Let the Worship Begin

_{Cornelius Hunter

May 15, 2010

Intelligent Design}

Share: Facebook; Twitter; LinkedIn; Flipboard; Print; Email

In 1734 Daniel Bernoulli used cutting edge statistical methods of his day to prove that our solar system must have evolved as a result of a single cause. He who would deny this, concluded the scientist-mathematician, “must reject all the truths, which we know by induction.” Bernoulli’s high confidence was, of course, unwarranted as later years would reveal. But today, almost three centuries later, little has changed. Read more

Comments

#20 and #21 So really all this comes down to is that you don't think there is any evidence for modern evolutionary theory and the only argument for it is that its proponents can't see any alternative. This has been discussed about a million times on this forum. My apologies - I thought you were commenting on Douglas's paper which is about strong evidence for a universal common ancestor.Mark Frank_{May 18, 2010
May
05
May
18
18
2010
12:41 AM
12
12
41
AM
PDT}

Eve’one knows Bubba ain’t none too bright. Eve’one can see that depriving Crooked Tooth of our only doctor t’weren’t none too bright. It’s staring ya’ right in the face, man: “Bubba Done It!” === Proponents of evolutionism like to caricature creationism as “goddidit!” … as though that is all there is to creationism. Proponents of evolutionism like to caricature ID as “goddidit!” … despite that ID isn’t even about God. *I* think that one may accurately characterize evolutionism as “Bubba Done It!”Ilion_{May 17, 2010
May
05
May
17
17
2010
11:48 PM
11
11
48
PM
PDT}

StephenB: “[A-1] Bubba must have committed the crime because there are no other possible suspects.” Even that is granting to Darwinistic “reasoning” an intellectual integrity that it simply does not possesses. It’s not that there are no other possible suspects than Bubba; it is that Sheriff Cornpone and the Public Prosecutor, Jimmy Crackcorn, Esq. are wholly uninterested in examining the question of whether Bubba really is the only possible suspect.Ilion_{May 17, 2010
May
05
May
17
17
2010
11:28 PM
11
11
28
PM
PDT}

stephenB, I prefer a process where alternative explanations are ruled out through decades of diligent scientific endeavour than through the non-scientific assertion of "it looks designed therefore something must have designed it". I would hope you are honest enough to admit that most ID supporters on this site have at their core a belief that God created the world and therefore there is just the teeniest possibility that that assumption influences their acceptance of ID. This parable is far more appropriate to ID supporters.zeroseven_{May 17, 2010
May
05
May
17
17
2010
03:18 PM
3
03
18
PM
PDT}

Inasmuch as the process Theobald used is comparative, perhaps the ID hypothesis could be tested against universal common descent to resolve this all for once and for all.San Antonio Rose_{May 17, 2010
May
05
May
17
17
2010
01:09 PM
1
01
09
PM
PDT}

---Mark Frank: "I am always pleased to provide amusment. Maybe in return you can explain the point behind the parable which I have clearly missed (I thought it was intended to be some kind of criticism of Douglas’s method of inference)." [A-1] Bubba must have committed the crime because there are no other possible suspects. [A-2] All other suspects, even if they could have been responsible, have been ruled out apriori for the sake of getting a conviction. [A-3] Therefore, we need not prove that Bubba did it because the proof is inherent in the fact that there are no other suspects. [A4] If there are no other suspects, then Bubba did it. [B-1] Naturalistic causes, such as Random Variation and natural selection, caused evolution because there are no other possible explanations. [B-2] All other explanations, including intelligence, have been ruled out apriori by Methodological Naturalism for the sake of maintaining a crumbling paradigm. [B-3] Therefore, we need not prove that Darwinistic-like mechanisms caused biodiveristy because the proof is inherent in the fact that no other explanation is possible. [B-4] If there are no other possible explanations, then Darwinism must be true.StephenB_{May 17, 2010
May
05
May
17
17
2010
12:46 PM
12
12
46
PM
PDT}

#15 Ilion I am always pleased to provide amusment. Maybe in return you can explain the point behind the parable which I have clearly missed (I thought it was intended to be some kind of criticism of Douglas's method of inference).Mark Frank_{May 17, 2010
May
05
May
17
17
2010
08:40 AM
8
08
40
AM
PDT}

What's so amusing, Mr Frank, is that your response illustrates the very thing about DarwinDefender "logic" that I am mocking with that parable -- and you still don't get it!Ilion_{May 17, 2010
May
05
May
17
17
2010
07:53 AM
7
07
53
AM
PDT}

#12 Ilion Owning a knife does not significantly raise the probability that Bubba did it compared to all the other possible murderers, many of whom may own knives or have access to knives. If the Doctor had died through use of the new zappa gun which Bubba had the only one known to exist and he was the only person who knew how to work it then the case against him would look strong because the alternatives - all the other candidates - were much less likely to able to do the murder.Mark Frank_{May 17, 2010
May
05
May
17
17
2010
02:46 AM
2
02
46
AM
PDT}

DarwinDefenders, and all others under the sway of scientism, habitually "reason" in the manner of Jimmy Crackcorn, Esq.Ilion_{May 16, 2010
May
05
May
16
16
2010
11:45 PM
11
11
45
PM
PDT}

C.Hunter: “My point was that: one hypothesis comparing well against others does not translate into very strong empirical evidence for the hypothesis.” A parable: In the small, isolated town of Crooked Tooth, the belovéd Dr Doctor has been found dead. As there are multiple knife wounds to his chest, natural death, and even suicide, has been ruled out, leaving only murder as an explanation of his death. After some crack detective work by Sheriff Cornpone, and some even cracker legal finagling by the Public Prosecutor, Jimmy Crackcorn, Esq. (who is, after all, a trained lawyer), Bubba Jones has been indicted for the murder of the belovéd Dr Doctor. Now, as it turns out in the trial’s progression, the evidence which the Public Prosecutor, Jimmy Crackcorn, Esq., presents as supporting his hypothesis that “Bubba Done It!” is the fact (acknowledged by all) that Bubba owns a knife. In contrast, Bubba Jones’ entire defense, as mounted by John Queue, Public Defender, amounts to the feebly pathetic, “Bubba didn’t Do It! … And the Prosecution has failed its Burden Of Proof!” I mean, really! *rolls eyes* In his closing statement, the Public Prosecutor, Jimmy Crackcorn, Esq., makes this emotionally moving appeal to the Jury: “Esteemed Ladies and Gentlemen of the Jury: the facts are these: 1) Our belovéd Dr Doctor has been brutally murdered (leaving Crooked Tooth without the care of a doctor); 2) Our belovéd Dr Doctor was brutally murdered with a knife; 3) That scallywag, Bubba Jones, owns a knife (as all admit); 4) The Public Defender’s only so-called evidence for his claim of Bubba Jones’ innocence of this heinous crime is to claim that the Prosecution has not proven guilt; 5) But, esteemed Ladies and Gentlemen of the Jury, if you do not convict Bubba Jones of the murder of our belovéd Dr Doctor, then this heinous crime shall go unpunished -- FOR WE HAVE NO OTHER SUSPECT!”Ilion_{May 16, 2010
May
05
May
16
16
2010
11:42 PM
11
11
42
PM
PDT}

Cornelius wrote:
My point was that: one hypothesis comparing well against others does not translate into very strong empirical evidence for the hypothesis.
I addressed that in the latter half of my comment, which you chose to ignore:
You wrote:
I again explained that when one hypothesis beats out others you cannot make the claims you are making. What you have is very strong evidence that the hypothesis beats out the other hypotheses, period. You do not have very strong evidence for the hypothesis, as you are claiming.
If someone claimed that the evidence was overwhelming that the earth orbits the sun, would you reply as follows? When a hypothesis beats out others you cannot make the claims you are making. What you have is very strong evidence that the hypothesis that the earth orbits the sun beats out the other hypotheses, period. You do not have very strong evidence for the hypothesis, as you are claiming.
You can't have it both ways, Cornelius. If your criticism applies to Theobald, it also applies to those reckless astronomers who, in their hubris, claim that we have strong evidence for the hypothesis that the earth orbits the sun.pelagius_{May 16, 2010
May
05
May
16
16
2010
07:25 PM
7
07
25
PM
PDT}

Doug: ============ George has made a very significant error in comparing my methodology to Bernoulli's. And the error is extremely ironic (and pretty darn funny, if you're a statistics geek like me). The results in my paper are explicitly based on model selection theory, likelihoodist and Bayesian statistics -- not on classical frequentist null-hypothesis testing, which in fact I criticize in the main text of the paper and in the supplementary materials. Bernoulli's solar system argument, however, is a classic example of a null-hypothesis test -- it is often cited as the first one known. The irony here, of course, is that I don't use Bernoulli's methods, ... So in this sense George is correct about Bernoulli, that "disproving" the null hypothesis is not evidence for the favored hypothesis ... But this criticism does not apply to Bayesian statistics ============ You're reading this in as, of course, I never made such a criticism. What I noted is that Bernoulli used contrastive thinking and made unsupportable claims, as you do. =========== And by calculating the probability of the observed data under each of the different competing hypotheses, you are in fact able to calculate the evidence for the different hypotheses -- the very thing George claims is impossible. That is exactly what Bayesian methods allow you to do, and it's why they have become so popular throughout science in the past 15 years. =========== No, I did not claim that is impossible. I said your claim that your results are very strong empirical evidence for the universal common descent hypothesis is false. You later agreed, but with the caveat that pointing out that your claim is false amounts to skepticism -- an overly naunced, finicky interpretation of your results. You wrote: ========= Fine, so from my analysis we have overwhelming evidence that universal common ancestry beats out competing multiple independent ancestry hypotheses. If you don't consider that as evidence for universal common ancestry, then you are certainly entitled to that opinion. But the rest of us are not required to believe that your opinion makes any sense. Yours is a strange philosophy, to my mind, and I'm sure to most people who will read your words. ========= So you make a false claim and when it is pointed out by someone you say that person's view is unreasonable. Evidence needs to be carefully understood and treated for what it is. You do no such thing with your results. Rather, in an attempt to defend your false claim you put me in the position of skeptic, saying that my pointing out your false claim amounts to an unreasonable position -- technically correct but really just a technicality. You have made a false claim, and now having been apprised you resist correcting it. It is difficult to imagine how one could do more to abuse science or abuse one's privilege as a scientist. Not only have you made a false claim, but you have shouted it from the rooftop, and you have made the false claim about what is arguably the most influential theory in all of science. You're not arguing about how a particular enzyme works. This is not an arcane scientific debate that doesn't matter to people. In those cases, as bad as false claims are, at least their impact is bounded. In your case, your false claim has global consequences, both literally and figuratively.Cornelius Hunter_{May 16, 2010
May
05
May
16
16
2010
05:52 PM
5
05
52
PM
PDT}

Pelagius (1): ============ You seem to be making the following implicit argument: 1. Bernoulli used a statistical argument. 2. Bernoulli was mistaken. 3. Theobald is using a statistical argument. 4. Therefore, Theobald is probably mistaken. ============ No, I did not / am not, making that argument. Perhaps you did not read the entire blog. My point was that: one hypothesis comparing well against others does not translate into very strong empirical evidence for the hypothesis.Cornelius Hunter_{May 16, 2010
May
05
May
16
16
2010
05:29 PM
5
05
29
PM
PDT}

Let The Worship Begin Indeed: Solid Rock - the 5th service band Featuring TRU-SERVA http://www.youtube.com/watch?v=G4jD70Y-mQ0 How He Loves Us - Kim Walker / Jesus Culture http://www.youtube.com/watch?v=JoC1ec-lYpsbornagain77_{May 16, 2010
May
05
May
16
16
2010
07:55 AM
7
07
55
AM
PDT}

Even when they do agree with one another on the trees they draw from one day to the next, it's because they've agreed with one another to ignore the discrepant trees they *could* have drawn using the same general assumptions used to draw the trees they've agreed upon.Ilion_{May 16, 2010
May
05
May
16
16
2010
12:06 AM
12
12
06
AM
PDT}

further notes without "simple assumptions": Comparing molecular sequences gives the same pattern of discontinuity as the fossil record does: Congruence Between Molecular and Morphological Phylogenies - Colin Patterson Excerpt: "As morphologists with high hopes of molecular systematics, we end this survey with our hopes dampened. Congruence between molecular phylogenies is as elusive as it is in morphology and as it is between molecules and morphology." http://www.arn.org/docs/odesign/od171/sampler171.htm 'The theory makes a prediction (for amino acid sequence similarity); we've tested it, and the prediction is falsified precisely.' Dr. Colin Patterson Senior Principal Scientific Officer in the Paleontology Department at the British Museum Walter T. Brown, In the Beginning (1989), p. 7 Excerpt: "There is not a trace of evidence on the molecular level for the traditional evolutionary series: simple sea life > fish> amphibians > reptiles> mammals. In general, each of the many categories of organisms appear to be equally isolated." http://evolution-facts.org/Appendix/a21.htm Bones, molecules...or both? Excerpt: Evolutionary trees constructed by studying biological molecules often don't resemble those drawn up from morphology. Can the two ever be reconciled?,,, When biologists talk of the 'evolution wars', they usually mean the ongoing battle for supremacy in American schoolrooms between Darwinists and their creationist opponents. But the phrase could also be applied to a debate that is raging (between Darwinists) within systematics. http://www.nature.com/nature/journal/v406/n6793/full/406230a0.html Trees for bees Excerpt: the application of different analytical methodologies does not explain why molecular and morphological data suggest strikingly different hypotheses for the evolution of eusociality in bees. http://www.life.illinois.edu/scameron/pdfs/Lock&Cam.TREE_01.pdf The universal ancestor - Carl Woese Excerpt: What then was this universal ancestor? A discrete picture of the ancestor began to emerge only when many more sequences representing all three phylogenetic domains became available. These sequences could be seen as putting phenotypic flesh on an ancestral phylogenetic skeleton. Yet that task has turned out to be anything but straightforward. Indeed, it would seem to require disarticulating the skeleton. No consistent organismal phylogeny has emerged from the many individual protein phylogenies so far produced. Phylogenetic incongruities can be seen everywhere in the universal tree, from its root to the major branchings within and among the various taxa to the makeup of the primary groupings themselves. http://www.pnas.org/content/95/12/6854.full Do orthologous gene phylogenies really support tree-thinking? Excerpt: We conclude that we simply cannot determine if a large portion of the genes have a common history.,,, CONCLUSION: Our phylogenetic analyses do not support tree-thinking. http://www.ncbi.nlm.nih.gov/pubmed/15913459bornagain77_{May 15, 2010
May
05
May
15
15
2010
07:01 PM
7
07
01
PM
PDT}

National Geographic also got on board to: All Species Evolved From Single Cell, Study Finds http://news.nationalgeographic.com/news/2010/05/100513-science-evolution-darwin-single-ancestor/ It turns out the author is so bold as to actually put a probability on humans being created and not evolving: The statistical analysis showed that the independent origin of humans is “an absolutely horrible hypothesis,” Theobald said, adding that the probability that humans were created separately from everything else is 1 in 10 to the 6,000th power. This is just so special that a evolutionist would all of the sudden find room for a probability calculation when evolutionists are notorious in their ability to ignore all probabilities that have been put forth. Just one example: In Barrow and Tippler’s book The Anthropic Cosmological Principle, they list ten steps necessary in the course of human evolution, each of which, is so improbable that if left to happen by chance alone, the sun would have ceased to be a main sequence star and would have incinerated the earth. They estimate that the odds of the evolution (by chance) of the human genome is somewhere between 4 to the negative 180th power, to the 110,000th power, and 4 to the negative 360th power, to the 110,000th power. Therefore, if evolution did occur, it literally would have been a miracle and evidence for the existence of God. William Lane Craig William Lane Craig – If Human Evolution Did Occur It Was A Miracle – video http://www.youtube.com/watch?v=GUxm8dXLRpA Along that same line: Darwin and the Mathematicians – David Berlinski “The formation within geological time of a human body by the laws of physics (or any other laws of similar nature), starting from a random distribution of elementary particles and the field, is as unlikely as the separation by chance of the atmosphere into its components.” Kurt Gödel, was a preeminent mathematician who is considered one of the greatest to have ever lived. Of Note: Godel was a Theist! http://www.evolutionnews.org/2009/11/darwin_and_the_mathematicians.html “Darwin’s theory is easily the dumbest idea ever taken seriously by science.” Granville Sewell – Professor Of Mathematics – University Of Texas – El Paso ,,,,,,,,,,,,,,,,, I guess when you are free to pick and choose your starting assumptions you can just about prove anything which is about the only thing this paper has proved conclusively,,,, I would love to tease apart his starting "assumptions" for the 23 proteins he chose to use to base his analysis on for studies conducted without any "starting assumptions" give very different conclusions than this paper: The Biological Big Bang model for the major transitions in evolution - Eugene V Koonin - Background: "Major transitions in biological evolution show the same pattern of sudden emergence of diverse forms at a new level of complexity. The relationships between major groups within an emergent new class of biological entities are hard to decipher and do not seem to fit the tree pattern that, following Darwin's original proposal, remains the dominant description of biological evolution. The cases in point include the origin of complex RNA molecules and protein folds; major groups of viruses; archaea and bacteria, and the principal lineages within each of these prokaryotic domains; eukaryotic supergroups; and animal phyla. In each of these pivotal nexuses in life's history, the principal "types" seem to appear rapidly and fully equipped with the signature features of the respective new level of biological organization. No intermediate "grades" or intermediate forms between different types are detectable; http://www.biology-direct.com/content/2/1/21 Biological Big Bangs - Origin Of Life and Cambrian - Dr. Fazale Rana - video http://www.metacafe.com/watch/4284466 This following paper corroborates Koonin's observation of irreconcilable differences being found in the genetic evidence with Darwinian evolution: Why Darwin was wrong about the (genetic) tree of life: - 21 January 2009 Excerpt: Syvanen recently compared 2000 genes that are common to humans, frogs, sea squirts, sea urchins, fruit flies and nematodes. In theory, he should have been able to use the gene sequences to construct an evolutionary tree showing the relationships between the six animals. He failed. The problem was that different genes told contradictory evolutionary stories. This was especially true of sea-squirt genes. Conventionally, sea squirts - also known as tunicates - are lumped together with frogs, humans and other vertebrates in the phylum Chordata, but the genes were sending mixed signals. Some genes did indeed cluster within the chordates, but others indicated that tunicates should be placed with sea urchins, which aren't chordates. "Roughly 50 per cent of its genes have one evolutionary history and 50 per cent another," Syvanen says. ...."We've just annihilated the tree of life. It's not a tree any more, it's a different topology entirely," says Syvanen. "What would Darwin have made of that?" http://www.newscientist.com/article/mg20126921.600-why-darwin-was-wrong-about-the-tree-of-life.html I would like to point out that this, "annihilation" of Darwin's genetic tree of life, article came out on the very day that Dr. Hillis, a self-proclaimed "world leading expert" on the genetic tree of life, testified before the Texas State Board Of Education that the genetic tree of life overwhelmingly confirmed gradual Darwinian evolution. One could almost argue it was "Intelligently Designed" for him to exposed as a fraud on that particular day of his testimony instead of just any other day of the year. Testing the Orchard Model and the NCSE’s Claims of “Nested Patterns” Supporting a “Tree of Life” Excerpt: Perhaps the reason why different genes are telling “different evolutionary stories” and “one group suggests one biogeographic pattern, and another group suggests another” is because the genes and organisms have wholly different stories to tell, namely stories that indicate that not all living organisms are ancestrally related, thereby fulfilling a testable prediction of the orchard model. http://www.evolutionnews.org/2010/03/testing_the_orchard_model_and.html Botching Evolutionary Science - Casey Luskin - April 2009 Excerpt: The textbook touts the cytochrome C tree, but it ignores the cytochrome B tree, which has striking differences from the classical animal phylogeny. As one article in Trends in Ecology and Evolution stated: “[T]he mitochondrial cytochrome b gene implied,, an absurd phylogeny of mammals, regardless of the method of tree construction. Cats and whales fell within primates, grouping with simians (monkeys and apes) and strepsirhines (lemurs, bush-babies and lorises) to the exclusion of tarsiers. Cytochrome b is probably the most commonly sequenced gene in vertebrates, making this surprising result even more disconcerting.” (See Michael S. Y. Lee, “Molecular Phylogenies Become Functional,” Trends in Ecology and Evolution, Vol. 14: 177 (1999).) http://www.evolutionnews.org/2010/04/the_biggest_problem_in_asking.html#more The new animal phylogeny: Reliability and implications: Excerpt: "The new molecular based phylogeny has several important implications. Foremost among them is the disappearance of "intermediate" taxa between sponges, cnidarians, ctenophores, and the last common ancestor of bilaterians or "Urbilateria."...A corollary is that we have a major gap in the stem leading to the Urbilataria. We have lost the hope, so common in older evolutionary reasoning, of reconstructing the morphology of the "coelomate ancestor" through a scenario involving successive grades of increasing complexity based on the anatomy of extant "primitive" lineages." From Proceedings of the National Academy of Sciences, USA, in 2000 - http://www.pnas.org/content/97/9/4453.full.pdf?ijkey=USJfrrxyih/gMbornagain77_{May 15, 2010
May
05
May
15
15
2010
07:00 PM
7
07
00
PM
PDT}

To comment on a couple of the common ancestry articles from physorg and National Geographic: Of microorganisms and man: First large-scale test confirms Darwin’s theory of universal common ancestry http://www.physorg.com/news192882557.html The author made some very interesting assumptions in his model that caught my eye: Theobald’s study rests on several simple assumptions about how the diversity of modern proteins arose. First, he assumed that genetic copies of a protein can be multiplied during reproduction, such as when one parent gives a copy of one of their genes to several of their children. Second, he assumed that a process of replication and mutation over the eons may modify these proteins from their ancestral versions. These two factors, then, should have created the differences in the modern versions of these proteins we see throughout life today. Lastly, he assumed that genetic changes in one species don’t affect mutations in another species—for example, genetic mutations in kangaroos don’t affect those in humans. I thought it real special of him to assume to be true what needs to be proven to be true. http://www.youtube.com/watch?v=RmwqnqL3Hbg Asking the Right Questions about the Evolutionary Origin of New Biological Information - Feb. 2010 As we've seen, it’s easy to duplicate a gene, but the key missing ingredient in many neo-Darwinian explanations of the origin of new genetic information is how a gene duplicate then acquires some new optimized function. Evolutionists have not demonstrated, except in rare specialized cases, that step-wise paths to new function for duplicate genes exist. http://www.evolutionnews.org/2010/02/asking_the_right_questions_abo.html Stephen Meyer - Functional Proteins And Information For Body Plans - video http://www.metacafe.com/watch/4050681 Proteins with cruise control provide new perspective: "A mathematical analysis of the experiments showed that the proteins themselves acted to correct any imbalance imposed on them through artificial mutations and restored the chain to working order." http://www.princeton.edu/main/news/archive/S22/60/95O56/ Cruise Control?,, The equations of calculus involved in achieving even a simple process control loop, such as a dynamic cruise control loop, are very complex. In fact it seems readily apparent to me that highly advanced algorithmic information must reside in each individual amino acid used in a protein in order to achieve such control. This fact gives us clear evidence that far more functional information resides in proteins than meets the eye. It is in realizing the staggering level of engineering that must be dealt with to achieve "cruise control", for each individual protein, that it becomes apparent even Axe's 1 in 10^77 estimate for finding specific functional proteins within sequence space, may be far to generous. This following paper, and audio interview, shows that there is a severe "fitness cost" for cells to carry "transitional" proteins that have not achieved full functionality yet: Reductive Evolution Can Prevent Populations from Taking Simple Adaptive Paths to High Fitness - May 2010 Excerpt: Despite the theoretical existence of this short adaptive path to high fitness, multiple independent lines grown in tryptophan-limiting liquid culture failed to take it. Instead, cells consistently acquired mutations that reduced expression of the double-mutant trpA gene. Our results show that competition between reductive and constructive paths may significantly decrease the likelihood that a particular constructive path will be taken. http://bio-complexity.org/ojs/index.php/main/article/view/BIO-C.2010.2 Dollo’s law, the symmetry of time, and the edge of evolution - Michael Behe - Oct 2009 Excerpt: Nature has recently published an interesting paper which places severe limits on Darwinian evolution.,,, A time-symmetric Dollo’s law turns the notion of “pre-adaptation” on its head. The law instead predicts something like “pre-sequestration”, where proteins that are currently being used for one complex purpose are very unlikely to be available for either reversion to past functions or future alternative uses. http://www.evolutionnews.org/2009/10/dollos_law_the_symmetry_of_tim.html As well, I think more than a few people here on UD have some severe objection to his "simple" assumptions:bornagain77_{May 15, 2010
May
05
May
15
15
2010
06:51 PM
6
06
51
PM
PDT}

Since George has disabled comments on his latest post, I'll reply here, not so much for George but for the others here. George has made a very significant error in comparing my methodology to Bernoulli's. And the error is extremely ironic (and pretty darn funny, if you're a statistics geek like me). The results in my paper are explicitly based on model selection theory, likelihoodist and Bayesian statistics -- not on classical frequentist null-hypothesis testing, which in fact I criticize in the main text of the paper and in the supplementary materials. Bernoulli's solar system argument, however, is a classic example of a null-hypothesis test -- it is often cited as the first one known. The irony here, of course, is that I don't use Bernoulli's methods, for the very reason that disproving the null hypothesis is not evidence for your favored hypothesis. Bernoulli's argument was fallacious because all he did was show that the random hypothesis (the null hypothesis) did not explain the data well. That says nothing about Bernoulli's favored hypothesis of a single solar cause. So in this sense George is correct about Bernoulli, that "disproving" the null hypothesis is not evidence for the favored hypothesis. But this criticism does not apply to Bayesian statistics (or to likelihoodist and model selection methods). There is a rich history in Bayesian statistics of criticizing null-hypothesis tests. Bayesians consider null-hypothesis tests to be illogical. Bernoulli's error was that he never considered how well his favored hypothesis (a single solar cause) explains the data. Bernoulli's favored hypothesis could have even been worse than the null hypothesis, for all he knew. Or not all that much better. And this is the strength of the Bayesian methods I used -- with these methods, you have to explicitly calculate how well all the different hypotheses explain the data, not just how well the "null" does. In fact, in my methodology there is not even such a thing as a "random null hypothesis". And by calculating the probability of the observed data under each of the different competing hypotheses, you are in fact able to calculate the evidence for the different hypotheses -- the very thing George claims is impossible. That is exactly what Bayesian methods allow you to do, and it's why they have become so popular throughout science in the past 15 years. Cheers, Douglasdtheobald_{May 15, 2010
May
05
May
15
15
2010
05:17 PM
5
05
17
PM
PDT}

The money quote from Scientific American's Scientific American's summary of Theobald's paper:
By plugging these sequences into various relational and evolutionary models, he found that a universal common ancestor is at least 102,860 more likely to have produced the modern-day protein sequence variances than even the next most probable scenario (involving multiple separate ancestors).
10 to the 2,860th power!pelagius_{May 15, 2010
May
05
May
15
15
2010
04:59 PM
4
04
59
PM
PDT}

Cornelius, You seem to be making the following implicit argument:
1. Bernoulli used a statistical argument. 2. Bernoulli was mistaken. 3. Theobald is using a statistical argument. 4. Therefore, Theobald is probably mistaken.
The problem is easy to spot. Unless you can cite actual flaws in Theobald's paper, you have no basis for questioning his conclusions. Can you cite any actual flaws? You wrote:
I again explained that when one hypothesis beats out others you cannot make the claims you are making. What you have is very strong evidence that the hypothesis beats out the other hypotheses, period. You do not have very strong evidence for the hypothesis, as you are claiming.
If someone claimed that the evidence was overwhelming that the earth orbits the sun, would you reply as follows? When a hypothesis beats out others you cannot make the claims you are making. What you have is very strong evidence that the hypothesis that the earth orbits the sun beats out the other hypotheses, period. You do not have very strong evidence for the hypothesis, as you are claiming. The moment I saw Theobald's article, I knew there would be wailing and gnashing of teeth among creationists. Perhaps this is what Barry meant when he talked about "smacking into the wall of reality."pelagius_{May 15, 2010
May
05
May
15
15
2010
04:29 PM
4
04
29
PM
PDT}

You must be logged in to post a comment.

Leave a Reply