6. Rob Ryan,

    You’re just digging the hole deeper. It really does seem as suggested in that you are waving the PhD as if it were somehow proof of correctness. You are complaining about the WSJ’s use of English? Scientist vs. Engineer? Isn’t what Burt and the others had to say important? What does it matter how the WSJ characterized things in its headline? Only those with PhD’s are capable of understanding such a subtle topic? C’mon. There are no factual errors you can illuminate for us? Handwaving is all you can do? Stop being silly.

    shows it’s both fraught with errors and shoddy analysis
    But that doesn’t make him an expert on whatever subject in which he decides to dabble. His “Engineer’s Critique” shows that admirably.

    That’s a little better but you still have this “only the annointed can understand this stuff” on your brain. Burt’s PPT would be a good place to start. Now the errors and shoddiness are ….. ? Remember, that’s all we care about here. If he’s correct his personal failings are irrelevant.

    Your turn.

  7. Rob Ryan,

    First off, take a chill pill. It’s just a blog.

    I have a small engineering firm as well. We make all sorts of machinery and equipment and we do some FEA modeling for high pressure components and for parts subjected to vacuum. I have worked in this field for some time. We use tools a bit more sophisticated than Excel and MathCad but we use them as well and do classic analysis as needed.

    Here’s the point. We do a model, and then we test and compare. Example: small high pressure bearing component fails FEA but experience suggests it will work fine. Rationale – stress will “dish-off” from concentration points to larger geometries and model shows failure due to grid resolution. Next step; test the part by pressurization. Measure the part for deflection. Write report – failed FEA; passed pressure test; good for flight.

    We are making a prediction; an informed prediction based on both modeling and empirical observation.

    And I have noticed we all get into rhetorical trouble with analogies but here goes: GCM are also models – not a straight analog to the finite element model I just described, but still models and rather than mechanical are to my limited understanding based on Navier-Stokes equations for fluid state. I admit I have not got a grasp of how boundary conditions and other necessary constraining conditions are done in climate models; but I know they also make predictions – in fact – without these predictions what would we have to talk about?

    If said GCM prediction is falsified, this is interesting, no? Does this not act as an indicator that our model-informed understanding is in need of confirmation; or does this not indicate that our model makes us too certain?

    Please consider re-reading Dr Brigg’s post, especially here:

    “Now—here’s the real tricky part—we do not want the error bars from the estimates, but from the predictions. Remember, the models that gave these dots tried to predict what the global temperature was. When we do see error bars, researchers often make the mistake of showing us the uncertainty of the model parameters, about which we do not care, we cannot see, and are not verifiable. Since the models were supposed to predict temperature, show us the error of the predictions.

    I’ve done this (on different but similar data) and I find that the parameter uncertainty is plus or minus a tenth of degree or less. But the prediction uncertainty is (in data like this) anywhere from 0.1 to 0.5 degrees, plus or minus. That is, prediction uncertainty is about five times larger.”

    Food for thought.

  8. GregO

    From my also limited understanding GCMs are actually closer to FEA than you think. At their heart they divide different parts of the planet up into 3D boxes then model processes within the box and also flows of matter and energy across the box boundaries. In particular they are applying all the conservation laws to these processes and flows. They then let this evolve over time and report what transpires. Commonly the ‘spin up a model’ by starting with a very cold earth and let it run till it stabilises. Then they add perturbations like changes in radiative force from GH gases.

    However, the point you make then reference to Brigg’s text suggesting that the points oin the graph are predictions is simply not true, No models are involved, no GCM’s, no predictions. Each point is simply calculated by applying various averaging techniques to observational data.

  9. wow.

    look at all the people who justified hiding the decline attacking Briggs for failing to link to the source of a graphic.

    look at all the people who thought hiding data was a great idea demanding that Briggs link to a source.?

    Holy crap. If you guys took this kind of attitude back in 2007 or 2008 or 2009 when folks like mcIntyre were demanding more transparency, you wouldn’t have defended the crap you did.

    I suppose we can go look at all RC, Tamino and Sks graphics with this new standard.

  10. Jeez.
    I find it hard to understand that there are people that don’t understand that the global average temperature is derived from a model.

  11. WOW Toby:
    You are all excited about Tammy making a bigger fool of himself.
    Output from a model using Extrapolated WAG. GIGO is the underlying principle behind AGW.

  12. Pingback: Two seemingly contradictory statements on global warming | The Thinker

  13. Glenn Tamblyn,

    Thanks for the link to that post of yours at SkS. I had forgotten you wrote it and I did indeed read it but stopped when you created the new concept of “climate teleconnection” (you wrote: “In Climatology this is the concept of ‘Teleconnection’ – that the climates of different locations are correlated to each other over long distances.”).

    It’s true that teleconnection results in correlation but in reality teleconnection has positive and negative correlation. Your method of long distance temperature averaging assumes positive correlation and has nothing to do with teleconnection, sorry.

    Regarding your reply above, it does not matter if a weighted average is performed on anomalies or on the absolute temperatures, the result is the same. It does not address the bias introduced by dropping stations. Also you have not addressed the fact that the red line is a model. I also contend that the weighted averaging is a model because the averaging techniques require various assumptions about physical reality that you have not made explicit.

  14. Glenn Tamblyn:

    Admittedly, you are offering a short-hand description of how GCMs function but you glossed over a critical component. GCMs don’t “stabilize” without intervention. Multiple runs of the same model produce a range — typically quite broad — of results. The modeler chooses how to restrict the model’s output and, perhaps more important for this debate, how to report these restricted outputs to the public.

  15. Paul D – Can’t you read – I said the escalator has nothing to do with Briggs’ point. It’s the silly bit showing the negative trends allegedly seen only by skeptics.

    Plait recognized it as not relevant to the question “what has been happening to global temperatures” and used only the “realist” (ahr ahr!) part of the animated gif. And frankly, if Briggs comments about Plait, Briggs should comment about the graph Plait showed, not some other graph.

  16. Well, I’m tired of arguing the engineer point. I simply state that I’m reasonably sure that Rutan wouldn’t characterize himself as a scientist – he seems to have little respect for the label (“science doesn’t really exist…”). But the WSJ thought the label was important or influential or something. As for me, I have high regard for both professions.

    It fascinates me that no one has addressed Briggs’ double standard wherein he changes what the “scientists” state in their letter by paraphrasing it in such a way that it’s no longer in violation of the point he’s making in his post.

    WSJ: “Perhaps the most inconvenient fact is the lack of global warming for well over 10 years now.”

    Briggs paraphrasing them: “just as the WSJ‘s scientists claim, we can’t say with any certainty that the temperatures have been increasing this past decade.”

  17. Darn, I wanted to be the 100th reader who wrote the comment on this post.

    My hyperopic right eye tells me that there APPEARS to have an overall positive trend factor (the slope/coefficient associated with time/parameter) since 1973. My myopic left eye tells me that there again APPEARS to have a negative trend since 2005 for this PARTICULAR DATA SETS.

    A conclusion based on fewer data point is usually associated with a higher uncertainty/error.

    The line represents the estimated regression model. No confidence intervals (error bars) for the mean value or predicted value of y are shown in the picture. Anyway, it’d probably only show that the majority of, if not all of, the data points fall inside the intervals, provided the model is adequate.

    However, as we are concerned about the trend/ slope parameter, the standard error of the slope parameter should be reported.

    My problem with many analyses presented on some blogs is that they don’t perform model checking using residuals plot. No, we can’t just pick a model and use it to make conclusions.

    Oh, btw, computing sample average is a special case of linear model with a constant term only. Try fit=model(y~1), input y first though, and check out the R output.


  18. If temperatures stayed absolutely stagnant for the next 100 years, a linear regression starting in 1973 would still show an upward trend; thus any model based off such a simplistic statistical tool would still predict higher temperatures in the following years.

    After reading all of the posts and comments from this site and others (Laden, Plait, Tamino), it seems no one fully understands Briggs’ position. Excuse me for speaking for you Briggs (and correct me if I’m wrong), but he has stated numerous times on this blog and elsewhere that it’s obviously true that humans are affecting the climate. Everyone and everything affects the climate. There is no denial, thus, he is not a “denier.” His qualm is with the perceived magnitude of human impact on the climate, and more specifically, with over-certainty due to lack of statistical rigor. Let’s try and stick to the content of his objection rather than to the fact that he used a JPG instead of a GIF.

  19. I find it fascinating that the good doctor accuses another doctor of making an error “like an undergraduate that left lecture early”, yet makes that very prematurely departing undergraduate error himself.
    “Remember, the models that gave these dots tried to predict what the global temperature was.” is incorrect, the data points (dots) are actually the AVERAGED MEASURED TEMPERATURES from ALL data that was MEASURED. So, in the good doctor’s world, measurement is prediction. Averaging is fallacious. If so, then statistics is a pseudoscience that is based in trickery, which it most certainly is NOT.
    No, from what I’ve read, the good doctor plays with semantics, disparages data sets as predictions, which is an egregious falsehood, as observed, averaged data is not a prediction, it is averaged data.
    Frankly, the only thing the good doctor here has done is make me suspect anything he has ever said in the past and anything he may say in the future. For, with his logic in this instance, he equates observation with fiction in a nineteen eighty fouresque manner in the grandest example of doublethink one could ever imagine!

  20. Am I right in thinking that you are asking for the (quadratic) error bars on the regression to be presented in addition to the maximum likelihood regression?

  21. Rob Ryan:

    From one of the definition below of difference between science and engineering, I have reached my conclusion long time ago, the so-called climate scientists are using their or our current generation’s lousy understanding of the nature and try to come up with some law of nature in Engineering type of practice using mathematical and phsysical equation in terms of model and numerical simulation.

    I am also a PhD in Mechanical Engineer in the field of computational fluid dynamics and heat transfer. What Climate “scientist” or modeler do are no different from what I do to model a flow and heat transfer behavior of combustion gas turbine. But every engineer like me knows the fact of modeling:

    “Garbage in, Garbage out” for the simulation.

    Maybe Climate modeler never has the concern of such principle, is it because they are not subjected to the immediate test result of their prediction 100 or 1000 years down the road. They can claim what ever they “predict” and claims like a inevitable truth. This is bullshit !

    The difference between Science and Engineering:

    The scientist seeks to understand nature at its core, to get to the fundamental essence. To do this, the scientist typically strips away extraneous effects and dives deeply into a very narrow element of nature. And from this look comes what is known as the laws of nature: energy and mass are the same thing, for every action there is an equal and opposite reaction, and so on. There are lots of laws of nature, and they apply everywhere all the time.

    Engineers live with the laws of nature. We have no choice. Our goal is to design things that work within what nature allows us. To do this, we have to be able to predict the behavior of systems. So a big question for engineers is, how do we understand and predict the behavior of systems in which all the laws of nature apply everywhere all the time. This is an issue of integration, and it is every bit as difficult as finding the laws in the first place. To account for all the laws of nature everywhere all the time is an impossible task. So the engineer must find ways of determining which laws are important and which can be neglected, and how to approximate those laws that are important over space and time.

    Engineers do more than merely predict the future. We make decisions based in part on their predictions in the knowledge that their predictions cannot be both precise and certain. Understanding and applying the mathematics of this is also important. This includes the application of probability theory, decision theory, game theory, optimization, control theory, and other such mathematics in the engineering decision making context. This also is a legitimate area of research for engineering.

    Read more:

  22. Pingback: William M. Briggs, Statistician » On Global Warming Apoplexy: Temperature Trends

  23. Pingback: A case study of the tactics of climate change denial, in which I am the target | Bad Astronomy | My Blog

  24. I find it to be thoroughly amusing when clowns like you try SO hard to be high and mighty, as you are here Mr. Briggs. Of course, most people tend to feel bad for the feeble minded idiot who thumps his chest to feel important, but I am not most people. If you want to make an argument that real, thinking people will take seriously, drop the condescension, present your side, and move on. With your first “Old Phil” remark, the rest went right out the window.

  25. Pingback: A case study of the tactics of climate change denial, in which I am the target | Space Travels - Space Turism

  26. Rob Eyan,

    Thanks for your interesting argument but I didn’t find it compelling enough to believe Burt Rutan’s Powerpoint is “both fraught with errors and shoddy analysis” as you have claimed nor that anything regarding climate in the WSJ is false. Maybe you shouldn’t have rested your case on the weakest of points (assuming it a point at all).

    Bob Adams,

    I think Matt answered you here:

  27. Wayne:

    As I mentioned, I’m finished with that argument. My point was that Rutan isn’t a scientist (and though I’m happy to be corrected BY HIM if I’m wrong, I think he does not want to be labelled as one), WSJ thinks the term “scientist” carries some sort of impact. I know what engineers (in general) do for a living. ‘Nuff said.

  28. Sks complains about cherry-picking the end-points.
    Sks produces “the escalator” to highlight the end-point problem.
    Briggs writes and article on dangers of cherry-picking the end-points.
    The bad astronomer removes the escalation animation, and uses the Sks chart.
    Briggs calls out the poor choice of end-points in the sks chart.
    And, Sks accuses Briggs of misrepresnting their chart.

    mmm Irony.

  29. Rob Ryan:

    My question to people or any self absorbed “Scientist” is, if the climate scientist , in particular climate modelers, are using the same basic methodolgy as engineer (fluid and heat transfer mathematical equation and physical or non-physical model) to do numerical simulation on a much more economical and political influential problem – the complex weather/climate problem than an Engineering one, why should climate modeling hold Sub-Par standard of rigor test of its modeling capability and validity?

    if A famous US aircraft engine maker can lose most of its market share financially due to untested unvalidated numerical prediction of their engine performance and wrong commitment to customer (I can tell you which engine maker if you don’t know), then as an analogy, who should we bill to if billions of $ wasted on the artificially blooned AGW problem based on incapable computer model. If we look back 50 years from now. can we charge back on You? Alarmist? The Climate Scientist as a whole? financial beneficiary of Cap and Trade Scheme ?

    In short, prematured science ‘consensus’ can lead to wrong policy and political decision that will affects billions people. This is my engineer point of view that demands rigor for any computing simulation on big problem

  30. I think that the disdain you have those who disagree with you really shows by using “uncertainty” as some mystical word that makes things unknowable really shows. As a statistician, you know that everything has uncertainty, particularly models. And that goes for spatial statistics as well. If you have a problem with a global simulation using station point data, then I see it reasonable to think you have a problem with a basic temperature map on the weather channel. You simply cannot have point data for every point on the Earth, or at a point in every pixel of the resolution. Thus, you interpolate… kriging, IDW, whatever… this where uncertainty comes in. But that’s not what this study was about: getting an average based on interpolation of stations that were “estimated.” Not even close.

    That model uses 39,028 stations of raw, point data (not modeled or estimated).… go here and look at the top of page 7 for the map of stations used. 67% of the stations showed positive slopes. And even if some data there is missing, the uncertainty created would be washed out by the robustness of dataset. So “uncertainty” is not as big of a deal as you make it out to be, and particularly not if you consider the size of the dataset. The uncertainty argument is really just a hand waving exercise in this case. A spatial study of which stations, worldwide were positive and which were negative would be a logical next step in this study. They did it for the US (page 10 of the paper).

    Unless, of course, you think uncertainty makes all models irrelevant. In that case, why bother modeling? And isn’t an average, really at its core, just a model in its plainest form?

  31. Thank you, sir, for taking the BadAstronomer down a notch. I used to be a faithful reader of his blog, until he completely went off the deep end. Anyone who connects AGW skepticism with creationism has lost their objectivity. There are simply too many uncertainties in climate modeling to launch Western civilization down a path to self-destruction.

    I have now added this blog to my “favorites.” Again, thank you!

  32. Someone’s probably already pointed this out, but Will Briggs’ criticism applies equally to the scientists he says are “right”, who rely on exactly the same “estimated” data of Phil Plait (global surface temperature anomaly data).

    Ten-year and (usually) 15-year trends from surface temperature data are not statistically significant – the noise swamps the signal – whereas the trend from 1973 most definitely passes statistical significance tests. Phil Plait 1. WSJ scientists 0.

    The middle section of this article about estimates and predictions is just loopy, but I’m sure that’s been pointed out, too. This article is plutonium-grade nonsense. The WSJ article isn’t much better.

  33. Your prose is reminiscent of lawyer ramblings. It reads as though you’re magician presenting an act of illusion to distort the underlying mechanism.

  34. Maurizio said “Paul D – Can’t you read – I said the escalator has nothing to do with Briggs’ point. It’s the silly bit showing the negative trends allegedly seen only by skeptics.”

    No need to be abusive. I suggest you read my comments.
    The Author of the animation (the graph shown here is a small part of the bigger ‘product’) was making a specific point by including the real myths presented by skeptics. Since you believe they don’t do this (cherry pick data and show it has cooled over a short period), can you show evidence that when you have found a skeptic saying/writing that it has cooled over a short period, that you have told that skeptic that they are wrong and that they shouldn’t promote such misinformation?

    The animation makes a powerful statement that is intended to educate a simple point, no matter what level of education.

  35. Paul D – “Since you believe they don’t do this” – You’re moving goalposts, and I’ve never said anything of the sort.

    The issue was and is the use of the graph as presented by Plait. The fact that the graph had another use with the original author doesn’t mean it cannot be used in other ways. And in fact, that’s what Plait did.

  36. Pingback: Still Going Down the Up Escalator

  37. Pingback: Briggs schools the “Bad Astronomer” on statistics | TaJnB | TheAverageJoeNewsBlogg

  38. Pingback: Clima de idiocia. «

  39. I find it amusing that many of the comments haggle over what is, or is not, a ‘scientist’. One side staking out the Argument To Authority of a Ph.D. in a field defined as a science (by whom?) while the other stakes out the Argument to Ability of an Engineer (note, the capital letter, so you know my bias…) as granting a mantle of “science” (as though knowing math and needing to avoid error makes a scientist). Yet none are mentioning The Scientific Method.

    I would assert the Argument Of Definition: One who follows the Scientific Method is a scientist, no matter what their degree, or lack their of, and no matter what their math skill. (One can do science in some areas that do not require math… watch an apple fall and you might postulate the law of gravity, then find it universal, then later the math and formulas can be applied…)

    FWIW, my contribution to this particular bit of Angels and Pins is that by the “Must have Ph.D” definition, Newton would not be a scientist. Can we agree that Newton WAS a scientist? If so, then one need not have a Ph.D. to be a scientist…

    Isaac Newton was born in 1643 in Woolsthorpe, England. His father was a wealthy, uneducated farmer who died three months before Newton was born. Newton’s mother remarried and he was left in the care of his grandmother. He attended Free Grammar school. Though Newton did not excel in school, he did earn the opportunity to attend Trinity College Cambridge where he wanted to study law. His mother refused to pay for his education so while at college he worked as a servant to pay his way. Newton also kept a journal where he was able to express his ideas on various topics. He became interested in mathematics after buying a book at a fair and not understanding the math concepts it contained. Newton graduated with a bachelors degree in 1665. The further pursuit of an education was interrupted by the plague. Trinity College was closed due to the highly contagious, deadly disease. Newton went home. It was during this time that Newton started to pursue his own ideas on math, physics, optics and astronomy. By 1666 he had completed his early work on his three laws of motion. The university reopened and Newton took a fellowship in order to obtain his masters degree.

    As the years progressed, Newton completed his work on universal gravitation, diffraction of light, centrifugal force, centripetal force, inverse-square law, bodies in motion and the variations in tides due to gravity. His impressive body of work made him a leader in scientific research. However, in 1679 his work came to standstill after he suffered a nervous breakdown. Upon regaining his health Newton returned to the university. He became a leader against what he saw as an attack on the university by King James II. The king wanted only Roman Catholics to be in positions of power in government and academia. Newton spoke out against the king. When William of Orange drove James out of England, Newton was elected to Parliament. While in London he became more enchanted with the life of politics than the life of research.

    Note the presence of a Masters, not a Ph.D.

    But he was good at math… inventing calculus and all… and he created gadgets, like the Newton Thermometer, so ought we to call him an Engineer instead?

    As the two guys shouted at each other from their balconies on opposite sides of the ally, the elder Old Geezer exclaimed:

    “Sir, I fear we shall never agree, for we argue from different premises.”

    IMHO, a “Scientist” is any person who applies the scientific method. BY DEFINITION.

    And by virtue of that, and of how aircraft designs are made and tested (using the gathering of data, the formation of a hypothesis [ it will fly... with these behaviours] and the TESTING of that hypothesis [ rather more rigorously than in most fields ] and iteration if that test fails to confirm the hypothesis) there is no doubt what so ever that Burt Rutan is a scietist.

    That he is one who specializes in the Engineering and Design of aircraft doesn’t change that.

    I also not in passing that the indulgence in a prolonged ‘Angels and Pins’ argument has attracted far more attention that the point that averaging temperatures is simply unsupportable from a philosophy of science point of view.

    Why let a substantive point (that averaging intrinsic properties erases their meaning) interfere with counting angels and measuring pins….

    So, “carry on”….