Raising the bar on statistical significance

Hasn’t John Brignel over at Number Watch been banging on about exactly this for years?

“The only proper standard for science is NO STATS. If a result has to be reached by statistics, it’s not a scientific result. Only well-calibrated measurements plus a well-balanced experiment can give scientific results.”
Nonsense. Many areas of science are inherently statistical. Chemical reactions for example, or quantum effects, or thermodynamics. The Second Law of Thermodynamics is entirely statistical in origin.

polistra says-
“If a result has to be reached by statistics, it’s not a scientific result.”
William Briggs, statistician to the stars, doesn’t go that far, but what he writes is still pretty damning-
“If you need statistics to prove something, and you have no proof except statistical proof, then what you have proved probably isn’t true. Statistical evidence is the lowest form of evidence there is. What a depressing conclusion.”
William Briggs, statistician, October 5, 2011

This seems like real non-news to anyone with a little background in statistics. It has always puzzled me that some branches of science seem content with p-values as high as 0.05!

[snip – stop trying to push your solar stuff on unrelated threads – Anthony]

Particle physicists don’t make claims unless the exceedance probability is over 6 sigma.

M Simon says:
November 12, 2013 at 4:23 am
“This is the reason so many nutritional findings are reversed. You know. Trans fats are good. Trans fats are bad. Soon to be followed by meat eating is banned. Too many natural trans fats.
The Atkins diet? There are problems.
A few small, short studies suggest Atkins raises HDL cholesterol and lowers blood pressure, reducing the risk of heart attack and stroke. But many of the studies were small and short, and some of the positive findings did not carry enough statistical weight to be trustworthy. And all that fat worries most experts.”
Well, maybe you should first point to a study that shows a correlation between fat consumption and heart attacks, without leaving out all data points that would destroy the correlation.
And please, the site you linked to says “The theory:The body is an engine; carbs are the gas that makes it go.”
Oh please. Ask any bicyclist on what fuel he runs most of the time. That site is a bad joke and misrepresents what they attack.
Atkins BTW has not invented the low carb diet.
http://www.lowcarb.ca/corpulence/corpulence_full.html

ss Since this is something of my game, I’ll summarize the idea. In Bayesian probability analysis, one rarely just states hypotheses. One states hypotheses based on various assumptions. Sometimes these assumptions are actually stated, sometimes they are not. Sometimes they are (in some rigorously defensible sense) true and sufficiently accurate beyond reasonable doubt — the assumption of Galilean or Newtonian gravity for near-Earth-surface physics problems — and sometimes they are basically little more than educated guesses with little or no solid evidence.
The simplest learning example of the latter is a coin flip. Suppose you meet up with a total stranger, who wants to bet you $1 a flip on 100 successive flips, and you get heads. You say to yourself “Hmm, a two sided coin, zero sum game, random walk, I expect to win or lose no more than $10-15 (with equal probability) and it will help to pass the time, sure.” You have intuitively used Bayesian reasoning. You picked a prior probability for a two-sided coin of 0.5 heads or tails, from symmetry and maximum entropy principles.
You didn’t have to. You could have said to yourself “Gee, a complete stranger wants to play a game of ‘chance’ with me with his coin, where he gets to pick heads for me. I’ll bet that he’s playing with a biased coin so that if I take this sucker bet, my expectation is to lose $100 or close to it.” This too is a Bayesian prior. You go ahead and take the bet anyway because you are bored and because you can count on proving that he cheated if the winning gets too lopsided.
They are also the basis for the null hypothesis — The coin has p(heads) = 0.5 or the coin has p(heads) = 0.0 respectively.
In traditional hypothesis testing, one assumes the null hypothesis, conducts an experiment, and determines the probability of obtaining the observed sequence given the null hypothesis. If you assumed p = 0.5 and the results of the first 8 flips were all tails, the probability of this outcome is 1/256 \approx 0.004. Based on additional prior knowledge you have (basically, the reasoning in the second case that it is unwise to gamble with strangers, especially with their cards, dice, coins) you might well have rejected the null hypothesis at the seventh flip or even the sixth. Since the bet is cheap, you might even go two more flips, but at the tenth flip you’ve already reached your expected win/loss threshold based on a random sequence of flips of an unbiased coin and the p-value is down to less than 0.001. Time to offer the stranger a counter-bet — using the same coin, for the rest of the bets you get tails and he gets heads OR nobody pays off and everybody walks away.
In Bayesian probability theory, one doesn’t reason exactly this way. Instead, one can allow the results of the experiment to modify you assertion of prior probabilities so that they basically asymptotically agree with the data however you start them out. Before the first flip your prior estimate of p(heads) is 0.5, but after a single flip — whether or not it comes out heads or tails — this is not true. If you get tails at the end of one flip, the probability p(heads) is strictly less than 0.5, and it montonically descends with every sequential flip of tails.
This approach (really, no approach) is going to be particularly reliable with only five or six flips because (in the words of George Marsaglia, a giant of hypothesis testing and random numbers) “p happens”. If you conduct many such experiments, not only will sequences of six tails in a row occur, but they’ll occur one in sixty-four randomly selected sequences of six coin flips, even if the coin is unbiased!
This is precisely the kind of reasoning that is not being conducted in climate science. In part this is because it is a house of cards — if you knock a single card loose on the ground floor, you risk the whole thing tumbling down. The list of (Bayesian prior) assumptions is staggering, and in the case of many of them there is simply no possibility of directly measuring them and setting them on the basis of direct empirical evidence, or there is some evidentiary basis for a number, but there is a rather wide range of possible/probable error in that number.
This multiplicity of Bayesian priors has the following effect. It becomes quite possible to obtain good agreement with a limited sequence of data with incorrect prior assumptions. This, in turn, means that limits on p have to be made more stringent. If one uses the coin metaphor, an additional (unstated) Bayesian prior assumption is that it is possible for you to detect it if your opponent switches coins! Of course, your opponent in addition to being a scoundrel could be an unemployed magician, and swapping coins “invisibly” could be child’s play to him. In that event, he might play you with a fair coin for the first ten or twenty throws, allowing you to conclude that the coin is a fair coin, and then swap in the unfair coin for a few throws out of every ten for the rest of the way. You end up losing with complete certainty, but at a rate just over the expected win/loss threshold. He makes (say) $20 or $25 instead of $100, but he kept you in the game until the end because you could have just been unlucky with a fair coin and you had direct evidence of apparently fair sequences.
In more mathematical theories the same thing often happens if you have nonlinear functions with parametric partially cancelling parts contributing to some result, function forms with a lot of covariance. One can often get good agreement with a segment of data with a mutually varying range of certain parameters, so that any prior assumption in this range will apparently work. It’s only when one applies the theory outside of the range where the accidental cancellation “works” that the problem emerges. Once again naively applying a hypothesis test to the range of data used to justify a Bayesian assumption of parameters is completely incorrect, as is applying the assumption to a naively selected trial set, and the requirements for passing a hypothesis test at all have to be made much more stringent in the meantime to account for the lack of evidence for the Bayesian priors themselves. The evidence has to both agree with the null hypothesis and affirm the prior assumptions, and to the extent that it has to do the latter without outside support it takes a lot more evidence to affirm the priors in the sense of not rejecting the null hypothesis. You have many “and” operators in the Bayesian logic — if the primary theory is correct AND this parameter is correct AND this second parameter is correct AND this third parameter is correct, what are the chances of observing the data — and the computation of that chance has to be diluted by accounting for all of the OTHER values of the prior assumptions that might lead to the same agreement with the data but effectively constitute a different theory.
And then there is data dredging, which is very nearly another version of the same thing.
So when there are 30+ GCMs, each with dozens of parameters in a complex theory with many countervarying nonlinear contributions, that are in good agreement with an indifferently selected monotonic training set of data, that is not yet particularly good evidence that the theory is correct. The real test comes when one applies it to new data outside of the training set, ideally data that does not conform to the monotonic behavior of the training set. If the theory (EACH GCM, one at a time) can correctly predict the alteration of the monotonic behavior, then it becomes more plausible. To the extent that it fails to do so, it becomes less plausible. Finally, as theories become less plausible, a Bayesian would go in and modify the prior assumptions to try to reconstruct good agreement between the theory and observation, just as you might change your prior beliefs about the fairness of the coin above, if you start seeing highly improbable outcomes (given the assumptions).
It is this latter step that is proceeding far too slowly in climate science.
rgb

I don’t understand. P=.05 should mean that the null hypothesis is correct only 5% of the time. How does this turn into error rates of approximately 20% — supposing that biases are accounted for?
What is the basic idea that changes 5% to 20%?

Jim Rose says:
November 12, 2013 at 7:19 am
What is the basic idea that changes 5% to 20%?
=======
You have 100 people in a company, of which 5 are actually using drugs. You employ a drug test that is 95% reliable. It will deliver 5 false positives. There is a 50-50 chance that someone identified as using drugs is actually using drugs.
You believe your test will be 95% accurate, but in fact 50% of the time it incorrectly identified the drug user. Since you don’t know there are only 5 drug users, when the test tells you there are 10 drug users, you believe the test. 5 innocent employees get fired along with the 5 guilty.
100 scientists conduct studies, of which 5 produce real positives. At the 95% significance, 5 produce false positives. Only the positives get published, as negative results do not attract attention. 5 true positive along with 5 false positives. 50% of the published papers are false.

Jim Rose: I don’t understand. P=.05 should mean that the null hypothesis is correct only 5% of the time. How does this turn into error rates of approximately 20% — supposing that biases are accounted for?
What is the basic idea that changes 5% to 20%?
The p-value is an estimate of the conditional probability of a result at least as far from the observed prediction given that the null hypothesis is true. Only rarely would that result in 5% of the true null hypotheses being reported true, or the literature only having false rejections of the null hypothesis in 5% of published papers. What changes the 5% to 20% (speaking loosely) is the fact that the null hypotheses are actually true (or at least very accurate) more often than the researchers expect them to be.
The proposal in the focus paper and the reasoning behind it are not that new. The debate about what significance level to use is probably at least a century old now. The penalty for insisting on low p-values is a higher than desirable rate of false non-rejection of false null hypotheses, aka “high rate of type ii errors”.
What has to be recognized is that single reported studies, without replication, are not as reliable as you would like them to be. That is not a problem solved by adopting smaller p-values, but by a deeper appreciation of the prevalence and size of random variation (the agglomeration of all the variation than is not directly relateable to the focus of the study and measurable covariates.)

ferd berple says:
November 12, 2013 at 7:14 am
“…climate science rejects chance as the cause. Of this they are 97% certain.”
Well said.

Nice explanation of applying Bayesian statistics to the flip of a coin. There is one huge difference between your example and the use of statistics in climate science. In your example, the statistician knows what the event space is. The event space consists of readily observable and readily definable physical phenomena, namely, flips of the coin. Climate science does not have the luxury of a readily observable or readily definable event space. Permit me to illustrate by reference to Michael Mann’s work on tree rings. What is (was) an event for Mann? It was the measurement of the width of a tree ring. For Mann, a series of events that together make up a proxy record consists of measurements of tree ring widths for the same kind of tree taken from trees scattered about the surface of the Earth. Does that count as a legitimate event space? Clearly not because tree ring growth is not determined by the tree but by the ever changing environment in which the tree grows. Did Mann investigate the several environments in order to establish readily observable and definable phenomena? Not in the least. All he did was a little hand waving to the effect that the sample trees were pretty much located at the the tree line (on mountains of course).
The usual Alarmist response to my point is that all the differences among the samples can be accommodated through powerful statistical techniques. This response does not climb above childishness.
I have “attacked” the soft underbelly of climate science by using Mann as my example. But the same is true throughout climate science. Climate scientists sometimes talk about heat content and sometimes talk about temperature measurement and they make the egregious assumption that the two are interdefinable. Climate scientists sometimes talk about temperatures taken in the atmosphere and sometimes about temperature taken on the surface or beneath the surface of the oceans. To summarize, climate scientists are the only so-called hard scientists now practicing who are quite willing to take any two series of measurements and assume that they are comparable. The worst offenders are the “paleoclimatologists” who are quite willing to take 50 existing “paleo” series and treat them as comparable while giving no thought to the actual events of measurement that occurred at some time in some readily observable and definable environment. Most climate scientists have no idea what their event space is.

While Bayes’s theorem is correct, Bayesian parameter estimation generally suffers from the lack of uniqueness of the prior probability density function with consequent violation of Aristotle’s law of non-contradiction. In particular, the method by which climatologists extract numerical values for the equilibrium climate sensitivity (TECS) from global temperature data violates non-contradiction.
There is an exception to the rule that Bayesian methods violate non-contradiction. It occurs in the circumstance that a sequence of events, for example a sequence of coin flips, underlies the model. In this case, the so-called “uninformative” prior probability density function is unique and non-contradiction is not violated.
However, no events underlie the IPCC climate models. In setting up this state of affairs, climatologists have ensured that the conclusions of their arguments violate non-contradiction. Rather than being one value for TECS, for example, values are of infinite number.

rgb
Nice post

@ polistra says:
November 12, 2013 at 4:28 am
“Stats can’t be saved by tweaking. The only proper standard for science is NO STATS. If a result has to be reached by statistics, it’s not a scientific result. Only well-calibrated measurements plus a well-balanced experiment can give scientific results.”
In fact, a number of scientific disciplines are observational and are unable to reach direct results by experiment. Major examples: astronomy, paleontology, evolutionary biology, Some of their findings are “consistent with” some experiments done in another context, but most of their findings are not reached through experimental methods. Of course, observational sciences still require careful measurements, and thus the other condition set by Polistra (well-calibrated measurements) generally applies, although one has to be careful about the basis for calibration (cf climate models calibrated to the rapidly warming 1970-2000 period).

Mike Maguire says:
November 12, 2013 at 7:55 am
“Why Most Published Research Findings Are False ”
See also Sturgeon’s law
http://en.wikipedia.org/wiki/Sturgeon%27s_law

Where is the damn like button, +, whatever on the comments. There is a nice list above of people who get it. I was watching a show about angels a long time ago. A person came on and said, “I fell through the ice, an angel appeared and said, ‘Go this way’, and I followed her advice and found the hole to get back out!”
My wife said … “What about all the people who fell through the ice and saw the angel and followed their directions and didn’t get out!”
This exactly corresponds to the “One tree in 1000 matches temperature better!”
This why you look at the absolute value of data and do not get too enamored of Anomaly Data. If the anomaly data lets you make accurate predictions on the unknown, awesome. Keep that absolute chart posted next to you though to remind you of the underlying magnitudes.
The inverse of Risk Ratio is Survivability Factor. Even with smoking, the survivability of smoking and lung cancer is 92% over 60 years. There is a 92% chance you won’t get lung cancer.

“This approach (really, no approach) is going to be particularly reliable with only five or six flips because …” — rgbatduke @6:45
rgb wrote a great bit on this, but it is distinctly different from what the paper is proposing. The papers stated problem, and its proposed solution, is to singly publish more papers that are reproucible.
Without reproducing them.
This is absurd in the first order, for if you make one mistake, one deceit, or one oversight, one bad choice with outliers and otherwise cleaning your dataset, with one paper: You have flipped the coin exactly once. To flip the coin five or six times you need to repeat the exact experiment of the paper, another four or five times.
Bayesian notions are pretty clever and terribly interesting: And point out exactly why experiments that are not replicated are nonsense. But this paper is precisely about non-replication. Faith, Trust, whatever you like. But it’s a misplaced solution.

Great issue. A probability estimate, a “p” level, is derived internally – based on the data of the study, only. It therefore cannot be any sort of statement about the world outside of that data set.
A p value only helps contribute to the evaluation of how convincing the study outcome is.
The problem is that some people value it for more than that.
Bradford Hill, instrumental in fingering tobacco smoking as a cause of lung cancer, has his well-recognized 1965 paper on “Association or Causation?” He gives the well-recognized criteria for helping assess observational data. “Statistical likelihood” is not in that list of nine aspects, and is briefly mentioned and put well in its place toward the end of the article.

tumetuestumefaisdubien1 says: @ November 12, 2013 at 7:36 am
I don’t believe raising thresholds much helps and I don’t believe 0.005 or 0.001 levels are needed for avoiding bad science.
In fact such a conclusion that raising thresholds to such levels will mean better science looks to me more insane than logical….
>>>>>>>>>>>>>>>>>>>>>
You should be doing what we did in QC. (This depends of course on the cost of the item and the cost of the tests.)
Taking ferd berple’s example of drug testing.
The sample from each person gets split before testing. Part of the sample is used for testing the rest is retained. You know that out of the ten who tested positive approx. five maybe false positives. You then use the more expensive but more accurate test to retest the retains for all ten to confirm the positives. (Splitting the sample is what is done for drug testing truck drivers.)
In science it is independent replication usually by at least two independent labs. If it can not be replicated it gets tossed into the dustbin of history.
I see no reason to change this but the confirmation testing by an independent lab or two or three is an absolute must and this is what is missing in Climate Science.

John Brignell. A tribute to John Daily (still waiting for greenhouse)
http://www.john-daly.com/
“Most of his admirers around the world never met him, but nevertheless held him in great esteem, simply on the basis of his writings. Forget all the pornographers, mass mailers and virus producers; one Daly is sufficient justification for the existence of the World Wide Web.”
Daly,McKitrick, McIntyre, Pielke, Watts, ……..

M Simon says: “This is the reason so many nutritional findings are reversed. You know. Trans fats are good. Trans fats are bad. Soon to be followed by meat eating is banned. Too many natural trans fats. ”
Often true. Another problem is the problem of the “healthy user” benefiting from the “healthy user effect.” People who TEND to do things that are believed to be healthy also TEND to do other supposedly healthy habits. They will, overall, reap benefits of what really contributes to a long, healthy life – probably regular exercise, a decent diet, and good stress management in the face of life’s slings and arrows via economic stability and or social relationships.
So, a behavior can have a somewhat BAD influence, but in some longitudinal study, be mathematically seen as healthy. The healthy habits carry the day, and the bad habit is a fellow traveler.
The extreme is the now-well-recognized reversal of hormone replacement therapy from being preventive of heart disease to being a predictor of heart disease: health-conscious women accepted and sustained their hormone prescriptions, until a randomized controlled trial tested this with much less ‘healthy user’ bias.

Regarding Mann: assuming he did everything properly, his model in the end is not quite scientific. And no forecast or estimate of the future ever can be. Likewise, it will be quite a day when “evolution” is scientifically confirmed.
In the long run, science depends upon making an a priori prediction, specifying a disprovable test of that prediction, then gathering that actual evidence to observe whether the prediction is accurate or not. We do not know what will happen in the future. A predciton can be based on some good science, but a prediction of what the future will be like can never be observable – until it happens, at which time it is no longer the future. So, patently, a prediction cannot quite ever be “confirmed,” or “scientiftic” in the way other things can be scientific facts.
Beyond micro-evolution, evolutionalry theory suffers the same weakness. We will never see the cow-like animal again adapt itself back to underwater life as the whale-like animal. Evolution of the various species makes sense, and has a lot of evidence to support it, but it is not observed. If our species pays attention and keeps record long enough, say, a million years, sure, we might observe a new species emerge from recognized species. But we have not yet.

Bill Marsh at 4:42 am: +5 “Numbers are like people…” Made my day!
chris y 5:05 am, +1 briggs quote.
Bill Illis 5:17 am, +2 The only statistics that count: $$$$. +2
rgbatduke 6:45 am +1 Always worth a read (and reread).
MCT 6:53 am +1 statistics (physics, causal) vs. stocastics (climate, corelatvie). I like the concept.
Jquip 9:31 am, +1 But this paper is precisely about non-replication.
Brad Tittle 9:16 am “Where is the damn Like button, + ?” Do it yourself. 😉
Gail Combs 9:53 am +1 Independent confirmation testing/splitting.

Gail Combs says:
November 12, 2013 at 9:53 am
“Taking ferd berple’s example of drug testing.”
Drug testing of employees is not science and anyway a drug test which has 95% confidence is a screening cheap crap which anyway needs retest in case of positive in any case.
“In science it is independent replication usually by at least two independent labs. If it can not be replicated it gets tossed into the dustbin of history.
I see no reason to change this but the confirmation testing by an independent lab or two or three is an absolute must and this is what is missing in Climate Science.”
Confirmation is matter of church, not science.
The point in science is not confirmation, replication, the point is falsification. If something is confirmed than good, but if not, then it actually belongs to the dustbin of history. The point of scientific method is falsifiability (a hypothesis which is not falsifiable, is not scientific hypothesis by definition). If a claim, for example “man is responsible for global warming, because we made model XYZ123, tuned it and it shows he is and we predict temperature rise with it this and this” is a dangerous claim in science – because immediately the reality shows that the temperature is significantly not following the model, the model is falsified and belongs to dustbin of history. You actually don’t need anything like “confirmation” for it.

In climate ‘science’ the only effect that rising the statistical bar will have is for more run time on the computers to ‘ensure ‘ they get the results ‘required ‘
Its simple really , start with what your ‘results ‘ then produce the ‘data’ that supports them.

You mean you want us to run more simulations with the same model, or set of models, to bring those error bars in tight? I hear you man! That’s why we are writing a grant proposal for $1 bn more computing power – so that we can report the output of our models to even more decimal places. Hopefully more decimal places will make our simulations better because we do not know the difference between accuracy and precision. [/sarc]

is this method similar to what the epa did with the meta study on second hand smoke? the studies found NO significant stat correlation so they altered what is significant to claim there was??

‘Some do not care for the inference. They may (or may not) have a point.’
It is not an inference; it is just that in cases of slowly reproducing species we can observe only smaller changes over the same amount of time. The extent of evolution directly observable is less.
The question is not whether species evolve. By their very characteristics as living organisms, they must and they do. It is a mathematical certainty. The question is whether evolution explains all of the biological variation we see around us.

Here is a fascinating article about genuine scientists producing results which are initially reproducible, then later are not!

The New Yorker – December 13, 2010
The Truth Wears Off
Is there something wrong with the scientific method?
by Jonah Lehrer
“Unfortunately, I couldn’t find the effect,” he said. “But the worst part was that when I submitted these null results I had difficulty getting them published. The journals only wanted confirming data. It was too exciting an idea to disprove, at least back then.” For Simmons, the steep rise and slow fall of fluctuating asymmetry is a clear example of a scientific paradigm, one of those intellectual fads that both guide and constrain research: after a new paradigm is proposed, the peer-review process is tilted toward positive results. But then, after a few years, the academic incentives shift—the paradigm has become entrenched—so that the most notable results are now those that disprove the theory….”
[Page 3]
“…The problem of selective reporting is rooted in a fundamental cognitive flaw, which is that we like proving ourselves right and hate being wrong. “It feels good to validate a hypothesis,” Ioannidis said. “It feels even better when you’ve got a financial interest in the idea or your career depends upon it….”
[Page 4]
“…Even the law of gravity hasn’t always been perfect at predicting real-world phenomena. (In one test, physicists measuring gravity by means of deep boreholes in the Nevada desert found a two-and-a-half-per-cent discrepancy between the theoretical predictions and the actual data.)….Just because an idea is true doesn’t mean it can be proved. And just because an idea can be proved doesn’t mean it’s true.”
[Page 5]

milodon: “I don’t know how the myth persists that speciation has not been observed.”
Yeh, you know. I didn’t say ‘speciation’ and detailing all the sophist redefinition and name-changing about ‘evolution’ and ‘species’ is about as thoroughly voluminous as the same treatments for Anthropogenic Global Warming, I mean Climate Change, sorry, I mean Climate that isn’t changing. And is not changing due to Natural Causes er… Water vapor feedbacks, nuts. I mean it’s been proven that it’s humanity. So fast… I mean it’s obviously the Koch brothers. And not only is it as stupid and voluminous; it’s almost guaranteed to be religious (like Cllimastrology) but off topic. But hey, if you can’t make your error bars big enough, undefine your words.
Point is, inferences that go backwards in time are in every case invalid. It’s pure pro causa non causa. And the only validity to an inference that goes forward in time is that we have validated it enough — observationally — that we can get it some inductive assurety in future uses.

Second to last sentence should begin, “That is purportedly …”

JEM on November 12, 2013 at 11:25 am
@John Whitman on November 12, 2013 at 9:15 am

– – – – – – –
JEM,
Thanks for your comment.
I think ‘helicoptered in’ has some plausibility given that the nature of peer review does not prevent it per se. If peer review process documentation were publicly available after the peer review process completes, then science could correct itself more efficiently than it currently does.
John

10 thousand Olympic athletes are tested for drug use with a test that is 99.99% accurate. what are the odds that an athlete identified as a drug user is a drug user?
50-50, even odds. One (very likely) true postive, one false positive. One reason that physicians should not give everybody that walks through the door a full spectrum of tests, especially for low prevalence conditions. If prevalence is one in 10,000, and you test everybody with a test that has a 1% false positive/negative rate, (99% accurate, as it were) you’ll get 1% of 10,000 or 100 false positives and one true positive 99% of the time (you’ll actually MISS that true positive 1% of the time, sigh).
Nearly all of the 100 people identified will be false positives, and you’ll have to do infinitely more tests, spending infinitely more money, to weed out the false positives and find the one lonely true positive. Not enough insurance money in the world… not to mention spending weeks thinking you might have brain cancer when you don’t. That’s why physicians have to have OTHER reasons to suspect a low-prevalence condition before they give you a test for it. The other reasons “promote” you from a Bayesian prior of randomly selected from a low prevalence base population to a much more refined population of people that actually exhibit symptoms for the disease AND have the disease, which ordinarily will have a much higher prevalence. Maybe enough to get to even odds.
And good examples, BTW, especially the data dredging example. I didn’t do this (prevalence) particular example and probably should have. I also like the “Let’s make a deal” example to illustrate why additional information changes the prior odds.
On the Lets Make a Deal show, one would often select (say) door number three in hopes of winning the Carribean Vacation package. Before showing you what was behind door number three, Monte opens one of the remaining two doors (say, door number one) to show you that it contains the barbecue set worth a whopping $150. He then asks if you want to change doors to number two before he opens them.
If Monte either always does this, or randomly decides to do this without being influenced by whether or not door three contains the big prize, the answer is “yes”. You improve your chances of winning if you switch to door number two, because you can take advantage of the additional knowledge associated with knowing that door one didn’t contain the prize in the second pick. Proving this is an entertaining exercise. But kind of irrelevant to hypothesis testing…
rgb

Gail Combs says:
November 12, 2013 at 1:51 pm
“I disagree, but then I worked in industrial chemistry. If a new reaction or method can not be duplicated by others it gets tossed. Think Fleischmann, Pons and Cold Fusion.
I should not however have used ‘confirmation’ when I meant verification and validation.”
I’m quite not sure Cold fusion has anything with chemistry or rather even whether it has to do with anything. Verification in science purely means to inequivocally set criteria for a hypothesis or theory to be true or false and then test whether the hypothesis or theory passes the criteria or not. Validation means assesment whether a scientific method is suitable and adquate for a defined purpose or not or in the case of mathematical modeling, whether the output of the model fits the observation or not and quantification of difference for deciding whether the model is or isn’t falsifiedl. So I quite still don’t completely understand what you’re talking about.
Independent replication of some scientific results is of course good if somebody does it, but somebody tries something like that only if the original claim is plausible, well supported and the independent researcher has a motivation to look into the issue. Otherwise nobody of course bothers. Definitely not in basic research.
For example: some credible reputable solar scientists published a claim that according to recent data from certain satellite some bands of solar spectrum vary not in phase with solar cycle. And because it looked interesting and plausible when one briefly checked the data and could have interesting implications if true I decided to replicate their results. And after month or so of work I indeed found that in some important bands indeed the solar activity consistently doesn’t variate in phase with solar cycle, moreover I’ve found additional facts, which have likely broad implications and aren’t in any sense part of the original claim – which paradoxicly all relates to the fact, that in other band, where they also claimed the same peculiar variation I’ve found that the data contain clear outliers which spoil the slopes and when taken out the peculiar variation artifact disappears. So partially I replicated some of the original results and partially I also falsified other, but the combination of the sucesful replication of one claim and failure to replicate the other together imply something yet different which is worth of further examination, because it not only means the replication of one and falsification of other claim, but in complex could mean a potential falsification of whole theory of the solar variation and its relation to earth insolation. Science is often history of accidental finding of something when looking for something else, because simply what we don’t know we can’t anticipate to find. So often also the falsification of some previous claim means not only tossing it in the dustbin of history, but also finding something else, sometimes much more interesting that what was falsified and that’s why even it could look destructive for a layman the principle of falsification in science is the way to the truth not only byl elimination of untrue, but also finding the new implications of it not be true.

rgbatduke: ” But kind of irrelevant to hypothesis testing….”
Contrary, in fact. As you already know how many doors, how many goats, and how many sports cars there are. But in the false positive condition you’re asking for people to be properly analytical rather than improperly analytical. But this still doesn’t inform you of whether or not you had zero drug users in fact, when you found 2 or 3 by test. After all, if the suspecting people aren’t terribly good at it, then they’ll only test the drug-free in the first place.
Quite strictly,there’s nothing wrong with hypo testing by statistics. But you cannot be demonstrating it on edge cases, outliers, or miracles. Or you’re simply lost in every case.

Deirdre McCloskey has been decrying the Cult of Statistical Significance for decades. Here is her book:
http://www.amazon.com/The-Cult-Statistical-Significance-Economics/dp/0472050079

Those of us who studied the non-belief-based sciences have usually been taught how to recognise appropriate statistical techniques. But we were warned not to try it ourselves for real research. Rather to get a specialist Statistician on the job. Sciences like Climate and Nutrition have shown the stupidity of doing otherwise. Brett Keane, NZ

milodon: You seem to be struggling still with what I believe, rather than what the question is. So just assume I’m a true believer of evolution and already know these things. The question isn’t biology or geology: It is what makes the *form of inference* valid. Because it is absolutely certain that our wishes for the topic cannot. Lay down the rules for what makes the argument valid.

Since some of the comments have strayed into the medical lab (where I’ve worked for 25 years) I thought I would throw in a couple of semi-relevant comments. In the lab the terms “95% confidence level” and “accuracy” are both important, but very different. There seems to be a little mixing of the two. For quantitative tests our quality control samples (run at least 3 times per day) must yield results within 2SD of the mean, or corrective action must be taken and documented. For us this statistical 95% level means we can be 95% certain that any deviation from the “true” level of the analyte is caused by randomness in the testing process (equipment, operator, reagents) rather than error such as malfunction, operator error, or contaminated reagents. Accuracy is related but refers to the correctness of the result. In Qualitative tests (pos/neg) such as drug screens (they can also be quantitative, but usually not) I’m pretty sure the accuracy rate is much higher than 95%. I doubt if a test procedure with accuracy that low would ever be approved for use. Usually “false positives”, which are usually interfering substances such as medications, can be sorted out through patient history and confirmation/verification using other methods without certain interferences. I’m certainly no expert on drug testing, I would guess the incidence of people being said to have a drug in them that was not there is much less than 1%. ( I know these are just examples people are using, but it seems as if there is some idea that they are real) I do wholeheartedly agree with rgb@duke about overtesting. There is a huge amount of overtesting. Mostly I think due to defensive medicine and partly due to convenience. I guess this doesn’t have much to do with Bayesian theory (which my basic statistics class did not include), but I have always suspected that statistical significance was somehow being misused.

Milodon sez: “There is no magic genetic barrier that keeps one species from evolving into a new one, given selective pressure to do so or simple reproductive isolation. The processes can be & have been observed all around us.”
Well, there is. At least, as far as I was taught in high school. We learned about sexual reproduction. The chromosomes line up in their pairs, then pulled into two complementary sets, then the cell splits in two, with a set in each cell, if all goes well, and you have two gametes (sorry to get technical with the language); you get a cell that has only half of the otherwise paired set of chromosomes.
A new member of the species results if a male gamete and a female gamete meet and combine, and their half-sets of DNA are able to match up. The resulting double-strand DNA then gets unzipped when and where necessary so that one of the strands can code for proteins. And so on.
If the genes don’t match up one-to-one, all of this may fail. If the chromosomes don’t line up, one to one, then all of this may fail.
So, a puzzle is: how does a gene get added to a strand of chromosome, and find a complementary gene in an opposite-sex gamete, allowing this process to carry on, with the newly added gene?
In short, how do genes get added?
I appreciate the frequent use of the term “assume,” and like terms, in milodon’s comments, making the case for me, that these building blocks of evolutionary theory/of speciation are based on logic and reason, and not on science.
[ ] I will; have to look into these bacteria that have a nylon fetish – if they can reproduce with the original bacteria, I might not consider them a new species.
[ ] conducting generations of reproduction and getting an organism that uses a new energy/food source may not necessarily be proof of a new species. The ability to eat nylon either was latent, and was made prominent by micro-evolution, or was a capability added by a genetic mutation or mutations that carried forward. A site mutation or mutations that has some advantage, but where the genes and the chromosomes can still be described, and replicate, the same way, may not be the same as the theory that explains where new species come from. If the genes are arranged the same way, and the chromosomes also, then it sounds like the same organism.
Great interest is being paid to humans that ought to be suffering from HIV, but are not. They are humans. A wildly rare, latent trait may be being expressed. The organism is still Homo sapiens.
[ ] It could be argued that producing a new species in the lab is proof of intelligent design, not natural selection: it takes quite a lot of purposeful intellectually-guided action to produce that new species. Sure, it helps make the case. The examples of this supposedly happening “in the wild” would be observable evidence of natural selection as the mechanism for the great variety of species we see, with their quite varying number, and pattern, of genes and chromosomes.

“I was trying to understand what your objections are to the scientific method. What makes a “form of inference” valid has long been known & used with huge success. First, the inference needs not to have been shown false. Second, it should enjoy support from other lines of evidence or new observations along the same line. Third, it should explain observations better than any competing hypotheses.”
Logic and reason are great tools to use to strive to test claims of knowledge. Inference is a matter of logic and or reason.
Logic and or reason is not the same as the scientific method. Logic/reason, combined with empiricism, by using a priori predictions to be supported or disproven by empiric observations, is science.
Proper inference is great, but is not, itself, “science.” Macro-evolution is, for the most part, very reasonable. Many great arguments can be made.
Arguments can also be made that increasing anti-oxidants will keep me safer from cancer, and that massive doses of vitamin C will keep me safe from a rhinovirus. Until we set up an a priori, disprovable test, then go conduct the test, then if successful hope that others can replicate it, these are just compelling, reasonable arguments.
I make a big point about this partly because our school kids have no ability to evaluate scientific claims – they are not being taught this properly. They are instead being taught another strategy for ascertaining knowledge: not logic/reason, not science, not empiricism, but the Edicts from The Authorities. Ninety Five Percent of all credible scientists are apparently telling my children that man-made global warming has put us on the brink of calamity. “Science” is that which is consensus of the popular scientists.
In the old days, people studied rhetoric, debate, logic (deductive and inductive), science, and natural science.
Nowadays, ask a college kid what rhetoric is. Ask how “science” is the same as or different from “natural science.” Ask them to define a debatable issue, and provide arguments for both sides, with rebuttals. Ask them to note the difference between deductive and inductive logic.
They likely will not have answers to these questions. By “answers,” I mean accurate answers. People need to be able to recognize the difference between a pronouncement from an august panel, a logical argument, and a scientific test.

One of the interesting things about the concept of species is that there are so many of them. There is, in fact, to use Sterelny and Griffiths’ words, a flock of species concepts:

* Phenetic species concepts define species by appealing to the intrinsic similarities between organisms. The idea is to purge species identification of theoretical commitments.
* Biological species concepts define species by appealing to reproductive isolation. One version of the biological species concept is the recognition concept, which defines species as systems of mate recognition.
* Cohesion species concepts generalise the biological species concept by recognising that gene flow is not the only factor that holds one population together and makes it recognisably different from others.
* Ecological species concepts define species by appealing to the fact that members of species are in competition with one another, since they need the same resources.
* Phylogenetic and evolutionary species concepts define species as segments of the tree of life. A species is a lineage of organisms, distinguished from other lineages by its distinctive evolutionary trajectory, and bounded in time by its origin in a speciation event and its disappearance by further speciation, or extinction.
[From Sterelny and Griffiths Sex and Death p 193]
It would be surprising indeed if all of these disparate ways that biologists view species produced agreement on which organisms were members of which species.

Milo, you say you are a lumper, rather than a splitter, yet you refer to the Galapagos finches as an example of separate species. You also refer to ring species as an example of speciation in action. Since the reproductive isolation here is based on mate recognition, then I imagine we can then refer to Bob Brown and his partner as separate species 😉 Dandelions and culinary garlics are examples of species that are reproductively isolated because there is no possibility of sexual exchange of genetic material between each other. If this garlic plant cannot exchange genetic material with that garlic plant over there why aren’t they separate species? “They can’t produce fertile offspring” yet they are members of the same species. There are animals, such as certain salamanders that fall into the same category.
I suspect that this line of discussion while very interesting, has little to do with the head topic.

@ milodonharlani
More than happy to discuss what science is and isn’t, but again it’s not about the head post topic. I have been meaning to finish an essay on science and submitting it to Anthony but haven’t managed to get a round twit. I have, however, managed to affix automatic vent openers to the vents in my greenhouse. Now I don’t have to race in and out of the house on showery, partially clouded days. I am calling this the enhanced greenhouse effect. And that’s OT for this thread, too 🙂

Re Intelligent Design, I can do no better than quote physicist Paul Davies:

“Scientists are slowly waking up to an inconvenient truth — the universe looks suspiciously like a fix. The issue concerns the very laws of nature themselves. For 40 years, physicists and cosmologists have been quietly collecting examples of all too convenient “coincidences” and special features in the underlying laws of the universe that seem to be necessary in order for life, and hence conscious beings, to exist. Change any one of them and the consequences would be lethal. Fred Hoyle, the distinguished cosmologist, once said it was as if “a super-intellect has monkeyed with physics”.
To see the problem, imagine playing God with the cosmos. Before you is a designer machine that lets you tinker with the basics of physics. Twiddle this knob and you make all electrons a bit lighter, twiddle that one and you make gravity a bit stronger, and so on. It happens that you need to set thirty something knobs to fully describe the world about us. The crucial point is that some of those metaphorical knobs must be tuned very precisely, or the universe would be sterile.
Example: neutrons are just a tad heavier than protons. If it were the other way around, atoms couldn’t exist, because all the protons in the universe would have decayed into neutrons shortly after the big bang. No protons, then no atomic nucleuses [sic] and no atoms. No atoms, no chemistry, no life. Like Baby Bear’s porridge in the story of Goldilocks, the universe seems to be just right for life.”

milodonharlani says:
November 13, 2013 at 12:01 pm
“Intelligent Design, like CACA, is not just unscientific, but anti-scientific, & for the same reason.”
CACA as you call it has been created by the UN together with all the Green NGO’s; so I guess it’s not the same reason.
“ID advocates look at flagella in bacteria & are happy to throw up their hands & give up, saying, “These structures are irreducibly complex, so couldn’t have evolved, therefore a Designer made them.””
It doesn’t help your case to overgeneralize; in fact I have not the slightest problem with macro-evolution. I also have no problem with an interfering God, as that is not a contradiction at all.
Well, it’s getting late here in EU territory; it was fun to talk to you. Good night and take care.

@ milodonharlani
First, I quote Theodosius Dobzhansky: “Nothing in Biology Makes Sense Except in the Light of Evolution”. In the world I inhabit, NeoDarwinism = the Modern Synthesis = The Received View in Biology. Biology has scientific laws just as other disciplines. Most theories invoke those laws. Live with it.
It is not I who confuse Intelligent Design with creationism. There is a world outside the USA that does not accept as Gospel Truth everything that comes out of the USA. Or anywhere else for that matter. I don’t give a fiddler’s fart that creationists attempt to own a term; they don’t.
I’m currently rereading Ernst Mayr’s One Long Argument. The first sentence reads: “A modern evolutionist turns to Darwin’s work again and again.” Why does using the term “evolutionist” make me a creationist and not Mayr? I know you haven’t gone that far, but many have. And you have taken me to task for using it.
The chapter I’m reading is titled, incidentally: A Hard Look at Soft Inheritance: Neo-Darwinism. See above.

@ milodonharlani
I’m not at all sure why you would think that the laws of biology do not apply to Neo-Darwinism. It’s too silly to argue about.

@ milodonharlani
Of course we can expect Kevin Kelly to know all this stuff backwards… And it’s kinda handy, I suppose, to distract as much as possible from directed evolution which was the point of Kelly’s piece 🙂 Evolution’s all really, really, really random; like over 30 distinct species of plants acquiring the same gene complex (C4) virtually simultaneously. No need to explain that stuff.
BTW how long have Mendel’s laws not been part of the Modern Synthesis? They were the last time I looked.

@ milodonharlani
Fearlessly plagiarised and adapted from a piece I wrote several years ago:
The Git has a bit of a bee in his bonnet about random mutation being the cause of macroevolution that is the core of NeoDarwinism. Merely having a gene mutate gradually into some other gene won’t do. If the gene has an important function for the organism it inhabits, then the organism would suffer from the disappearance of that function. Ohno’s Hypothesis has it that the gene must first be duplicated and the duplicate gene then proceeds to mutate into the new gene with the new function. During the period of mutation, the gene is not expressed (and is therefore not subject to Natural Selection), but at some random point in time becomes expressed. For example, a plant that previously utilised the C3 photosynthetic process, overnight as it were, gains the C4 photosynthetic process and is a new and distinctly different species. So the story goes, some thirty odd plant species virtually simultaneously and randomly discovered the C4 process in the blink of an evolutionary eye.
This argument bears more than passing resemblance to the stories The Git read when he was a tadpole. At the end of an episode in The Wizard, Fearless Dick would be helplessly bound by fierce African natives looking forward to a bit of white flesh for supper. At the beginning of the next episode, one would read: “With a bound, Dick sprang free!”
This does not make the Ohno Hypothesis wrong, merely less probable. It would help, of course, if there were any evidence to support it. Despite the reputed abundance of gene duplication, The Git’s searches have turned up no evidence that macroevolution works in this way. Here’s some evidence about what does happen from Nature:

Adaptive evolution of bacterial metabolic networks by horizontal gene transfer
Csaba Pál, Balázs Papp & Martin J. Lercher compared the genome of E. coli with those of its closest relatives. “Under realistic parameter settings, we estimated that 15-32 genes were transferred horizontally into the E. coli metabolic network since its divergence from the Salmonella lineage, vastly outnumbering the one (1) identified gene duplication over the same period.” The duplicated gene “functions in the same enzymatic reaction” as the original. They observe, “Most changes to the metabolic network of Escherichia coli in the past 100 million years are due to horizontal gene transfer, with little contribution from gene duplicates.”

And from Trends in Genetics a piece about corals and sea anemones:

“The resulting data set… implies that much of the genetic complexity commonly assumed to have arisen much later in animal evolution is actually ancestral. The most surprising implication of these analyses, however, is that anthozoans have retained a substantial number of genes not previously known in the animal kingdom. Two possibilities remain to explain the presence of these genes in the anthozoan genomes:
(i) lateral gene transfer (LGT); or
(ii) conservation of ancient genes that have been lost from those animals for which complete sequences are available.
Although we cannot rule out LGT in all cases, we favor the latter explanation for most of these matches…
In many respects, the complexity of the anthozoan gene set does not differ substantially from that of vertebrates and frequently exceeds that of the model invertebrates Drosophila and Caenorhabditis… One possible interpretation of the counterintuitive genetic complexity of cnidarians could be that they are actually highly derived deuterostomes. However, this interpretation is strongly contradicted by a large body of phylogenetic data, which indicates that cnidarians are a monophyletic group basal within the Eumetazoa and forming the sister group to the Bilateria….
Four general conclusions emerge from this work. First, a link between morphological complexity and gene number is illusory. Second, the common ancestor of cnidarians and ‘higher’ animals (the Ureumetazoa) was surprisingly complex at the genetic level. Third, a small percentage of genes in the two anthozoans represents preserved ancient genes that were present in the common ancestor but have been lost in the ‘higher’ animals so far examined… Finally, gene loss has had a major role in animal evolution, and has been particularly extensive in the ecdysozoan model organisms… The remarkable genetic complexity of anthozoan cnidarians implies that most of the qualitative genetic differences between animals and other eukaryotes are ancestral…”

Neither of these published research papers support the Doctrine of the NeoDarwinian Synthesis as presented by Richard Dawkins (for example): that speciation is caused by genes randomly evolving into new genes in situ. Note that this is not the same as the Creationist claim: “organisms do not evolve; speciation does not occur.” Funnily enough, both papers are compatible with Intelligent Design. But then they are also compatible with Panspermia. And doubtless many other theories that have yet to be invented.

Despite milodonharlani’s claims that a universe created by God is not an example of intelligent design, there is a most fascinating book that is rather famous among philosophers who believe it contains arguments central to any credible intelligent design thesis. Richard Swinburne’s The Existence of God contains a Bayesian argument that the existence of God is more likely than his non-existence. The book’s focus is on how we explain things in epistemology and science. The only major “flaw”, if it can be called that, is that a logical consequence of Swinburne’s argument is that in a universe devoid of humans (thinking beings), God could not exist. God can only exist in a universe occupied by thinking beings.
J.L. Mackie, Swinburne’s major critic, fails to address explanation in his rejoinderThe Miracle of Theism. Consequently, Swinburne’s central them goes unchallenged. The Git did have a lecturer who claimed he had successfully challenged Swinburne in his Doctorate. But then that lecturer also claimed that Aristotle’s works were reintroduced into Western thought by Augustine of Hippo (it was Thomas Aquinas) and corrected the Git’s use of the word “apologetics” to “apologists” in his major essay.

@ milodonharlani

Irreducible complexity is as far from a fact as is possible. It’s a made up, sciencey sounding scam in order to sneak creationism into schools. It is entirely without any basis in fact & lacks any scientific validity.

Try arguing that with Chaitin. Good luck!

The Omega Number: Irreducible Complexity in Pure Math
Gregory J. Chaitin
Purchase on Springer.com
$29.95 / €24.95 / £19.95*
Abstract
We discuss the halting probability Ω, whose bits are irreducible mathematical facts, that is, facts which cannot be derived from any principles simpler than they are. In other words, you need a mathematical theory with N bits of axioms in order to be able to determine N bits of Ω. This pathological property of Ω is difficult to reconcile with traditional philosophies of mathematics and with traditional views of the nature of mathematical proof and of mathematical knowledge. Instead Ω suggests a quasi-empirical view of math that emphasizes the similarities between mathematics and physics rather than the differences.

@ milodonharlani

A philosopher should never take what he or she assumes to be what science says as a given. Clearly, no one can become learned in every relevant discipline, but IMO Janice Moore’s heroes from the Discovery Institute must understand enough biology to know they’re lying.

I was taken to task for not taking what science (i.e. Dawkins et alia) says as a given! Pointing at recent discoveries was what got me labelled as a creationist. Funny when you think about it. That said, philosophers are not science researchers; philosophers ponder the logic and rationality of what is discovered and what is purported to have been. Most of that science is what makes it into academic texts, rather than the latest, greatest and frequently better forgotten papers. That said, many of my favourite philosophers are, or were, scientists.

While some philosophers may be proponents of both design hypotheses, no biologist can defend ID on other than religious grounds.

I doubt that. Perhaps you should distinguish between intelligent design and Stupid Design 😉 Just because people use the term Intelligent Design to describe their theory does not mean that they are intelligent.
Sorry I haven’t had time to follow up the read on the current status of C4 in the depths of time. I am pretty busy. It’s not raining today. I have opened the link in a tab that may be perused when it starts raining again.
Apropos the machine problem, I attempted to install the software I was given. It refused to install on my 64 bit Windows 7. Attempted to purchase the latest version from Amazon and discovered that only US citizens are allowed to purchase it! I have downloaded some free software in its stead. So it goes…
And it’s not raining today! So it’s out to tend the plants, but no zea mays this year. It’s now too late due to weeks of inclement weather. We do not eat a lot, but the little we usually grow goes down a treat.

Well, Milodon Harlani. So you are STILL trying the spread the word about Neo-Darwinism. You do realize, don’t you, that in your almost daily promoting of the theory of evolution and of Darwin’s Origin of Species ideas as if they are fact and not conjecture, you are acting like one who is promoting ones’ religion? I am hopeful that your constantly pushing Darwinism is because you have some doubt as to its truth (perhaps, only subconsciously) and will open your mind to the possibility that you are mistaken. Your level of anger when confronted with Intelligent Design is, you know, quite telling… .
It is nearly pointless to participate in a debate on this subject, because the Intelligent Design hypothesis requires some Bayesian prior assumptions that make the theory globally inconsistent and absurdly unlikely from the point of view of any sort of axiom of parsimony (e.g. Ockham’s Razor) or the actual evidence.
I’ll try one time to address these points, although it is probably pointless because ID advocates without exception are inventing a hypothesis with the motivation of allowing for the participation of a beneficent deity that otherwise is completely invisible in any sort of statistical analysis of human affairs, usually (if they were honest) a specific beneficent creator deity from one specific world mythology. In the US and Europe, that deity is almost certainly “God” and/or “Jesus” in the Christian church.
Any sort of argument based on teleology fails because if ID is true, there is an intelligent designer. Either the intelligent designer’s intelligence arose spontaneously — in which case intelligence and structure with the appearance of design can arise spontaneously and one cannot invoke the need for a designer to explain design — or that designer’s intelligence was itself designed by a still earlier intelligence. Since the Big Bang cuts off any sort of recursive chain without resorting to deity in some imagined external/parallel reality that we haven’t a shred of evidence to support, the argument is inconsistent.
Given that one cannot say that ID is necessary when confronted with structures with purpose (because of the recursion problem), granting that ID is sufficient to explain almost anything, as is a theory that invisible fairies are the true cause of gravity, one has to invoke parsimony and look at the evidence. There is an absolutely enormous amount of evidence for evolution due to mutation plus natural selection. We see it happen all of the time in the laboratory. We combat it in the world of diseases. We have mountains of fossil evidence showing the evolution of species The theory is a sufficient explanation for species, diversity, intelligence, and structure.
We then have two competing theories, both sufficient. Which theory has the preponderance of evidence? No evidence of structure counts in favor of ID, because evolution creates similar structures and we have direct laboratory evidence for it. What would count as evidence for ID is discovering direct scientific evidence of the designer. And there isn’t any. Not a shred. To invoke a designer, you have to explain how the designer got there or it is an incomplete theory. To claim “proof” of a designer, you have to produce direct evidence for the existence of a designer. The former requires an infinitely complicated explanation, all of it safely hidden — you might as well make your theory “I don’t know” because that’s all you will be able to say when asked about the nature or mechanism of the designer. The latter requires a measurement, a direct observation, of the designer. Otherwise you’re claiming to be able to infer a hidden cause when there is a much simpler explanation with direct evidence supporting it that is also sufficient.
That’s why people don’t pay any attention to your silly videos. Show me the designer. That’s the only thing that counts as evidence of Intelligent Design.
rgb

Robert, I must take you to task for the following statement:

There is an absolutely enormous amount of evidence for evolution due to mutation plus natural selection. We see it happen all of the time in the laboratory.

Mutations occur at a rate of roughly one in a million replications. Most mutations are deleterious and are weeded out by natural selection. Note that last sentence. It’s vital to the issues here. Deleting errors is quite different to generating novelty, such as feathers instead of scales, or mammalian skin cells. Explaining the generation of novelty is a Big and Complex Problem.

…molecular biologist, Barry Hall, published results which not only confirmed Cairns’s claims but laid on the table startling additional evidence of direct mutation in nature. Hall found that his cultures of E. coli would produce needed mutations at a rate about 100 million times greater than would be statistically expected if they came by chance. Furthermore, when he dissected the genes of these mutated bacteria by sequencing them, he found mutations in no areas other than the one where there was selection pressure. This means that the successful bugs did not desperately throw off all kinds of mutations to find the one that works; they pinpointed the one alteration that fit the bill. Hall found some directed variations so complex they required the mutation of two genes simultaneously. He called that “the improbable stacked on top of the highly unlikely.” These kinds of miraculous change are not the kosher fare of serial random accumulation that natural selection is supposed to run on. They have the smell of some design.

Now the smell of design certainly does get those Discovery Institute types running around flapping their hands and saying “it must be God’s work”, but it does no one any good to call anyone who happens to notice that we are talking about the results of empirical research here a Creationist. There are other explanations. The most obvious one is that we don’t actually understand a very great deal of biology. I usually put it thusly. There are at least four possible explanations here:
1. It’s all just down to an amazing long streak of lucky events. We Know The Truth. Live with it. [neoDarwinists]
2. This is not the explanation for evolution. Evolution involves whole nucleotide sequences (horizontal gene transfer). [Panspermia advocates/Margulis et alia]
3. There is some undiscovered mechanism/mechanisms operating to skew the odds. That is, the process is not random at all. [Prigogine et alia]
4. God done it.
The first explanation doesn’t really cut it. The number of possible random permutations of even a single gene sequence is impossibly huge to explore. The second has the benefit of support from the laboratory, but it’s also far from sufficient at this time. Prigogine’s observation that self-organising systems are involved is almost certainly true. Indeed, it would be surprising if they weren’t. That said, we don’t understand self-organising systems very well at this stage much beyond acknowledging their existence. The final one has, as you correctly point out, zero supporting evidence and any Bayesian argument requires “Bayesian prior assumptions that make the theory globally inconsistent and absurdly unlikely from the point of view of any sort of axiom of parsimony”. But then biology isn’t globally consistent either (not to mention science in general) and also generates many absurdities as David Stove pointed out in his excellent book of essays Darwinian Fairytales.
Like nearly all philosophers, I am averse to entering into the ongoing food fight between creationists and biologists; it seems to consist mainly in mutual accusations of bad faith. What I am interested in are arguments that enable me to learn new things. Like the physicist Paul Davies (and others) I am interested in the question of why the universe is the way it is. And that definitely gets you into the issue of teleology. For an excellent overview of teleology including the fine-tuning argument which is what fascinates me, the Stanford Encyclopedia has an excellent, though longish piece here:
http://plato.stanford.edu/entries/teleological-arguments/
You correctly point out that a creator of the universe would be undetectable. Unfortunately, the current competing view appears to be that there are many if not an infinite number of universes. Is it not the case that these ever so many alternative universes are also undetectable? I do not expect an answer to that question.
Thanks BTW for your many illuminating posts on this website. And I’m not sure if I thanked you directly for your excellent novel, but I found it very amusing.

@ milodonharlani
You wrote: “Ohno was wrong about that. He didn’t know then what we know now, & was already shown wrong even before we found out as much as we have about genomics.”
I quote here from the Wiki-bloody-pedia because it’s in electronic rather than paper form:

Functional divergence is the process by which genes, after gene duplication, shift in function from an ancestral function. Functional divergence can result in either subfunctionalization, where a paralog specializes one of several ancestral functions, or neofunctionalization, where a totally new functional capability evolves. It is thought that this process of gene duplication and functional divergence is a major originator of molecular novelty and has produced the many large protein families that exist today.[1][2]
Functional divergence is just one possible outcome of gene duplication events. Other fates include nonfunctionalization where one of the paralogs acquires deleterious mutations and becomes a pseudogene and superfunctionalization (reinforcement),[3] where both paralogs maintain original function. While gene, chromosome, or whole genome duplication events are considered the canonical sources of functional divergence of paralogs, orthologs (genes descended from speciation events) can also undergo functional divergence [4][5][6][7] and horizontal gene transfer can also result in multiple copies of a gene in a genome, providing the opportunity for functional divergence.
Many well known protein families are the result of this process, such as the ancient gene duplication event that led to the divergence of hemoglobin and myoglobin, the more recent duplication events that led to the various subunit expansions (alpha and beta) of vertebrate hemoglobins,[8] or the expansion of G-protein alpha subunits [9]

This reflects what I discussed with a friend who was far more into genomics than I am when I was in that philosophy of biology class in 2005. I do note that Ohno’s hypothesis regarding whole genome duplication (R2) appears to have fallen, but the part that interested me appears to still be currently accepted contra your statement above.

@ milodonharlani

Forgot to reply to your citation of Cairns/Foster/Hall on adaptive mutation (AM). As I’ve commented repeatedly above, it has long been known that stresses can increase the mutation rate.
The supposedly anti-darwinian “magic” of AM didn’t survive long, as is usual with such supposed mysteries.

So now John Cairns, ? Foster and Barry Hall are “anti-darwinian” creationist magicians, too. [sigh] At least I’m in good company…

“If you were really interested in learning biology rather than promoting a teleological philosophy”
From my notes ca. 2005:

The teleological terms “function” and “design” appear frequently in the biological sciences.
Examples of teleological claims include:
A (biological) function of stotting by antelopes is to communicate to predators that they have been detected.
Eagles’ wings are (naturally) designed for soaring.

Biologists, despite frequently claiming to eschew teleological language, use such quite frequently. So it goes…

You really cannot see the distinction between recognizing that adaptive behavior has a survival enhancing purpose so was selected for and believing that a supernatural power directs evolution in general toward some purposeful end such as humanity?
Some philosopher! Pure sophistry!

Diego Diaz said @ November 15, 2013 at 1:09 pm

Your false examples are straight out of Answers in Genesis.

Since I have never read Answers in Genesis, I have no idea whether your statement is true or not. Please quote my words and provide a link. FWIW I am an agnostic on many things, most especially those I have never investigated. This is the very opposite of the faith you are alleging I possess.

Diego Diaz said @ November 15, 2013 at 1:17 pm

You really cannot see the distinction between recognizing that adaptive behavior has a survival enhancing purpose so was selected for and believing that a supernatural power directs evolution in general toward some purposeful end such as humanity?

Please quote my words where you claim that I said I believe that a supernatural power directs evolution.
I did write above “The [God done it explanation] has, as you correctly point out, zero supporting evidence and any Bayesian argument requires ‘Bayesian prior assumptions that make the theory globally inconsistent and absurdly unlikely from the point of view of any sort of axiom of parsimony’.” Emphasis added.

1. It’s all just down to an amazing long streak of lucky events. We Know The Truth. Live with it. [neoDarwinists]
2. This is not the explanation for evolution. Evolution involves whole nucleotide sequences (horizontal gene transfer). [Panspermia advocates/Margulis et alia]
3. There is some undiscovered mechanism/mechanisms operating to skew the odds. That is, the process is not random at all. [Prigogine et alia]
4. God done it.
This list is hardly exhaustive, and it isn’t clear at all how much luck is needed. I’m a bit of an expert on evolutionary algorithms, which are important in all sorts of optimization theories and search algorithms because they are literally the most efficient search algorithm we’ve been able to find for high dimensional spaces. Also (although my previous reply may have given the wrong impression) I’m not advocating only mutation plus natural selection, although that is a rather powerful process. There could be all sorts of ways that the dice are loaded, if you will. The world’s most successful species very probably evolved to evolve better than that — the algorithm itself is subject to tuning.
I’m very fond of Prigogine’s general work, not specifically in the context of evolution. But it is indeed the case that there can be all sorts of things that skew the odds while still remaining “random”. They simply aren’t random on the original oversimplistic picture of mutation plus natural selection. As a single example, it is now known that species hybridization is not rare or nearly impossible, it is commonplace. Hybridization plus mutation plus selection is one of many possible skewing mechanisms.
None of this affects the direct evidence we have of evolution in the form of a fossil record that — highly incomplete as it is (the odds of a dying animal being fossilized are poor indeed) — paints a clear and compelling picture of the evolution of species from common progenitor species, happening over and over and over again for nearly every species we look at. In our own family tree we can quite literally see where a break occurred in a chromosome comparing human and gorilla DNA, along with many other homologies:
http://en.wikipedia.org/wiki/Human_evolutionary_genetics
These genes are pure evidence for evolution. The leave lots of room (and the article discusses some of that room) for different mechanism for the changes, but there is little doubt that discrete changes occurred, and not much doubt when they occurred, to split the genetic line that became modern humans off from the line that became modern gorillas. There appear to be multiple mechanisms at work here — small changes that gradually are selected out according to benefit, and large changes that occur “all at once” (or in a comparatively short period of time), but both are arguably evolution, and neither one invokes an external intelligence making changes in Earth’s species over some 3 to 4 billion years.
This is the critical issue, not the particular mechanism(s) of evolution. Is evolution the result of reasoned activity by an external entity or is evolution a naturally occurring process of genetic change due to all mechanisms plus the inevitable sorting out of living creatures on the basis some mix of luck and fitness to survive and reproduce (and yes, I’m well aware that “reproduce” is broader than just the individual as well, while even at the tribal or familial level it is still evolution)?
The fossil record is absolutely overwhelming evidence for evolution, whether or not the evolution is precisely Darwin’s theory of evolution. Evolution best fits the observations. Evolution can be and has been observed in the lab. We use evolution as a tool — humans have evolved improved crops and animals for husbandry for thousands of years if not much longer by simply becoming an agent of natural selection, picking the biggest and best of animals to breed, picking the animals that were the safest to work with and best behaved according to our needs. Humans created the dog out of a wolf ancestor by means of pure evolution — breeding most the animals that exhibited (and continue to exhibit) the most desired traits. Perhaps, as you assert, mutation is too slow a mechanism to be able to create radical changes in appearance and behavior rapidly, but if so the differences between chihuahua and great dane are difficult to account for.
Where I teach in the summers at the Duke Marine lab I can look out of my window and see the results of a mere 400 years of evolution. The so-called “Shackleford Ponies” live in comparative abundance on the outer bank islands just outside of my back door. They are the distant descendents of domesticated horses that made it to shore when ships foundered offshore in the sixteenth and seventeenth centuries. In a mere 400+ years, they have evolved to be much smaller (the islands have a severely constrained food supply), shaggier (they have to survive the winter), and most interestingly, they have evolved the ability to survive on brackish water, as the islands have almost no fresh water and what they have is inevitably far saltier than actual fresh water. The horse’s kidneys have significantly drifted due to mutation plus natural selection in only a few hundred years. The horses have other interesting traits — they have learned to read the tides, and know how to move between the islands when it is safe to do so, for example — but they are again direct evidence of natural evolution occurring on a fairly rapid timescale even in a small population.
In the laboratory, every physician faces the challenge of successful evolution almost every day. Bacteria and other parasites are evolving resistances to the drugs and antibiotics we use to combat them. New genetic variants of diseases are constantly emerging and the successful ones can at any moment become the next pandemic. Bacteria or viruses that are not diseases mutate and become new species that are diseases — another source of potential pandemic. We observe evolution at every scale from microscopic to macroscopic, we use it as a tool, we use evolutionary algorithms in computational optimization theory, we have immensely powerful computer programs that can do statistical genetic analysis. While scientists are hardly a uniform group and are apt to disagree about all sorts of theories or the meaning of this or that bit of evidence, you will have a very difficult time finding credible scientists who don’t believe in evolution as the explanation for the diversity of species and as the best explanation for the natural history of the biosphere, even as I’m sure you can find that those same scientists are not at all in agreement on the precise details of the mechanisms involved (and could even all be right as there could be many mechanisms).
God, of course, is a universal explanation, as are invisible fairies, solipcism, sufficiently advanced (and very, very patient) space aliens, pink unicorns, etc. One can always just make something up and explain away any inconsistencies by adding exceptions. This is not very reasonable — the more exceptions and inconsistencies you add, the lower the probability is that your “theory” is correct, especially without either supporting evidence or the ability to falsify a claim on the basis of evidence. As such it can never by purely logically or empirically refuted, any more than I can logically or empirically prove that I’m not a power unit in the matrix so that everything I think I know about the world is false. However, neither can it ever be logically supported until one comes up with direct observational evidence, and so far Gods and Pink Unicorns alike are scarce as hen’s teeth. So are super-intelligent space aliens or any other non-diety “intelligences” that ID advocates will offer up to prove that they don’t really mean God, it could be any old superhuman intelligence.
This also applies to your semi-telelogical argument about the tuning of the Universe to “life” if not more specifically “human life”. There are a number of problems with this argument, as I’m sure you are aware. The first is that given direct knowledge only of the spacetime continuum in which we seem to live, we cannot speak of “probability”, as in “what is the probability of finding a Universe with the parameters our Universe has”. The answer is “unity”. Behold it. It Is. So far, we are unable to empirically demonstrate a hat full of Universes from which our Universe is drawn, nor can we postulate on the basis of any evidence a process that might have produced a “Universe tuned to life”. Worse, any attempt to do so will run into the teleological paradox. If you wish to assert that the Universe appears designed, and thereby infer a designer, that designer must be even more complex than the Universe, and hence must in an information theoretically precise sense be less likely. You are invoking a cause that is even less likely than the effect that you wish to claim is necessary because it is supposedly so very unlikely, in spite of the fact that the latter is manifestly real and the former pure supposition.
Who designed the designer?
If you postulate a designer that needed no designer, then surely it is far simpler to not bother, and postulate a Universe that needed no designer. You have the substantial advantage in the latter case that the Universe is not a postulate, it is an accomplished fact and every instant of your experience empirically affirms this. There is no evidence whatsoever for the undesigned designer.
rgb

Diego Diaz said @ November 15, 2013 at 1:29 pm

You did not search. Afraid of truth?

I possess the following by Dawkins:
Unweaving the Rainbow, Allen Lane 1998
The Blind Watchmaker, Penguin 1998
Climbing Mount Improbable Penguin 1996
The Extended Phenotype Oxford 1989
It would seem I am unafraid of Dawkins 😉 Tell me where in those pages I may find Dawkins contradicting his statement that I quoted above.

Oh, and I do know, BTW, that you are not arguing for either ID or God per se — my arguments are against teleological arguments in general. I didn’t even point out the usual answer to the assertion — there could even be a hat from which separated, discrete Universes (or rather, spacetime continua as I dislike using the term Universe for anything but “everything that actually objectively exists”, the existential Universe) are “drawn”, or bubble out of, and their physical parameters could be completely random but it is a simple matter of fact that there won’t be any sentient beings that evolve to wonder about all of this in any of those Universes except the ones where the parameters are just right for this to occur.
Indeed, this isn’t all that crazy an argument. Forget physical coupling constants. What is the probability that I exist, doing what I’m doing right now, in a Universe that is in exactly the state that this one appears to be (even with the right coupling constants)?
Mathematics lacks enough zeros to put before the first nonzero digit… or, unity. Personally, I prefer unity, unless and until we find the hat and some sort of random process. I might even prefer unity afterwards. What’s the probability that I just typed the phrase “What’s the probability that I just typed the phrase “”What’s the probability that I just typed the phrase “””What’s the probability….””” (recurse indefinitely)? Apparently, it was unity.
That’s the problem, those pesky Bayesian priors. Even with a hat, or urn, to draw from, you arrive at very different estimates for the probability of drawing a green ball from a large urn given only the evidence that you have drawn one green ball from it depending on how you think the urn was prepared! This makes e.g. Polya’s Urn type estimates so very interesting.
rgb

Lady with ID videos and man with literal interpretation of Genesis sound ignorant to me. I apologize but in Amazon Basin my work is hurt by fundamentalist missionaries.
I see this is not a good site for me.
Thank you for your excellent comments and you are right I was rude.
Goodbye.

It would seem Gregory Chaitin has recently written a book: Proving Darwin: Making Biology Mathematical and I have downloaded it to my Kindle. However, the sun is shining in a clear sky for the fist time in many weeks and farms do not take care of themselves so it isn’t going to be read by me today.
http://books.google.com.au/books?hl=en&lr=&id=J8XG8Y5Ou5QC&oi=fnd&pg=PR7&dq=Proving+Darwin:+Making+Biology+Mathematical&ots=9NuHNx_Fl2&sig=SzF-NGUahndpPxZIUuk7jEKCflM#v=onepage&q=Proving%20Darwin%3A%20Making%20Biology%20Mathematical&f=false

I know you are not she nor ignorant prejudiced fundamentalist with no interest in truth like her or Genesis speaks of plasma and ions man but still this not a good site for me but thank you for saying “stick around”. I am Catholic but not crazy fundamentalist. My work is to help indigenous people and the nature of the Amazon, my home.
So goodbye to you too sir as to Dr RGB.

@ Diego Diaz
You are (I imagine) referring to programs like Thomas S. Ray’s Tierra. While this emulates certain aspects of evolution, it does not generate novelty. This is the aspect of evolution that has me most fascinated and frankly, being so seems to get me into hot water every now and then. So it goes… I have always been keenly interested in the hard questions.
Good luck with your work and your rainforest. It sounds like a fascinating place to work. The Git lives adjacent to a rainforest in a much cooler part of the world: Southern Tasmania. Our indigines are supposedly extinct which makes them justifiably angry. However, it’s probably better to be angry than extinct 😉

@ Diego Diaz
I have long believed that the conundrum I face with the evolution of novelty in biology would eventually be solved computationally. Gregory Chaitin seems to believe the same, but estimates that it’s going to take a long time to achieve. IOW The Git will be dead when it happens. The problem with Tierra and its ilk is that information comes from outside. Dawkins’ example of evolution from a random string to “METHINKS IT IS LIKE A WEAZEL” presupposes the existence of the final string: “METHINKS IT IS LIKE A WEAZEL”. Also, IIRC, Dawkins acknowledged this and says something like “but evolution is very similar” or some such. This is arm waving to say the least.
One question I remember asking all these many years ago was “Why would ‘junk DNA’ persist under natural selection pressure?” A few years ago I heard a geneticist on the radio saying how remarkably well conserved it was (more so than expressed DNA) and that it had been renamed ‘silent’ rather than ‘junk’. It is my belief, and this is not original with me, that the silent DNA is akin to a computer operating system and that the various organisms inhabiting Earth are running different software on essentially the same operating system. However, it’s vastly different to anything like what we currently run on our computers in that it automagically generates new stuff within an apparently closed system. There is no way that I can conceive of MS Word evolving into MS Excel gradually while retaining usefulness.
Chaitin tips his hat to at least two panspermia (new information comes from outside) advocates: Fred Hoyle and Francis Crick. And that’s enough for him to be condemned by several biologists I have come across, but that’s life so to speak. He also notes how indebted he is to John von Neumann, Alan Turing and Kurt Gödel, three other thinkers who had a major impact on my thinking. And now I return to finishing his rather short book.

rgbatduke said @ November 15, 2013 at 2:20 pm

So far, he has said little that I would fundamentally disagree with except create a list of evolutionary theories that I think is a bit too narrow and give perhaps a bit too little weight to the ongoing work of evolutionary biologists.

One of the problems I was having in the mid 2000s was being tasked for giving too much weight to current/recent work and that I should merely accept the older, simpler prescriptions of the modern synthesis (dare I say consensus). So it goes…
You also write:

if he did bring up one of the neo-teleological arguments, well, even I think that the observations are “interesting” at the same time that I recognize (and pointed out) that they cannot constitute statistical/empirical “evidence”.

The ID argument as exemplified by Paley et alia is most decidedly based upon empirical evidence; it’s certainly not a priori. We just do not find it compelling or sufficient within the context that it is presented. For example, the creationists present the evidence of cnidarians (jellyfish) with well developed lenses, but no brain or retina to process the information from the gathered light. The creationist says: “God done it; The Git says: “The genes for lens formation did not arise in the jellyfish, they appear to have been transferred horizontally from some other organism; Dawkins said: “Retinas and brains precede lenses” (paraphrase from Climbing Mount Improbable). This latter is about as far from empirical as you can get.
It is interesting though that these design arguments do not go away. “One possibility is that they really are better arguments than most philosophical critics (including The Git) concede. Another possibility is that design intuitions do not rest upon inferences at all.” But that then becomes another argument that I am loath to pursue.
Thanks for your supportive comments Robert.