Re: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book,
Maybe this is an oversimplification, and I readily admit to being in a fog about the long list of "conceptual advances" (however useful--in their fashion), but isn't the point of all of them to strain, without mercy, the biases out of hypotheses and let the light of reality shine through, no matter what the result? WT At 10:16 AM 2/21/2008, Gary Grossman wrote: It would be interesting to have this discussion after reading Don Strong's 1980 seminal paper "Null Hypotheses in Ecology" Synthese 43:271-285 . Although I use AIC in my own research (see Grossman et al. 2006 Ecol Monog.76:217), IMO Anderson, Johnson and others have thrown out the baby with the bath water when they state that null hypotheses are trivial in ecology. In fact, the whole neutral model approach in ecology really is based on null hypotheses, and it has been one of the most productive areas in ecology since the 80's (see the great book by Gotelli and Green, Null Models in Ecology). Prior to those conceptual advances we had "models" ( i.e. the competitionist model) and many investigators worked hard to twist their data to fit the "model" (really it could be argued that the development of neutral models were a paradigm shift in the Kuhnian sense). Frankly, frequentist, information-theoretic, and Bayesian approaches all have their place in ecology and we should just get over, trashing frequentist approaches. To twist a phrase "Statistics don't misuse data, People misuse data" . Frankly, to suggest that information-theoretic approaches are less arbitrary because they don't use cut-off values is inappropriate, because cut off values are used for the interpretation of wi values and DeltaAIC values. Nonetheless, weight of evidence approaches are fantastic tools for ecology, but they are not the end-all and be-all for our field. There have been several back and forth exchanges in the literature over the last 5-6 years regarding these points so I won't belabor them here. cheers, -- Gary D. Grossman Distinguished Research Professor - Animal Ecology Warnell School of Forestry & Natural Resources University of Georgia Athens, GA, USA 30602 http://www.arches.uga.edu/~grossman Board of Editors - Animal Biodiversity and Conservation Editorial Board - Freshwater Biology Editorial Board - Ecology Freshwater Fish
Re: [ECOLOG-L] Anderson's new book,
Jeff Houlahan writes: > That said, science is many things - 'a predictive > enterprise, not some form of mindless after-the-fact exercise in number > crunching.' - fits under the umbrella but I don't think captures the whole > enterprise. Sequencing the human genome was, in my opinion, a version of > mindless number crunching (although perhaps somebody can put that effort in a > hypothesis testing context that I haven't thought of). I think most people > would be hard pressed to say it wasn't science. In fact, there is an > emerging field of statistics (data mining) that seems to be useful in > developing scientific hypotheses and is all about the 'mindless after-the- > fact exercise in number crunching'. My feeling is that data can provide > hypotheses or test them. When it does the first, it is a very useful part of > science but it is not predictive and it does not test hypotheses (null, > competing or otherwise). When it does the latter it falls ito the category > that Feynman was describing. > I think the reason we often get these trivial tests of hypotheses is because > there is this sense that science is only about testing hypotheses - therefore > to do science I must test a hypothesis...whether there is a meaningful one or > not. In my opinion, science can also just be about looking for patterns that > we can use to suggest hypotheses. These kinds of discussions can quickly become pretentious, but I don't want this one to become so. There is a deep joy associated with doing science, and you're right of course, science isn't purely about prediction. It also has an exploratory component to it as well, where you go over the mountain just to see what you can see. Nonetheless, prediction is still our only measure of how well we understand the world around us, and no one has ever said that making these predictions was supposed to be easy. If it were, none of us would be getting the large salaries we're being paid. Nonetheless, your last sentence strikes a deep resonant chord with me. No one agrees more than I do that to do science we must seek out patterns. Robert H. MacArthur's first line in his 1972 book, "Geographical Ecology," is: "To do science is to search for repeated patterns, not simply to accumulate facts, and to do the science of geographical ecology is to search for patterns of plant and animal life that can be put on a map." But seeking out these patterns is only the beginning. The Latin word "scientia" is generally translated as "knowledge," but I much prefer to translate it as "understanding," it's alternate meaning, and there is a difference between the two. Understanding is by far the higher state of grace. There is only one science, regardless of what subdiscipline you engage in, and your statement that perceived patterns in the data can be used to suggest hypotheses has been said a hundred times before. It was certainly said most clearly by the astronomer Alan Sandage in the first few paragraphs of his 1975 book, "Galaxies and the Universe." Indeed, he precisely recapitulates your last sentence in his first paragraph: "The first step in the development of most sciences is a classification of the objects under study. Its purpose is to look for patterns from which hypotheses that connect things and events can be formulated by a method proposed and used by Bacon (1620). If the classification is useful, the hypotheses lead to predictions which, if verified, help to form the theoretical foundations of a subject." But he goes on to quite rightly say that doing just this is insufficient to doing science. In the end, we want to understand causation and mechanism. We want to understand the rules -- the physics -- that governs the system under study. We haven't done our job until we do achieve this understanding. Sandage continues: "Simple description, although not sufficient as a final system, is often an important first step... But as a classification develops, a next step is often to group the objects of a set into classes according to some continuously varying parameter. If the parameter proves to be physically important, then the classification itself becomes fundamental, and often leads quite directly to the theoretical concepts." Ecology has had this large psychological penduluum that has swung through its core over the last several decades. I first became involved in ecological research during the time of "systems ecology," in the late 1960's and early 1970's, a time of Lotka, Volterra, MacArthur, Slobokin and Hutchinson, and I was greatly entranced by the idea that there are rules that govern the interaction of life on this planet. But I was also impressed at the time that the psychological attitude then seemed to recapitulate that of The Golden Age of Reason, a time when Newton's laws of motion were first being introduced into Europe, where for the first time the world began to make sense, to the point that poetry was written about the effect: Nature and nature'
Re: [ECOLOG-L] Anderson's new book, "Model Based Inference in the Life Sciences"
Wirt Atmar wrote: In 1964, Richard Feynman, in a lecture to students at Cornell that's available on YouTube, explained the standard procedure that has been adopted by experimental physics in this manner: "How would we look for a new law? In general we look for a new law by the following process. First, we guess it. (laughter) Then we... Don't laugh. That's the damned truth. Then we compute the consequences of the guess... to see if this is right, to see if this law we guessed is right, to see what it would imply. And then we compare those computation results to nature. Or we say to compare it to experiment, or to experience. Compare it directly with observations to see if it works. "If it disagrees with experiment, it's wrong. In that simple statement is the key to science. It doesn't make a difference how beautiful your guess is. It doesn't make a difference how smart you are, who made the guess or what his name is... (laughter) If it disagrees with experiment, it's wrong. That's all there is to it." -- http://www.youtube.com/watch?v=F5Cwbt6RY In physics, the model comes first, not afterwards, and that small difference underlies the whole of the success that physics has had in explaining the mechanics of the world that surrounds us. I agree with much of what you cited and in large parts also with David Anderson's crusade against hypothesis testing and for multi-model inference (although it isn't exactly a new topic). However, I'm really tired of hearing about the physics envy cultivated among so many ecologist. Especially the last paragraph expresses this whole notion well: if only ecologists had used such and such an approach, as physicists did, we would by now have the same set of conclusive and stringent laws and would be able to successfully construct ecosystems from scratch. In reality, ecology has had loads of rigorous scientists, bright minds and multi-model inference but the signal to noise ratio in our system is completely different from the systems explored in physics. If you were to be a good scientist as Feynman suggest and come up with detailed theories/laws in ecology, build models based on them, make predictions and try to validate them on data from the real world, you would always have to reject them because you can always find an ecological system that will violate your predictions. I still believe that this would be the right way to progress in ecology but I think it is folly to expect the same "clean" results as in physics. A good point in case is the unified neutral theory of biodiversity. Hubbell came up with a theory, built a mathematical machinery according to this theory and validated his predictions on empirical data. Then people tried to apply his theory and predictions to other systems and soon failures to explain an acceptable level of variation in certain systems became apparent. According to Feynman then the theory is "wrong and that's all there is to it". I, in contrast, believe that we have to take into consideration the low signal to noise ratio in our systems and the staggering number of more or less equally important factors that govern them, plus the multitude of feedback loops and time lags before passing such harsh judgments about ecology. AND I don't believe that switching from hypotheses tests to multi-model inference will get us to a set of conclusive and stringent laws as they exist in physics any time soon. But I do believe that the described way is the right path to advance ecology. Volker -- -- Volker Bahn Department of Biology McGill University Stewart Biol. Bldg. W3/5 1205 ave Docteur Penfield Montreal, QC, H3A 1B1 Canada t: (514) 398-6428 f: (514) 398-5069 [EMAIL PROTECTED] www.volkerbahn.com Lat-Long: 45.50285, -73.5814 --
Re: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book,
That's why I think context, especially with a character like Feynman, might be crucial. Damned near everything he said was with a wink, and I suspect he might not have been above making bold misstatements to lure great minds out of hiding. And he could have been just plain "wrong." However, I think the crucial lesson here is that statements can, even while "wrong," contain, or lead to, truths. The presumption of correctness is poisonous to the fertile mind; so is the terror of being wrong. My contact with Feynman has been zero, except when his brilliance shone with penetrating energy, yea, even through the Toob. And his books, of course. I did attend a talk in the Arcadia CA library when Ralph Leighton's book, "Tuva or Bust" came out. It was clear that Feynman's life force (determined joy?) had stimulated Leighton to explore his own inner self. Who could forget the ironic challenge he laid before ass-covering bureaucrats and politicians with a simple glass of ice-water and an o-ring? That one act alone illuminated the institutional rigidity (hence, again ironically, the brittleness) of one of the "greatest" "scientific" institutions in the world. Anyone should have been able to see, with crystal clarity, that the government was being run by self-serving bozos who could blithely override technical competence (none dare call it treason?). Sadder yet, no engineer, no scientist, no manager, no flunky in the whole in-the-loop crowd, would risk his job in defiance of stupidity. The failure of a robo-nation to rise up in riot must have weighed heavily on Feynman. Even if Feynman had been a dummy, he would have been a personality of great magnitude. WT At 08:13 AM 2/21/2008, William Silvert wrote: It might be worth adding that Einstein probably would also have disagreed with Feynman on this point. The original test of general relativity proved it false. Einsten didn't give up, and is even alledged to have faked some calculations to support his view, and eventually a flaw was found in the experiment and subsequent work was consistent with the theory. Hey, if you have a good theory you don't give it up without a fight. I might add that my only personal contact with Feynman was at a meeting of the American Physical Society where he presented his black hole theory of the nucleus. It was wrong. Bill Silvert - Original Message - From: "Wayne Tyson" <[EMAIL PROTECTED]> To: Sent: Thursday, February 21, 2008 5:58 AM Subject: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book, There's one distinction that might need to be made, maybe not. When Feynman said, "If it disagrees with [the?] experiment, it's wrong. In that simple statement is the key to science. It doesn't make a difference how beautiful your guess is. It doesn't make a difference how smart you are, who made the guess or what his name is... (laughter) If it disagrees with [the?] experiment, it's wrong. That's all there is to it." I hope everyone who reads this list understands that Feynman means that the guess is wrong if the experiment demonstrates otherwise (not the experiment), or that if I am mistaken in this presumption that I will be corrected. I suspect that a transcript of Feynman's lecture, especially a fragment thereof, could be misinterpreted in the absence of the context of the actual lecture, even Feynman's way of expressing himself.
Re: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book,
It would be interesting to have this discussion after reading Don Strong's 1980 seminal paper "Null Hypotheses in Ecology" Synthese 43:271-285 . Although I use AIC in my own research (see Grossman et al. 2006 Ecol Monog.76:217), IMO Anderson, Johnson and others have thrown out the baby with the bath water when they state that null hypotheses are trivial in ecology. In fact, the whole neutral model approach in ecology really is based on null hypotheses, and it has been one of the most productive areas in ecology since the 80's (see the great book by Gotelli and Green, Null Models in Ecology). Prior to those conceptual advances we had "models" ( i.e. the competitionist model) and many investigators worked hard to twist their data to fit the "model" (really it could be argued that the development of neutral models were a paradigm shift in the Kuhnian sense). Frankly, frequentist, information-theoretic, and Bayesian approaches all have their place in ecology and we should just get over, trashing frequentist approaches. To twist a phrase "Statistics don't misuse data, People misuse data" . Frankly, to suggest that information-theoretic approaches are less arbitrary because they don't use cut-off values is inappropriate, because cut off values are used for the interpretation of wi values and DeltaAIC values. Nonetheless, weight of evidence approaches are fantastic tools for ecology, but they are not the end-all and be-all for our field. There have been several back and forth exchanges in the literature over the last 5-6 years regarding these points so I won't belabor them here. cheers, -- Gary D. Grossman Distinguished Research Professor - Animal Ecology Warnell School of Forestry & Natural Resources University of Georgia Athens, GA, USA 30602 http://www.arches.uga.edu/~grossman Board of Editors - Animal Biodiversity and Conservation Editorial Board - Freshwater Biology Editorial Board - Ecology Freshwater Fish
Re: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book,
It might be worth adding that Einstein probably would also have disagreed with Feynman on this point. The original test of general relativity proved it false. Einsten didn't give up, and is even alledged to have faked some calculations to support his view, and eventually a flaw was found in the experiment and subsequent work was consistent with the theory. Hey, if you have a good theory you don't give it up without a fight. I might add that my only personal contact with Feynman was at a meeting of the American Physical Society where he presented his black hole theory of the nucleus. It was wrong. Bill Silvert - Original Message - From: "Wayne Tyson" <[EMAIL PROTECTED]> To: Sent: Thursday, February 21, 2008 5:58 AM Subject: [ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book, There's one distinction that might need to be made, maybe not. When Feynman said, "If it disagrees with [the?] experiment, it's wrong. In that simple statement is the key to science. It doesn't make a difference how beautiful your guess is. It doesn't make a difference how smart you are, who made the guess or what his name is... (laughter) If it disagrees with [the?] experiment, it's wrong. That's all there is to it." I hope everyone who reads this list understands that Feynman means that the guess is wrong if the experiment demonstrates otherwise (not the experiment), or that if I am mistaken in this presumption that I will be corrected. I suspect that a transcript of Feynman's lecture, especially a fragment thereof, could be misinterpreted in the absence of the context of the actual lecture, even Feynman's way of expressing himself.
Re: [ECOLOG-L] Anderson's new book,
This has been an intersting discussion, especially for me since I have spent half my career as a theoretical physics and half in marine ecology, and I am a great admirer of Richard Feynman. I think that the key to all this is that science involves trying to find explanatory patterns in nature, which involves either looking at existing data or looking for new data. Much science involves just looking around, such as the amazing work that was done by simply exploring abysses in the ocean and more recently investigating the fauna under the antarctic ice. Sequencing genomes and number crunching are explorations of this kind. Most science is a bit mixed though. High energy physicists are building huge accelerators in hopes of finding the Higgs boson (an hypothetical particle) but they are also on the lookout for unexpected results. The role of statistics in physics ir relatively minor, it is simply used to see whether the patterns we see seem real. It is analogous to analysing the well-known psychology experiment where you see two lines (<---> and >---<) and one looks longer than the other, but one can use a tool - a measuring stick - to see that in fact they are the same length. Despite my long study of physics, as both an undergraduate physics major and a PhD student, I was never asked to take a statistics course, although some statistics was covered in my freshman laboratory work (ironically that is where I learned about propagation of error, something that few ecologists seem to know). In fields where statistics are relevant, such as high-energy physics involving the analysis of millions of particle tracks, most physicists develop their own statistical concepts. There is one point where I disagree with the quotations from Feynman, "If it disagrees with experiment, it's wrong." It's wrong if the experiment is right. In many cases I have found that the experimental data are wrong (and my criterion for wrong is that after discussing the experiment the experimentalists agree that their data are wrong, which usually means misinterpreted). This is more of a problem in ecology than in physics because theory and experiment are closer in physics, and experimentalists thus pay careful attention to identifying the underlying assumptions and problems of interpretation of their data. All experiments after all are based on models, and it is hard to do a good experiment if you don't understand the theory behind what you are doing. Since Feynman's name has been raised, I will recall an incident that occurred on this list several years ago. I referred to Feynman's excellent book, "Surely you are joking Mr. Feynman" and mentioned an experiment he did with ants in his kitchen. An angry response followed with a complaint that he knew nothing about ant behaviour and was totally unqualified to carry out such experiments. Draw your own conclusions, and stay out of the kitchen. Bill Silvert - Original Message - From: "Jeff Houlahan" <[EMAIL PROTECTED]> To: Sent: Wednesday, February 20, 2008 8:46 PM Subject: Re: [ECOLOG-L] Anderson's new book, Hi Wirt, I completely agree with almost all of what you (and David) wrote. Feynman is talking about a real hypothesis that arose from a great deal of thought and creativity...not one that has been attached with baling wire, duct tape and a little leftover Juicy Fruit to a pile of data that happened to be sitting around. That said, science is many things - 'a predictive enterprise, not some form of mindless after-the-fact exercise in number crunching.' - fits under the umbrella but I don't think captures the whole enterprise. Sequencing the human genome was, in my opinion, a version of mindless number crunching (although perhaps somebody can put that effort in a hypothesis testing context that I haven't thought of). I think most people would be hard pressed to say it wasn't science. In fact, there is an emerging field of statistics (data mining) that seems to be useful in developing scientific hypotheses and is all about the 'mindless after-the-fact exercise in number crunching'. My feeling is that data can provide hypotheses or test them. When it does the first, it is a very useful part of science but it is not predictive and it does not test hypotheses (null, competing or otherwise). When it does the latter it falls ito the category that Feynman was describing. I think the reason we often get these trivial tests of hypotheses is because there is this sense that science is only about testing hypotheses - therefore to do science I must test a hypothesis...whether there is a meaningful one or not. In my opinion, science can also just be about looking for patterns that we can use to suggest hypotheses. Hypotheses have to be tested to be useful but the patterns we see in nature (and those patter
[ECOLOG-L] Ecology and Theory and Evidence and Limitations and so on Re: [ECOLOG-L] Anderson's new book,
atistics (data mining) that seems to be useful in developing scientific hypotheses and is all about the 'mindless after-the-fact exercise in number crunching'. My feeling is that data can provide hypotheses or test them. When it does the first, it is a very useful part of science but it is not predictive and it does not test hypotheses (null, competing or otherwise). When it does the latter it falls ito the category that Feynman was describing. I think the reason we often get these trivial tests of hypotheses is because there is this sense that science is only about testing hypotheses - therefore to do science I must test a hypothesis...whether there is a meaningful one or not. In my opinion, science can also just be about looking for patterns that we can use to suggest hypotheses. Hypotheses have to be tested to be useful but the patterns we see in nature (and those patterns are often less distinct without number crunching)are almost always the birthplace of hypotheses. Best. Jeff H -Original Message- From: Wirt Atmar <[EMAIL PROTECTED]> To: ECOLOG-L@LISTSERV.UMD.EDU Date: Wed, 20 Feb 2008 12:03:54 -0700 Subject: [ECOLOG-L] Anderson's new book, "Model Based Inference in the Life Sciences" I just purchased David Anderson's new book, "Model Based Inference in the Life Sciences: a primer on evidence," and although I've only had the opportunity to read just the first two chapters, I wanted to write and express my enthusiasm for both the book and especially its first chapter. David and Ken Burnham once bought me lunch, and because my loyalties are easily purchased, I may be somewhat biased in my approach towards the book, but David writes something very important in the first chapter that I have been mildly railing against for sometime now too: the uncritical overuse of null hypotheses in ecology. Indeed, I believe this to be such an important topic that I wish he had extended the section for several more pages. What he does write is this, in part: "It is important to realize that null hypothesis testing was *not* what Chamberlin wanted or advocated. We so often conclude, essentially, 'We rejected the null hypothesis that was uninteresting or implausible in the first place, P < 0.05.' Chamberlin wanted an *array* of *plausible* hypotheses derived and subjected to careful evaluation. We often fail to fault the trivial null hypotheses so often published in scientific journals. In most cases, the null hypothesis is hardly plausible and this makes the study vacuous from the outset... "C.R. Rao (2004), the famous Indian statistician, recently said it well, '...in current practice of testing a null hypothesis, we are asking the wrong question and getting a confusing answer'" (2008, pp. 11-12). This is so completely different than the extraordinarily successful approach that has been adopted by physics. In ecology, an experiment is most normally designed so its results may be statistically tested against a null hypothesis. In this procedure, data analysis is primarily a posteriori process, but this is an intrinsically weak test philosophically. In the end, you rarely understand more about the processes in force than you did before you began. But the analyses characteristic of physics donât work that way. In 1964, Richard Feynman, in a lecture to students at Cornell that's available on YouTube, explained the standard procedure that has been adopted by experimental physics in this manner: "How would we look for a new law? In general we look for a new law by the following process. First, we guess it. (laughter) Then we... Don't laugh. That's the damned truth. Then we compute the consequences of the guess... to see if this is right, to see if this law we guessed is right, to see what it would imply. And then we compare those computation results to nature. Or we say to compare it to experiment, or to experience. Compare it directly with observations to see if it works. "If it disagrees with experiment, it's wrong. In that simple statement is the key to science. It doesn't make a difference how beautiful your guess is. It doesn't make a difference how smart you are, who made the guess or what his name is... (laughter) If it disagrees with experiment, it's wrong. That's all there is to it." -- http://www.youtube.com/watch?v=ozF5Cwbt6RY In physics, the model comes first, not afterwards, and that small difference underlies the whole of the success that physics has had in explaining the mechanics of the world that surrounds us. The entire array of plausible hypotheses that were advocated by Chamberlin don't all have to present during the first experimental attempt at verification of the first hypothesis; they can occur sequentially over a period of years. As David continues, "We must encourage and re
Re: [ECOLOG-L] Anderson's new book, "Model Based Inference in the Life Sciences"
I recently read a similar thing in the book "Data Analysis and Graphs Using R" from Mainload & Braun. I will reproduce it here. In fact, it is already a quotation from Tukey, J. W. (1991). The philosophy of multiple comparisons. Statistical Science 6:100-116. "Statisticians classically asked the wrong question - and were willing o answer with a lie, one that was often a downright lie. They asked 'Are the effects of A and B different?' and they were willing to say 'no'. All we know about the world teaches us that the effects of A and B are always different - in some decimal place - for every A and B. Thus, asking 'Are the effects different?' is foolish. What we should be answering first is 'Can we tell the direction in which the effects of A differ from the effects of B?' In other words, can we be confident about the direction from A to B? Is it 'up', 'down', or 'uncertain'? Latter, in the words of the book author: "Turkey argues that we should never conclude that we 'accept the null hypothesis'. --- Wirt Atmar <[EMAIL PROTECTED]> escreveu: > I just purchased David Anderson's new book, "Model > Based Inference in the Life > Sciences: a primer on evidence," and although I've > only had the opportunity to > read just the first two chapters, I wanted to write > and express my enthusiasm > for both the book and especially its first chapter. > > David and Ken Burnham once bought me lunch, and > because my loyalties are easily > purchased, I may be somewhat biased in my approach > towards the book, but David > writes something very important in the first chapter > that I have been mildly > railing against for sometime now too: the uncritical > overuse of null hypotheses > in ecology. Indeed, I believe this to be such an > important topic that I wish he > had extended the section for several more pages. > > What he does write is this, in part: > > "It is important to realize that null hypothesis > testing was *not* what > Chamberlin wanted or advocated. We so often > conclude, essentially, 'We rejected > the null hypothesis that was uninteresting or > implausible in the first place, P > < 0.05.' Chamberlin wanted an *array* of *plausible* > hypotheses derived and > subjected to careful evaluation. We often fail to > fault the trivial null > hypotheses so often published in scientific > journals. In most cases, the null > hypothesis is hardly plausible and this makes the > study vacuous from the > outset... > > "C.R. Rao (2004), the famous Indian statistician, > recently said it well, '...in > current practice of testing a null hypothesis, we > are asking the wrong question > and getting a confusing answer'" (2008, pp. 11-12). > > This is so completely different than the > extraordinarily successful approach > that has been adopted by physics. > > In ecology, an experiment is most normally designed > so its results may be > statistically tested against a null hypothesis. In > this procedure, data analysis > is primarily a posteriori process, but this is an > intrinsically weak test > philosophically. In the end, you rarely understand > more about the processes in > force than you did before you began. But the > analyses characteristic of physics > don’t work that way. > > In 1964, Richard Feynman, in a lecture to students > at Cornell that's available > on YouTube, explained the standard procedure that > has been adopted by > experimental physics in this manner: > > "How would we look for a new law? In general we look > for a new law by the > following process. First, we guess it. (laughter) > Then we... Don't laugh. That's > the damned truth. Then we compute the consequences > of the guess... to see if > this is right, to see if this law we guessed is > right, to see what it would > imply. And then we compare those computation results > to nature. Or we say to > compare it to experiment, or to experience. Compare > it directly with > observations to see if it works. > > "If it disagrees with experiment, it's wrong. In > that simple statement is the > key to science. It doesn't make a difference how > beautiful your guess is. It > doesn't make a difference how smart you are, who > made the guess or what his name > is... (laughter) If it disagrees with experiment, > it's wrong. That's all there > is to it." > > -- http://www.youtube.com/watch?v=ozF5Cwbt6RY > > In physics, the model comes first, not afterwards, > and that small difference > underlies the whole of the success that physics has > had in explaining the > mechanics of the world that surrounds us. > > The entire array of plausible hypotheses that were > advocated by Chamberlin don't > all have to present during the first experimental > attempt at verification of the > first hypothesis; they can occur sequentially over a > period of years. > > As David continues, "We must encourage and reward > hard thinking. There must be a > premium on thinking, innovation, synthesis and > creativity" (p. 12), and this > hard thinking must be done
Re: [ECOLOG-L] Anderson's new book,
Hi Wirt, I completely agree with almost all of what you (and David) wrote. Feynman is talking about a real hypothesis that arose from a great deal of thought and creativity...not one that has been attached with baling wire, duct tape and a little leftover Juicy Fruit to a pile of data that happened to be sitting around. That said, science is many things - 'a predictive enterprise, not some form of mindless after-the-fact exercise in number crunching.' - fits under the umbrella but I don't think captures the whole enterprise. Sequencing the human genome was, in my opinion, a version of mindless number crunching (although perhaps somebody can put that effort in a hypothesis testing context that I haven't thought of). I think most people would be hard pressed to say it wasn't science. In fact, there is an emerging field of statistics (data mining) that seems to be useful in developing scientific hypotheses and is all about the 'mindless after-the-fact exercise in number crunching'. My feeling is that data can provide hypotheses or test them. When it does the first, it is a very useful part of science but it is not predictive and it does not test hypotheses (null, competing or otherwise). When it does the latter it falls ito the category that Feynman was describing. I think the reason we often get these trivial tests of hypotheses is because there is this sense that science is only about testing hypotheses - therefore to do science I must test a hypothesis...whether there is a meaningful one or not. In my opinion, science can also just be about looking for patterns that we can use to suggest hypotheses. Hypotheses have to be tested to be useful but the patterns we see in nature (and those patterns are often less distinct without number crunching)are almost always the birthplace of hypotheses. Best. Jeff H -Original Message- From: Wirt Atmar <[EMAIL PROTECTED]> To: ECOLOG-L@LISTSERV.UMD.EDU Date: Wed, 20 Feb 2008 12:03:54 -0700 Subject: [ECOLOG-L] Anderson's new book, "Model Based Inference in the Life Sciences" I just purchased David Anderson's new book, "Model Based Inference in the Life Sciences: a primer on evidence," and although I've only had the opportunity to read just the first two chapters, I wanted to write and express my enthusiasm for both the book and especially its first chapter. David and Ken Burnham once bought me lunch, and because my loyalties are easily purchased, I may be somewhat biased in my approach towards the book, but David writes something very important in the first chapter that I have been mildly railing against for sometime now too: the uncritical overuse of null hypotheses in ecology. Indeed, I believe this to be such an important topic that I wish he had extended the section for several more pages. What he does write is this, in part: "It is important to realize that null hypothesis testing was *not* what Chamberlin wanted or advocated. We so often conclude, essentially, 'We rejected the null hypothesis that was uninteresting or implausible in the first place, P < 0.05.' Chamberlin wanted an *array* of *plausible* hypotheses derived and subjected to careful evaluation. We often fail to fault the trivial null hypotheses so often published in scientific journals. In most cases, the null hypothesis is hardly plausible and this makes the study vacuous from the outset... "C.R. Rao (2004), the famous Indian statistician, recently said it well, '...in current practice of testing a null hypothesis, we are asking the wrong question and getting a confusing answer'" (2008, pp. 11-12). This is so completely different than the extraordinarily successful approach that has been adopted by physics. In ecology, an experiment is most normally designed so its results may be statistically tested against a null hypothesis. In this procedure, data analysis is primarily a posteriori process, but this is an intrinsically weak test philosophically. In the end, you rarely understand more about the processes in force than you did before you began. But the analyses characteristic of physics don’t work that way. In 1964, Richard Feynman, in a lecture to students at Cornell that's available on YouTube, explained the standard procedure that has been adopted by experimental physics in this manner: "How would we look for a new law? In general we look for a new law by the following process. First, we guess it. (laughter) Then we... Don't laugh. That's the damned truth. Then we compute the consequences of the guess... to see if this is right, to see if this law we guessed is right, to see what it would imply. And then we compare those computation results to nature. Or we say to compare it to experiment, or to experience. Compare it directly with observations to see if it works. "If it disagrees with experiment, it'
[ECOLOG-L] Anderson's new book, "Model Based Inference in the Life Sciences"
I just purchased David Anderson's new book, "Model Based Inference in the Life Sciences: a primer on evidence," and although I've only had the opportunity to read just the first two chapters, I wanted to write and express my enthusiasm for both the book and especially its first chapter. David and Ken Burnham once bought me lunch, and because my loyalties are easily purchased, I may be somewhat biased in my approach towards the book, but David writes something very important in the first chapter that I have been mildly railing against for sometime now too: the uncritical overuse of null hypotheses in ecology. Indeed, I believe this to be such an important topic that I wish he had extended the section for several more pages. What he does write is this, in part: "It is important to realize that null hypothesis testing was *not* what Chamberlin wanted or advocated. We so often conclude, essentially, 'We rejected the null hypothesis that was uninteresting or implausible in the first place, P < 0.05.' Chamberlin wanted an *array* of *plausible* hypotheses derived and subjected to careful evaluation. We often fail to fault the trivial null hypotheses so often published in scientific journals. In most cases, the null hypothesis is hardly plausible and this makes the study vacuous from the outset... "C.R. Rao (2004), the famous Indian statistician, recently said it well, '...in current practice of testing a null hypothesis, we are asking the wrong question and getting a confusing answer'" (2008, pp. 11-12). This is so completely different than the extraordinarily successful approach that has been adopted by physics. In ecology, an experiment is most normally designed so its results may be statistically tested against a null hypothesis. In this procedure, data analysis is primarily a posteriori process, but this is an intrinsically weak test philosophically. In the end, you rarely understand more about the processes in force than you did before you began. But the analyses characteristic of physics don’t work that way. In 1964, Richard Feynman, in a lecture to students at Cornell that's available on YouTube, explained the standard procedure that has been adopted by experimental physics in this manner: "How would we look for a new law? In general we look for a new law by the following process. First, we guess it. (laughter) Then we... Don't laugh. That's the damned truth. Then we compute the consequences of the guess... to see if this is right, to see if this law we guessed is right, to see what it would imply. And then we compare those computation results to nature. Or we say to compare it to experiment, or to experience. Compare it directly with observations to see if it works. "If it disagrees with experiment, it's wrong. In that simple statement is the key to science. It doesn't make a difference how beautiful your guess is. It doesn't make a difference how smart you are, who made the guess or what his name is... (laughter) If it disagrees with experiment, it's wrong. That's all there is to it." -- http://www.youtube.com/watch?v=ozF5Cwbt6RY In physics, the model comes first, not afterwards, and that small difference underlies the whole of the success that physics has had in explaining the mechanics of the world that surrounds us. The entire array of plausible hypotheses that were advocated by Chamberlin don't all have to present during the first experimental attempt at verification of the first hypothesis; they can occur sequentially over a period of years. As David continues, "We must encourage and reward hard thinking. There must be a premium on thinking, innovation, synthesis and creativity" (p. 12), and this hard thinking must be done in advance of the experiment. Science is a predictive enterprise, not some form of mindless after-the-fact exercise in number crunching. Although expressed in a different format, David Anderson is saying the same thing as Richard Feynman, and I very much congratulate him for it. Wirt Atmar