My last two posts have been about the new Federal Reference Manual on Scientific Evidence, just out (December 31) from the Federal Justice Center. The Chair of that Center is U.S. Chief Justice John Roberts. The latest version of the Manual is the Fourth Edition. The prior version in 2011 was the Third Edition; and there were also two prior Editions from 2000 and 1994. The National Academies of Science were not involved in the First Edition, but got heavily involved by the Third Edition; and now with the Fourth Edition they seem to be the main source of material.
In those previous two posts, I principally criticized a newly-added chapter in the Fourth Edition titled “Reference Guide on Climate Science.” Today, I want to take a look at another chapter titled “How Science Works.” There was no such chapter in the First Edition, but a chapter by that title, written by a guy named David Goodstein (an Emeritus Professor at Caltech), was added in the Second Edition. In the Third Edition, Goodstein’s chapter was somewhat modified and slightly expanded (from 16 pages to 18). Goodstein died in 2024, and in the Fourth Edition he has been replaced by Michael Weisberg and Anastasia Thanukos, who have now produced a chapter with the same title, but now running to some 61 pages.
In my January 31 post, my comment on the Weisberg/Thanukos work product was that it was “not too terrible,” but that it was “way longer than it needs to be” and “the most important points are buried.” Further comparing this chapter to the chapter on (so-called) “climate science” (which is entirely hoakum) I continue the view that there are some good points here. However, there are also some serious flaws, and I don’t want to move on without pointing some of those out.
Let’s start with the identity of the lead author. Weisberg is said to be a Professor of Philosophy at the University of Pennsylvania. One part of that gives great pause, and it’s not that Weisberg is a Professor of Philosophy rather than of some field of science. I think that the nature of the scientific method and of the development of scientific knowledge is actually a bona fide part of philosophy, namely logic. So the part of Weisberg’s resume that gives me pause is instead that he works at the University of Pennsylvania. That is the institution that in 2022 hired the single biggest charlatan pseudoscientist in the entire country, namely Michael “Hockey Stick” Mann, and gave him a top University Professorship. Has Weisberg ever spoken out against Mann, or criticized him in any way? Not that I can find. So for starters, here we have a guy who is willing to look past and excuse the worst of the worst in the way of politicized pseudoscience.
As I said in the previous post, there are many things here to which I can subscribe, and I should start with those. As the most important example, the section on “Key Traits of Science,” beginning at page 60, basically has it right. Subsections include: “Science Investigates the Natural World and Natural Explanations”; “Science Investigates Testable Hypotheses”; and “Science Responds to Evidence.” So far, so good.
But in the process of generating a way-too-long 60+ pages, Weisberg veers badly off track from time to time. There are too many examples to cover them all in a short blog post, but here are a several of the more important:
Is Science a method of inquiry or a body of accepted knowledge (or both)?
Weisberg gets this one completely wrong. From page 50:
Science is both a body of knowledge and the process for building that knowledge based on evidence acquired through observation, experiment, and simulation. The term is accurately applied to knowledge on a wide variety of topics and to diverse lines of inquiry.
I completely disagree. The idea that Science can be a body of knowledge is where we get pronouncements from a priestly class that “The Science” has established such and so, and therefore we mere laymen and peons are not allowed to question it. That is the opposite of the scientific method. So science cannot be both the method that questions all allegedly accepted propositions, and also a body of accepted knowledge. Richard Feynmann’s definition of science is the one I subscribe to: “Science is the belief in the ignorance of experts.”
Confused treatment of the concept of falsification.
At the beginning of a subsection titled “Science Does Not Prove Hypotheses,” Weisberg states “No matter how much evidence supports or refutes it, a hypothesis cannot be absolutely proven true or false.” I agree that a hypothesis cannot absolutely be proven true, but how about false? After making that statement, Weisberg goes through a series of examples, all of which are instances of how a hypothesis can still turn out to be false even after much accumulation of corroborating evidence. Yes. But he gives no examples of the opposite circumstance, where a hypothesis could turn out to be true after falsified by definitive evidence. In discussing the subject, he confuses the logic of advancing knowledge through a process of falsification with a very separate concept, which is the practical difficulty of accumulating unambiguous evidence.
Sloppy statements about “accepted science” and “consensus.”
In the midst of otherwise sensible sub-sections and paragraphs, sloppy sentences repeatedly appear about things deemed to be “accepted science” and “consensus.” For example, from page 64:
Despite its tentative nature, accepted scientific knowledge is reliable.
Well, Michael, which “accepted” scientific knowledge is “reliable”? All of it? And, “accepted” by whom? By your friends? By my friends? By the orthodox climate clique? How can someone make such a statement after the “accepted science” Covid debacle of lock-downs and masking and “social distancing” that we have just been through, not to mention the endless and ongoing climate scam?
Weisberg continues:
Such [“accepted science”] explanations generate predictions that hold true in many different contexts and at many diff er ent scales, allowing us to figure out how entities in the natural world are likely to behave and how we can harness that understanding to solve problems and dispense justice.
Well, “accepted science” explanations do generate useful predictions in some circumstances, and in other circumstances they prove to be completely wrong. The only thing significant about real science (the method) is providing a method to distinguish between those two categories. Weisberg does not do that.
Correlation and causation
From page 92:
While the often-stated maxim that correlation does not imply causation is true, in fact, correlation is the only means that we have of establishing causation in science.
That’s just completely wrong. We absolutely have a way of “establishing causation” — or at least of progressively ruling out causes other than our hypothesized cause — which is by disproof of the null hypothesis. In the most common example with which almost everyone is familiar, pharmaceutical companies seeking approval of a drug are required to (at least tentatively) prove its efficacy by disproving the null hypothesis that a placebo is as good or better.
Weisberg follows the statement I quote above with a long example about how the causal relationship between smoking and lung cancer was established through a long series of studies proving correlation. Yes, in part. But those studies also disproved the null hypothesis that people or animals not exposed to inhaled tobacco smoke got lung cancer at the same rate.
Conclusion
So the operating hypothesis is that Professor Weisberg wrote this chapter in complete good faith to give the courts a neutral guide to science, and the flaws I have identified are just a few innocent mis-steps attributable to short deadlines or sloppiness. But then there’s the null hypothesis that what I say are flaws were actually very intentionally inserted to give support to the litigation efforts of the most politicized consensus “science” scams going on these days, starting with the climate alarm scam. I kind of think that we are close to having to reject the original operating hypothesis in favor of the null hypothesis.
I would propose that ‘How Science Works’ is best defined by those who do it, not by those who write about it. If someone does both (Feynman) that would be the one I’d probably most agree with.
If you are limiting yourself to the likes of Feynman, well and good. But having worked closely with a very great many PhDs for close to a decade (mainly in medical sciences) I can tell you there are very many credentialed idiots who know how to publish papers but know nothing about anything much, still less the subtleties of how science works. (I find the replication crisis unsurprising to point of inescapable.)
It is unfortunate that your point is as valid as it is. Could it be that ‘doing science’ and ‘publishing papers’ about it are as separate as ‘doing science’ and just ‘writing about it’?
A Gazillion Dittos! I have no PhD and little fundamental understanding of any science but spent many years as spokesman for top-of-the-food-chain organizations and individuals in medicine and aerospace and I have a pretty good idea how science “works”.
Data rule BUT data is subect to myriad influences. Funding. power, culture and ego spring to mind.
I have been final reviewing authority for thousands of papers, articles, presentations, statements and responses. Data was always verified but, regrettably ; The dog that didn’t bark was often conspicuous to the practiced observer.
Short version: Take it all with a grain of salt – “Why does this ‘expert’ WANT me to believe what is claimed?”.
Sins of omission dominate research. You can design a study to get the conclusions being paid for.
“Why does this ‘expert’ WANT me to believe what is claimed?”.
A key question in identifying bias! “Who benefits?” and following the money a fundamental requirement for understanding the “why”.
Feynman said it best. In your paper, you have to also list other things that could be the cause instead of your theory. Then you list which ones are disproven by measurement, theory, or ruled out as too unlikely. Then list the ones that could be the cause of the phenomena you seek to explain and why you could not test those to disprove them as well. I actually saw a case of this with a paper proposing a concentration of dark matter in our galaxy. The authors pointed out that a smallish black hole would have the same effect. they also pointed out that no x-ray emissions came from that area, strong evidence that it was not a black hole. However, they noted that the possible black hole may not be consuming matter at this time and so would not be producing x-rays. They could not rule it out and were honest enough to publish this.
I was intrigued by an obituary to a medical statistician that exposes the problem scientists and scientific journals refuse to admit, which is relevant to scientific studies and the whole climate discussion. I doubt those producing the manual were cognisant both of the production of papers and the peer review issues.
Douglas Altman, who has died aged 69 (2018), waged a long-running campaign to improve the use of statistics in medical research.
A professor of statistics in medicine at the University of Oxford, in 1998 Altman described the problem as follows:
“The majority of statistical analyses are performed by people with an inadequate understanding of statistical methods.
They are then peer reviewed by people who are generally no more knowledgeable.
Sadly, much research may benefit researchers rather more than patients, especially when it is carried out primarily as a ridiculous career necessity.” (my emphasis)
I believe that in some cases, as with glyphosate litigation, the advocates of harm
are sufficiently dishonest to be prosecuted under RICO.
Michael Mann’s hockey stick study (MBH98) is about as discredited as any soft science study can be, and Mann should retract it. But it is useful for advocates who only want talking points, not an attempt at describing reality.
The hockey stick is Mann’s only claim to fame. He has done nothing else of note, either before or after. If he were to retract it, he would completely vanish politically. That is something his ego can’t handle.
Actually, Michael Mann has done a lot ‘of note’, all of it vile.
Is that similar to your ego’s inability to admit that you have no clue what the Second Law of Thermodynamics tells us, Professor? Would you “vanish”, as well, if you retracted your false claim that the Second Law somehow doesn’t apply to electromagnetic radiation?
We’re still waiting for your erudite lesson on “pages of dense math” that constitutes the “real” Second Law. Or were you just bluffing? Like some sort of hypocrite?
I know more about the glyphosate litigation than I’m at liberty to say, even semi-anonymously. All I can say is that you’re right.
Now you have to shoot us?
While the often-stated maxim that correlation does not imply causation is true, in fact, correlation is the only means that we have of establishing causation in science.
I think this way of thinking allows for the way the BBC etc frames its science resources for schools and pupils, and its broadcasts to the general public.
“…what’s the evidence for global warming and how do we know it’s being caused by humans?
…
Only when human factors are introduced can the models explain increases in temperature.
…
For many years, groups of so-called climate “sceptics” have cast doubt on the scientific basis of global warming.
However, virtually all scientists who publish regularly in peer-reviewed journals now agree on the current causes of climate change.
A key UN report released in 2021 said it “is unequivocal that human influence has warmed the atmosphere, oceans and land”. Auntie
However, due to human actions, carbon dioxide levels today are rising 100 times faster than any of these natural increases. There is now more carbon dioxide in our atmosphere than there has been in over 3 million years.
…
All of the extra heat energy trapped in our atmosphere, as the result of greenhouse gases from human activity, is causing major changes to our climate and producing more extreme weather. Areas of the world that were already hot are getting even hotter and drier, increasing the chances of heatwaves, droughts and forest fires. BBC Bitesize
In this paradigm no mention is made of the fact that CO2 bottomed out ~3 million years ago to dangerous levels. Models are also treated as bona fide evidence.
Scientists created two climate models using data on carbon dioxide level increases:
due to natural sources onlydue to both human activity and natural sourcesThe second model better matched the observed temperature changes.
This adds to the evidence that the observed warming of the Earth is because of human activities changing the composition of the atmosphere. – BBC Bitesize
The rot runs deep.
As I like to say, correlation is not causation, but it is often a good place to start looking.
More CO2 than any time in the last 3 million years.
1) That means there was more CO2 in the air a mere 3 million years ago. And life didn’t come to a grinding halt. Hmmm.
2) 3 million years ago, isn’t that right around the start of the current ice age?
They say the Quaternary started ~2.58 million years ago
I’d like to add: Correlation is certainly NOT causation when the supposed “cause” us PRECEEDED BY the supposed “effect.”
…
Argument based on ignorance. “We can’t explain it without our pet hypothesis” is not a damning statement, but an unspoken indication of how little they know about the Earth’s climate.”The models” ASSUME their pet hypothesis to be carved-in-stone fact as opposed to a hypothesis, and further assume it operates WITHOUT its implicit, necessary, and FOUNDATIONAL assumption, “all other things held equal,” being true.
Trapped?! LMAO. somebody needs to point out to the British Bullshit Commies that the “radiation” leaving the Earth’s atmosphere has INCREASED as the climate has warmed, exactly the OPPOSITE of their fact-free assertions.
Apparently they don’t read their IPCC darlings’ “Assessment Reports.” Even they can’t hide the FACT that the weather is OBJECTIVELY NOT getting worse.
Apparently the BBC is also immune to the fact that the Earth (including THE SAHARA) is greening, not “getting drier.” Oh and an increase in THE AVERAGE temperature is not “getting hotter.” Most of the increase in the average is due to nighttime lows not getting as cold.
No. Next stupid question, please.
Wow. What Francis describes is not just badly expressed views. It is jaw-droppingly wrong. A “professor” wrote that? I can’t imagine statements like that getting a passing mark in an undergraduate essay.
Philosopher. He was probably dwelling on what ‘correlation‘ means as a process – you drop an apple 100 times, it lands in the grass 100 times, thats 100% correlation. Isaac Newton’s famous ‘discovery’ was based on correlation. Reminds me of a former president in court saying it depends what you mean ‘is’ is. If an opponent gets suckered into arguing definition that way, then they lose. All it costs the person employing that technique is their sense of honor and dignity.
With William Jeffer…er, the former president, it didn’t cost him his sense of honor and dignity because he never had any in the first place.
I hink the correct statement is not that one disproves the null hypothesis (the hypothesis that there is no relationship between the variables), one rejects it. Et c’est tout.
Good point. “Reject” is indeed a more appropriate word.
Genuine question: what is the difference between disproving and rejecting? I will admit to being at ease with saying it is disproven, but I am probably treating the term “disprove” as a mere turn of phrase in this context. Can you illustrate the difference?
Theory A rejects the null hypothesis, but is incorrect. Theory B better describes the phenomena but is still incomplete/incorrect. Think:
Angels and grappling hooks –> Newtons laws of motion –> Einstein’s Relativity.
I don’t contest your point. But it doesn’t address my question: what is the difference between disproving the null hypothesis and rejecting the null hypothesis? Why is it wrong (or misleading or weak, or whatever the problem is) to speak of having “disproved” the null hypothesis?
(I repeat, this is a sincere question.)
Here is a long answer from Grok, for what it’s worth.
My prompt: “At the conclusion of a controlled experiment, which is the best word to use when the dependent variable shows a response to the independent variable? That the null hypothesis has been 1) Disproven, 2) Rejected, or 3) Falsified?”
Grok’s response:
“The best word to use is 2) Rejected.
In the context of a controlled experiment and standard statistical hypothesis testing, when the dependent variable shows a clear response to the independent variable (and assuming the result is statistically significant, i.e., the p-value is below the pre-specified significance level like 0.05), we say that the null hypothesis has been rejected.
Why “rejected” is the correct and standard term:
Why not the other options?
Quick summary of standard phrasing
So for your controlled experiment scenario, go with 2) Rejected—that’s the most accurate and conventionally correct choice.”
Thank you. I just remembered the phrasing from my grad course on statistics in the social sciences that I took during the administration of Richard M. Nixon.
Ok, yes, I will buy this. “Reject” is potentially a better way to express the idea. However we’re probably veering into the psychological rather than the objective by preferring the word “reject”. When I “reject” a null hypothesis I am (or should be) reminding myself that 19 times out of 20 (or whatever) it would have been inconsistent with observation. When I say I “disproved” it I am tricking myself into thinking I’ve driven a stake through its heart. But I think that is a connotation of the words that is not necessarily evident. Proof of which is I (A) had to ask the question and (B) it took a couple of attempts to get a good explanation.
I think in future I will say, “the null hypothesis is rejected—this time”.
Thanks David. (And your helper.)
A simpler answer:
If you reject a thing you understand it might be correct, but the odds seems so far.
If you disprove a thing you believe it to be false.
(Here we are debating fine distinctions of the definitions of words. THis is why the philosophy professor produced such terrible work.)
Can I tighten this up further?
If you say you reject a thing you think it is probably incorrect,
If you say you have disproved a thing you know it is false.
(Related word-play: the difference between rebut and refute.)
It becomes addictive – the nitpicking takes over and the basic argument gets lost. A fair test of mental sharpness for a philosophy professor might be “how many clarifications of word meanings can you answer before you forget the original proposition?”
How climate alarmism works
Gabriella Ditton, 32, and Nicola Stickells, 55, are each accused of two counts of criminal damage after pink paint was thrown over council buildings in Norwich. Both defendants admit carrying out the protest but claim they had a “lawful excuse” for their actions as they were raising awareness about climate change.
Ditton was asked while giving evidence whether she thought it was hypocritical to use the diesel-powered vehicle to carry out the demonstrations […] The 32 year-old, who works as an illustrator and animator, said this was not the case, instead insisting her actions were “overshadowed by the enormity of the climate crisis”. She told the jury that lowering her carbon footprint did not really matter as what is needed is a “system of change”. – Daily Sceptic
Never mind science, just tell any alarmist that your Carbon footprint does not really matter. Because it doesn’t.
Francis Menton is doing a fine job with this series of posts.
“We absolutely have a way of “establishing causation” — or at least of progressively ruling out causes other than our hypothesized cause — which is by disproof of the null hypothesis. In the most common example with which almost everyone is familiar, pharmaceutical companies seeking approval of a drug are required to (at least tentatively) prove its efficacy by disproving the null hypothesis that a placebo is as good or better.”
Yours truly is a mechanical engineer by training. Most of my career in industry – over 28 years in capital project management and facilities engineering – was in support of pharmaceutical development and production. This concept of disproving [edit: “rejecting” would be a better word] the null hypothesis of “no effect” was at the heart of the series of clinical studies that were required to gain approval of a new drug. Controlled experiments.
The valid “no effect” null hypothesis for investigation of the efficacy of incremental CO2 to warm the planet can be stated this way: Rising concentration of CO2 does not suppress the overall longwave emission to space, properly integrated over time and location. Another version could be: Rising concentration of CO2 is not capable of operating as a climate forcing.
Has a controlled experiment been properly performed to rule out the null hypothesis? No. Any claim that “climate” models have served this purpose is bogus. Why? Because of the circular nature of the exercise, in which the conclusion is assumed at the outset in the coding and tuning of the simulations, to generate the “forcing” scenarios based on past and future emissions. This should be obvious to all, especially to those familiar with controlled experiments for establishing a sufficient basis for a regulatory approval.
Also, any claim that the measurements necessary to falsify the null hypothesis can be performed with sufficient accuracy and precision for proper analysis, is also bogus.
Thank you for your attention to this matter.
Another good post! I prefer ” Rising concentration of CO2 is not capable of operating as a climate forcing.” as a Null Hypothesis. Minuscule changes in average thermometer readings over decades are unrelated to significant descriptors of “climate”.
Following Climate Science will turn up more reasons not to trust science.
From my file:
I’d accept Climate Science:
If climate science wasn’t pushed as an absolute in schools.
If the predictions from climate science seemed to be true.
If climate science didn’t confuse accuracy and precision.
If climate scientists didn’t rig the peer review process.
If climate scientists didn’t sabotage scientific careers.
If climate scientists didn’t hide their historical data.
If climate scientists didn’t appear to cherry pick data.
If IPCC reports weren’t re-written after final approval.
If climate scientists didn’t try to sue the opposition.
If climate scientists didn’t appear to fudge the data.
If climate scientists didn’t resort to name-calling.
If climate scientists complied with FOI requests.
If climate scientists agreed to debate the issue.
If climate scientists didn’t exaggerate findings.
If Grant programs weren’t rigged.
And yet we must believe something to make it worth going through a day. Francis Bacon wrote some great words about it a long time ago.
I agree with you fully if you replace “climate scientists” with “Climate Scientists”.
I did some research on obtaining a BS in philosophy. I examined both Idaho and Stanford Univ. From what I could find,
How does one obtain a “science” degree without training and experience with actual physical science. It sounds very much like an “elite” training course in telling folks what they should be doing!
Am I the only one flabbergasted at this statement? “correlation is the only means that we have of establishing causation“. This is the antithesis of science. It absolves one when using “the end justifies the means”.
Whatever happened to a hypothesis that has a functional physical relationship between variables that could be experimentally validated? This sounds more like a social justice warrior attempting to excuse murder to increase diversity!
Why do you presume that a person enrolled for a BS degree in philosophy, especially at scientifically-renowned Stanford University, would not have taken a “high level math class”?
Do you understand the difference between required and elective classes in working toward a Bachelor of Science degree?
And there is this from Google’s AI bot:
“Yes, Stanford University offers a extensive range of advanced mathematics classes for undergraduate, graduate, and pre-collegiate students. The Department of Mathematics provides courses in specialized topics such as Analytic Number Theory (MATH 155), Abstract Algebra (MATH 120, 121), and Topology (MATH 144, 147).
Key Offerings in Advanced Mathematics:
University-Level Online Math & Physics: Stanford Pre-Collegiate Studies offers advanced courses for high schoolers, including Multivariable Calculus and Linear Algebra, allowing them to earn college credit.
Undergraduate & Graduate Courses: The math department offers advanced coursework in areas like applied matrix theory (MATH 104), as well as research-based courses for students to explore original mathematics (MATH 197).
Specialized Programs: The Stanford University Mathematics Camp (SUMaC) is an elite residential program covering topics like Number Theory and Topology.
Additionally, Stanford features an accelerated introductory series (MATH 51, 52, 53 or 61, 62, 63) suitable for students with strong backgrounds.”
Actually I do understand what a degree program is. I have a BSEE. I graduated with 162 hours, minors in math and political science.
When I examined the philosophy programs not one, I reiterate, not one showed a requirement of a physical lab or math class for a “science” degree.
All your response shows is that a university offers advanced classes. Big deal.
You fail to show that a BS in philosophy requires any of them for graduation.
Do you know how many Philosophy graduates post scientific analysis here on WUWT? How many Drs. of Philosophy issue scientific papers on climate change?
Now, I may have misinterpreted what degree the author was describing. A PhD in science is not a Doctor of Philosophy. Here is what the author described – “a Professor of Philosophy”. That is normally a PhD in the discipline of Philosophy .
Here is a thought. Rather than throwing out a red herring, maybe you could show us some university degree plans that have advanced math or lab courses as prerequisites for philosophy classes. I couldn’t find any, maybe you can.
Problem is that a PhD (Doctor of Philosophy) can be given in any area…
eg I have PhD in Civil Engineering.
I have no idea what a “Professor of Philosophy” might be,
.. but it sounds more like it might come from a “Humanities” background, rather than a “STEM” background.
And you, again, fail to admit that a student enrolled for a BS degree, or even for a PhD degree, at almost any major university in the US is free to take a “high level math class” as an elective course.
While not necessary, correlation is sometimes used to identify interesting issues. Many interesting issues are identified just by seeing.
500 B.C. Thales, a Greek philosopher observed that amber, a fossilized type of tree sap attracted bits of paper and certain materials, like straw, when rubbed. This is the first mention of static electricity.
551 A.D. Jerome Cardan, an Italian mathematician, determines that while amber attracts light objects, a magnetic black stone attracts only iron. This is the first in a series of discoveries that link electricity to magnetism.
One of the greatest English scientists was Michael Faraday who understood scientific method. Those who claim to be following science when it comes to seeking to understand climate totally ignore his method despite this having been followed by leading scientists up to our day. One of these was the Japanese scientist, Akira Yoshino. He was as a child inspired by Faraday. He went on to create the first safe, production-viable lithium-ion battery and was awarded a Chemistry Nobel Prize in 2019.
Clealy climate alarmists are ignorant both of science and history.
Plenty of very smart people in history and today, people capable of replicating work in electromagnetics or chemistry, have no interest in it. There is a Newton-class mathematician out there somewhere doom scrolling Instagram or fetching a pail of drinking water from a mud puddle who will never hear the word ‘integral’ and will not miss it.
Sometimes its more fun to throw tomato soup at boring old paintings and yell “the end is nigh”. Even if dad’s job managing the coal mine paid for their history degree.
I’ll first answer the above article’s headline question with this question:
“Would you trust any organization who has Michael Mann as a member currently in good standing, such as the NAS that elected him to be a member in 2020 based on—get this!— his “distinguished contributions to climate science, including his research on climate change?”
But the obvious and simpler answer is: “NO, hell not.”
An excellent point. We should note that Michael Mann demonstrated his character in his testimony during the Mark Steyn trial, earning the admonishment of the judge for presenting misleading and even false information regarding the amount of his ‘lost grants and contracts’. The NAS bestowed upon such character the ”highest honour a scientist can receive’ by electing him to an NAS position.
The NAS does not look well by this act, and has not demonstrated the morality or discipline expected for it to be lecturing anyone on how science is done. It is unfortunately probably true that the NAS has destroyed science, not advanced it.
‘In my opinion’.
CO2-phobia has corrupted all our science institutions.
There is still no proof of causation in the smoking/lung cancer debate. Yes, the association is extremely strong after age 70 . Most people also conflate lung cancer with all other cancers.
It seems few people have actually read the English doctors study.
Nowhere in any commonly-accepted definition of The Scientific Method does one find reference to “proof”. Instead, science—like the legal process—seeks to assemble a preponderance of evidence, beyond reasonable doubt, that a presented hypothesis is or is not “true” (aka “factual”).
Yes, proof is for math (deductive logic). Science is about evidence (inductive logic). However in complex cases the weight of evidence is relative to the observer (Wojick’s 2nd law) so reasonable people can look at the same body of evidence and draw opposite conclusions. Hence hung juries, etc.
Climate scientists do not require anything more than a balance of [their] probabilities.
They hush up the uncertainties wherever possible.
Physical science is not based on the preponderance of the evidence. That is a statistician’s viewpoint. You don’t have a physical science degree do you?
Science is based on the truth not being positively falsified.
See that word EXPERIMENT. That is a reference to validating a physical functional relationship proposed in an hypothesis. Why do you think the Hadron supercollider was built? To conduct EXPERIMENTS to validate the theoretical conjectures predicted by the functional relationships created by theoretical physicists.
As I have written elsewhere…
“I agree that experiments are the ultimate test of a theory or hypothesis, and people often back this up by quoting Richard Feynman on the subject: “It doesn’t matter how beautiful your theory is, it doesn’t matter how smart you are. If it doesn’t agree with experiment, it’s wrong.”
It’s hard to argue with Feynman, but he must have known, and would have acknowledged if pressed, that it is often very difficult to organize an experiment that doesn’t depend on auxillary assumptions or beliefs. Sometimes the misapplication, or even the correctness, of these auxillary hypotheses influence the outcome of an experiment. Sometimes a person has to apply “corrections” to experimental data; these can mislead. Sometimes people simply make numerical errors. Sometimes they cheat.
“It’s hard to argue with Feynman, but he must have known, and would have acknowledged if pressed, that it is often very difficult to organize an experiment that doesn’t depend on auxillary assumptions or beliefs.”
A while back I found the following link to a transcript of the entire video from which the famous clip ending with your quote was extracted and posted to YouTube.
URL : https://jamesclear.com/great-speeches/seeking-new-laws-by-richard-feynman
From that link, with some highlighting added :
For Richard Feynman it did not matter which “auxiliary assumptions or beliefs” were in the experiment designers heads before constructing it.
Those “assumptions or beliefs” can never rise to the status of “Scientific Fact” or “Settled Science”.
No scientific experiment can ever “prove” that “what you thought was right” is actually right.
When using The Scientific Method (TSM) you have to accept the notion that participants “can only be sure we’re wrong“, that “tomorrow’s experiment may succeed in proving what you thought was right, wrong“.
As human beings we all seek “certainty” in life, and many people — especially politicians — have great difficulty in accepting “We do not know (yet)” for an answer.
.
When it comes to “assumptions or beliefs” Richard Feynman summarised the difference between TSM and the current main alternative for human beings as follows :
“Religion is a culture of faith; science is a culture of doubt.“
Just excellent comment!
Were Richard Feynman alive to advise us now, I’m sure he would admit to “shorthanding” his comment “If it doesn’t agree with experiment, it’s wrong.”
The simple fact is that many experiments, especially early ones intended to test a hypothesis, turn out to be wrong or fradulent. See https://en.wikipedia.org/wiki/List_of_experimental_errors_and_frauds_in_physics
I think that, given the wisdom and logic of Feynman, he really meant to say:
“If it doesn’t agree with the preponderance of results from multiple, independently-conducted, reproducible experiments, it’s wrong.”
I’d add “or real-world observations,” since “experiments” are not always possible.
“Climate Science” as currently “practiced” is a culture of unquestionable certainty.
Which tells us, without any room for doubt, that it is not “science” at all.
I tried to summarize what you and Mark BLR says later into this statement. You can’t prove something is correct, but you can prove it is wrong.
The “truth” occurs because it isn’t proven wrong. It can’t be the truth if one can find a contrafactual occurrence. It is why a physical science hypothesis must entertain a mathematical functional relationship that can be tested for its accuracy.
Earth experienced glaciation with 10 times today’s atmospheric CO2 levels. Which falsifies the notion that atmospheric CO2 levels “drive” the Earth’s climate.
As do the multitude of episodes of REVERSE CORRELATION between temperature and atmospheric CO2 levels in the ice core reconstructions.
As does the fact that (as seen in the ice core reconstructions) temperatures consistently begin RISING when atmospheric CO2 is (a) FALLING and (b) near its LOW point, and consistently begin FALLING when atmospheric CO2 is (a) RISING and (b) near its HIGH point.
Plus, sometimes the only valid experiments require thousands of years to execute or need huge numbers of test samples when only one sample exists.
AKA the price becomes too high. Anyone can learn whether there’s really an afterlife. Once. Then they can’t publish the result.
That’s where observations of reality come in, but there are of course difficulties with availability, quality and level(s) of precision of data about the real world.
The problem being that models which are literally crap are being passed off as if they replicate reality when they most certainly do not.
“What is truth?”
— Pontius Pilate as quoted in the Bible, John 18:38
You might stay on topic. Neither Pilate nor Jesus were discussing science!
But they WERE discussing “truth”.
But perhaps you forgot that this statement (with my bold emphasis) was made by you:
“Science is based on the truth not being positively falsified.”
ROTFL.
You forgot one little piece that is very important in science.
“not being positively falsified.”
Read the Bible verse again. Was anything falsified?
Einstein supposedly asked why it took 100 scientists to declare his theory wrong when it only took one to falsify his work.
Lastly, the discussion is physical science, not theology or faith . Stay on topic!
The phrase that you quote
“Science is based on the truth not being positively falsified.”
is attributed to Karl Popper’s ruminations on the philosophy of science and his developed concept of Falsifiability. It is not found in any commonly-accepted definition of The Scientific Method simply because the Method doesn’t involve the word “truth”, only words such as “results”, “data”, “findings” or “observations”.
Some of the criticisms scientists have levied against the concept of Falsifiability are:
— Duhem-Quine Thesis (Under-determination): It is rarely, if ever, possible to test a single hypothesis in isolation. Experiments usually test a whole network of theories and assumptions. If an experiment fails, any part of that network could be wrong, meaning a single, definitive falsification is logically impossible.
— Problems with “Probabilistic” Science: Many valid scientific theories are probabilistic (e.g., quantum mechanics), making them impossible to definitively falsify with one “no” result, as Popper demanded.
—Self-Refutation: Arguments exist that the principle of falsifiability itself is not falsifiable, making it a philosophical, not scientific, statement according to its own criteria.
These and other criticisms suggest that while Popper’s concept of Falsifiability is one view on how to test theories, it is an inaccurate description of how science actually progresses.
Moreover, I’ve seen many references to the phrase that “It’s impossible to prove a negative.”
Some examples, in the realm of physical science:
— it’s impossible to prove that there isn’t any life in the universe other than on Earth (and in its nearby space)
— it’s impossible to prove that dark energy and dark matter don’t exist
— it’s impossible to prove that some forms of matter or energy cannot travel faster that the speed of light (ref: theoretical tachyons)
— it’s impossible to prove that an asteroid won’t collide with Earth in the next 10 million years
— it’s impossible to prove that the universe won’t expand forever
— it’s impossible to prove that the universe won’t contract into a black hole in the future.
I, and many other scientists, hold that there are “truths” that currently exist independently of mankind even knowing them, let alone being able to experimentally confirm or “positively falsify” (your words) them . . . this falls under the term “scientific discoveries”.
Lastly—help me out here—should I, or anyone else, have faith in science? /sarc (and I do believe this is “on topic”.)
Or, where experiments are not possible, by OBSERVATIONS OF REALITY.
Hint: “Models” ARE NOT “observations,” ARE NOT “reality,” and ARE NOT “experiments.”
Deception primarily happens through sins of omission. Ignoring data that doesn’t support your hypothesis is standard practice today. Falsification is not even attempted because your study won’t see the light of day and you won’t get any future grants if the right conclusions are not reached.
Pharmacological studies are a bad example. 70% can’t be reproduced. Manipulating who’s included in the groups is how they get the desired results.
That or re-running the trials until the “desired” results are achieved and then shit-canning the others.
An example of Richard Feynmann’s definition of science as posted by Francis Menton: “Science is the belief in the ignorance of experts.”, is that of Barry Marshall and Robin Warren, two Australian physicians, who discovered that the bacterium Helicobacter pylori (H. pylori) is a major cause of peptic ulcers. <– As I recall at the time all medical science and other scientists (The Consensus) poo-pooed the correct Marshall and Warren findings. This is a perfect example, I believe, of when/how the consensus position, the so-called “accepted science”, is perfectly wrong, thus Richard Feynmann’s sage above comment, and helping make Francis Menton’s article point: “The idea that Science can be a body of knowledge is where we get pronouncements from a priestly class that ‘The Science’ has established such and so, and therefore we mere laymen and peons are not allowed to question it.“
Related observations.
Saying that ‘climate science’ is science doesn’t make it so.
And juries aren’t bound by ‘scientific’ evidence, as the glyphosate, talcum powder, and silicone breast implant cases plainly demonstrate. So this fourth edition is in the end a fruitless endeavor.
As for expanding from 18 to 61 pages, an apology should be in order—‘I didn’t have the time to make it short.’
Hhmm.
From my scientific layman point of view, I think that any hypothesis or theory should remain as a “work in progress” for as long as it takes for a representative ‘jury’ of ordinary citizens to understand and accept or reject the assertions being made.
Such ‘jury’ proceedings could be repeated as many times as the proponents call for them, but at no stage should the “work in progress” hypotheses be relied upon as the basis for public policy settings or taxpayer expenditures.
Proponents can apply their own money to any propositions they desire, and good luck to them, but scarce taxpayer funds must only be directed at “net societal benefit” developments.
I think that the nature of the scientific method and of the development of scientific knowledge is actually a bona fide part of philosophy, namely logic.”
Science is not philosophy. Science is not a branch of logic. Rather, logic is a tool of science.
Science is knowledge for its own sake. Predictive hypothesis and empirical test is the scientific method.
And that’s the whole ball of wax.
Very well said.
You have summarized my thoughts precisely.
I’ve been reading the new Federal Reference Manual on Scientific Evidence when these articles first appeared. I have a lot of heartburn with it, it is very much politically slanted for AGW and vaccine use. Most of my issues are with the terms test and experiment, which are not the same, and there is a weak and flexible definition of what a model is. The first thing the authors should have done is create their taxonomy and ontology. I don’t know how ‘experts’ can have a guide on anything without defining the language and vocabulary they are using. This is, after all, a book for lawyers, people who use precise words.
The Reference Guide to Engineering section clarifies a lot of the misconceptions about science. “Engineering begins with a goal and proceeds to the design and creation or manufacture of an object or a process to achieve the goal, while science begins with a question and strives to find an answer.” This is a significant distinction in the military where test organizations are not allowed by law to perform experiments. Science is sourced to FFRDC organizations like Aerospace and Miter under specific science contracts and conducted at Federal or DoD Laboratories. For the most part Scientists experiment and Engineers test.
I’d always thought a philosophy degree would mean you had learned to reason.
I stand corrected.
“So science cannot be both the method that questions all allegedly accepted propositions, and also a body of accepted knowledge. “
Mr. Menton seems unable to understand that words can have multiple meanings. The word “science” is both a noun and a verb which is explained by Prof. Weisburg quite well. The English language is very flexible and the same word can mean multiple things depending on the context. And if you are a judge in a trial you need to understand what people might mean which requires knowing all possible meanings of a word.
So is there a sentence where the word “science” can be used as verb?
Say something like –
“oh baby, oh baby – science me all night long!”
So, he scienced her like she’s never been scienced before.
(Just like the Net Zero policies science economies).
I think the intention was to convey that science is both a process and an outcome. I think.
Science assuredly is NOT an outcome.
Science is a framework for reasoning with provisionally held conjectures. Some conjectures endure longer than others. Some may turn out to endure forever. But science doesn’t care which—or if—any do.
The word “science” means both the outcome and the process in everyday English. The Oxford English Dictionary has 17 different meanings for “science”. For example
“The kind of organized knowledge or intellectual activity of which the various branches of learning are examples. In early use, with reference to sense 3a: what is taught in universities or may be learned by study. In later use: scientific disciplines considered collectively, as distinguished from other departments of learning; scientific doctrine or investigation; the collective understanding of scientists.”
The collective understanding of scientists is definitely an outcome and not a framework for reasoning.
Words have multiple different meanings in English that change constantly in time. Which is why the OED is descriptive and not prescriptive.
This site and the head post are not examinations of dictionary definitions.
The head post is about an examination of the definition of science. And if you want to provide advice to a judge about the meaning of a word then it has to include all common meanings since that way the judge is less likely to be confused. If you only told the judge about meaning A while experts in the case used meaning B then the judge could make a mistake. So a discussion about all meanings of “science” is needed.
Do you think an eminently qualified scientist wrote this or did some other “expert” in another totally unrelated discipline write this?
I wouldn’t trust any outfit out of hand. Organizations with scientific sounding titles are no different. My first question is how much is this organization influenced by politics? In the past I assumed everyone could trust outfits like AMA, CDC, NIH and so on. Today we know that isn’t true.
I trust them as much as I trusted the IRS, FBI, and DOJ under Clinton, Obama, Biden. Get it?
Francis Menton objects to the idea that science is or can be a body of knowledge, saying it can’t be both […] and accepted knowledge. So the word ‘accepted’ has crept in. My view is that the meaning of the word ‘science’ is in essence just knowledge, or at least a kind of knowledge. That knowledge is acquired via the scientific method (a specific method for acquiring knowledge). So science does provide us with a body of knowledge, it’s just that ‘knowledge’ and ‘facts’ are not the same thing, and we have to know how to see and use (scientific) knowledge. We have to know how to see and use facts too, for that matter. At this point, the “laws of science” become interesting, because these are scientific theories that have been so extensively and successfully tested that they are identified ss the closest things to facts that you can get via the scientific method. But even a law of science can be refined, even if not overturned. So there is only one item of knowledge that is absolute knowledge, the rest is just knowledge.
What is that one item of absolute knowledge? It’s personal: I think therefore I am. It’s arguable that nothing else can be absolute knowledge.
To me, science has nothing to do with knowledge per se. Physical science is ultimately the study of cause and effect. Note, “social science” is a different animal entirely. The “knowledge” part of physical science is the knowing of how cause and effect is related. The “knowing” doesn’t have to be definite, it can be probabilistic as in quantum physics, but it must have associated mathematics that the define the relationship between cause and effect.
Problem with many of these groups is that the upper echelon, the “bureaucrats” and spokespersons…
… tend nowadays to all be rapid leftists and activists.. ie. the scum floats to the top
… other members may never get a say in what is released or published.
As someone said.. anyone that give Mickey Mann an award for “science”… is totally untrustworthy.
I wonder who the “others” are who should have a say in what message leaders and their spokespersons provide. Perhaps have a referendum so all hands (The People) make the decision? Isn’t that the communist/socialist way?
Like it or not, perception trumps reality far too often. Most who visit “ wattsupwiththat “ are aware of this. We could use some competent “scum” of our own to get the facts in front of more people. I know; that’s hard when the air-heads and advocates in the media have been bought and paid for.