Evo-Info 3: Evolution is not search

Introduction to Evolutionary Informatics, by Robert J. Marks II, the “Charles Darwin of Intelligent Design”; William A. Dembski, the “Isaac Newton of Information Theory”; and Winston Ewert, the “Charles Ingram of Active Information.” World Scientific, 332 pages.
Classification: Engineering mathematics. Engineering analysis. (TA347)
Subjects: Evolutionary computation. Information technology–Mathematics.

Marks, Dembski, and Ewert open Chapter 3 by stating the central fallacy of evolutionary informatics: “Evolution is often modeled by as [sic] a search process.” The long and the short of it is that they do not understand the models, and consequently mistake what a modeler does for what an engineer might do when searching for a solution to a given problem. What I hope to convey in this post, primarily by means of graphics, is that fine-tuning a model of evolution, and thereby obtaining an evolutionary process in which a maximally fit individual emerges rapidly, is nothing like informing evolution to search for the best solution to a problem. We consider, specifically, a simulation model presented by Christian apologist David Glass in a paper challenging evolutionary gradualism à la Dawkins. The behavior on exhibit below is qualitatively similar to that of various biological models of evolution.

Animation 1. Parental populations in the first 2000 generations of a run of the Glass model, with parameters (mutation rate .005, population size 500) tuned to speed the first occurrence of maximum fitness (1857 generations, on average), are shown in orange. Offspring are generated in pairs by recombination and mutation of heritable traits of randomly mated parents. The fitness of an individual in the parental population is, loosely, the number of pairs of offspring it is expected to leave. In each generation, the parental population is replaced by surviving offspring. Which of the offspring die is arbitrary. When the model is modified to begin with a maximally fit population, the long-term regime of the resulting process (blue) is the same as for the original process. Rather than seek out maximum fitness, the two evolutionary processes settle into statistical equilibrium.

Figure 1. The two bar charts, orange (Glass model) and blue (modified Glass model), are the mean frequencies of fitnesses in the parental populations of the 998,000 generations following the 2,000 shown in Animation 1. The mean frequency distributions approximate the equilibrium distribution to which the evolutionary processes converge. In both cases, the mean and standard deviation of the fitnesses are 39.5 and 2.84, respectively, and the average frequency of fitness 50 is 0.0034. Maximum fitness occurs in only 1 of 295 generations, on average.

I should explain immediately that an individual organism is characterized by 50 heritable traits. For each trait, there are several variants. Some variants contribute 1 to the average number offspring pairs left by individuals possessing them, and other variants contribute 0. The expected number of offspring pairs, or fitness, for an individual in the parental population is roughly the sum of the 0-1 contributions of its 50 traits. That is, fitness ranges from 0 to 50. It is irrelevant to the model what the traits and their variants actually are. In other words, there is no target type of organism specified independently of the evolutionary process. Note the circularity in saying that evolution searches for heritable traits that contribute to the propensity to leave offspring, whatever those traits might be.

The two evolutionary processes displayed above are identical, apart from their initial populations, and are statistically equivalent over the long term. Thus a general account of what occurs in one of them must apply to both of them. Surely you are not going to tell me that a search for the “target” of maximum fitness, when placed smack dab on the target, rushes away from the target, and subsequently finds it once in a blue moon. Hopefully you will allow that the occurrence of maximum fitness in an evolutionary process is an event of interest to us, not an event that evolution seeks to produce. Again, fitness is not the purpose of evolution, but instead the propensity of a type of organism to leave offspring. So why is it that, when the population is initially full of maximally fit individuals, the population does not stay that way indefinitely? In each generation, the parental population is replaced with surviving offspring, some of which are different in type (heritable traits) from their parents. The variety in offspring is due to recombination and mutation of parental traits. Even as the failure of parents to leave perfect copies of themselves contributes to the decrease of fitness in the blue process, it contributes also to the increase of fitness in the orange process.

Both of the evolutionary processes in Animation 1 settle into statistical equilibrium. That is, the effects of factors like differential reproduction and mutation on the frequencies of fitnesses in the population gradually come into balance. As the number of generations goes to infinity, the average frequencies of fitnesses cease to change (see “Wright, Fisher, and the Weasel,” by Joe Felsenstein). More precisely, the evolutionary processes converge to an equilibrium distribution, shown in Figure 1. This does not mean that the processes enter a state in which the frequencies of fitnesses in the population stay the same from one generation to the next. The equilibrium distribution is the underlying change­less­ness in a ceaselessly changing population. It is what your eyes would make of the flicker if I were to increase the frame rate of the animation, and show you a million generations in a minute.

Animation 2. As the mutation rate increases, the equilibrium distribution shifts from right to left, which is to say that the long-term mean fitness of the parental population decreases. The variance of the fitnesses (spread of the equilibrium distribution) increases until the mean reaches an intermediate value, and then decreases. Note that the fine-tuned mutation rate .005 ≈ 10–2.3 in Figure 1.

Let’s forget about the blue process now, and consider how the orange (randomly initialized) process settles into statistical equilibrium, moving from left to right in Animation 1. The mutation rate determines

  1. the location and the spread of the equilibrium distribution, and also
  2. the speed of convergence to the equilibrium distribution.

Animation 2 makes the first point clear. In visual terms, an effect of increasing the mutation rate is to move equilibrium distribution from right to left, placing it closer to the distribution of the initial population. The second point is intuitive: the closer the equilibrium distribution is to the frequency distribution of the initial population, the faster the evolutionary process “gets there.” Not only does the evolutionary process have “less far to go” to reach equilibrium, when the mutation rate is higher, but the frequency distribution of fitnesses changes faster. Animation 3 allows you to see the differences in rate of convergence to the equilibrium distribution for evolutionary processes with different mutation rates.

Animation 3. Shown are runs of the Glass model with mutation rate we have focused upon, .005, doubled and halved. That is,  = 2 ⨉ .005 = .01 for the blue process, and  = 1/2 ⨉ .005 = .0025 for the orange process.

An increase in mutation rate speeds convergence to the equilibrium distribution, and reduces the mean frequency of maximum fitness.

I have selected a mutation rate that strikes an optimal balance between the time it takes for the evolutionary process to settle into equilibrium, and the time it takes for maximum fitness to occur when the process is at (or near) equilibrium. With the mutation rate set to .005, the average wait for the first occurrence of maximum fitness, in 1001 runs of the Glass model, is 1857 generations. Over the long term, maximum fitness occurs in about 1 of 295 generations. Although it’s not entirely accurate, it’s not too terribly wrong to think in terms of waiting an average of 1562 generations for the evolutionary process to reach equilibrium, and then waiting an average of 295 generations for a maximally fit individual to emerge. Increasing the mutation rate will decrease the first wait, but the decrease will be more than offset by an increase in the second wait.

Figure 2. Regarding Glass’s algorithm (“Parameter Dependence in Cumulative Selection,” Section 3) as a problem solver, the optimal mutation rate is inversely related to the squared string length (compare to his Figure 3). We focus on the case of string length (number of heritable traits) L = 50, population size N = 500, and mutation rate  = .005, with scaled mutation rate uʹ L2 = 12.5 ≈ 23.64. The actual rate of mutation, commonly denoted u, is 26/27 times the rate reported by Glass. Note that each point on a curve corresponds to an evolutionary process. Setting the parameters does not inform the evolutionary search, as Marks et al. would have you believe, but instead defines an evolutionary process.

Figure 2 provides another perspective on the point at which changes in the two waiting times balance. In each curve, going from left to right, the mutation rate is increasing, the mean fitness at equilibrium is decreasing, and the speed of convergence to the equilibrium distribution is increasing. The middle curve (L = 50) in the middle pane (N = 500) corresponds to Animation 2. As we slide down the curve from the left, the equilibrium distribution in the animation moves to the left. The knee of the curve is the point where the increase in speed of convergence no longer offsets the increase in expected wait for maximum fitness to occur when the process is near equilibrium. The equilibrium distribution at that point is the one shown in Figure 1. Continuing along the curve, we now climb steeply. And it’s easy to see why, looking again at Figure 1. A small shift of the equilibrium distribution to the left, corresponding to a slight increase in mutation rate, greatly reduces the (already low) incidence of maximum fitness. This brings us to an important question, which I’m going to punt into the comments section: why would a biologist care about the expected wait for the first appearance of a type of organism that appears rarely?

You will not make sense of what you’ve seen if you cling to the misconception that evolution searches for the “target” of maximally fit organisms, and that I must have informed the search where to look. What I actually did, by fine-tuning the parameters of the Glass model, was to determine the location and the shape of the equilibrium distribution. For the mutation rate that I selected, the long-term average fitness of the population is only 79 percent of the maximum. So I did not inform the evolutionary process to seek out individuals of maximum fitness. I selected a process that settles far away from the maximum, but not too far away to suit my purpose, which is to observe maximum fitness rapidly. If my objective were to observe maximum fitness often, then I would reduce the mutation rate, and expect to wait longer for the evolutionary process to settle into equilibrium. In any case, my purpose for selecting a process is not the purpose of the process itself. All that the evolutionary process “does” is to settle into statistical equilibrium.

Sanity check of some claims in the book

Unfortunately, the most important thing to know about the Glass model is something that cannot be expressed in pictures: fitness has nothing to do with an objective specified independently of the evolutionary process. Which variants of traits contribute 1 to fitness, and which contribute 0, is irrelevant. The fact of the matter is that I ignore traits entirely in my implementation of the model, and keep track of 1s and 0s instead. Yet I have replicated Glass’s results. You cannot argue that I’ve informed the computer to search for a solution to a given problem when the solution simply does not exist within my program.

Let’s quickly test some assertions by Marks et al. (emphasis added by me) against the reality of the Glass model.

There have been numerous models proposed for Darwinian evolution. […] We show repeatedly that the proposed models all require inclusion of significant knowledge about the problem being solved. If a goal of a model is specified in advance, that’s not Darwinian evolution: it’s intelligent design. So ironically, these models of evolution purported to demonstrate Darwinian evolution necessitate an intelligent designer.

Chapter 1, “Introduction”


[T]he fundamentals of evolutionary models offered by Darwinists and those used by engineers and computer scientists are the same. There is always a teleological goal imposed by an omnipotent programmer, a fitness associated with the goal, a source of active information …, and stochastic updates.

Chapter 6, “Analysis of Some Biologically Motivated Evolutionary Models”


Evolution is often modeled by as [sic] a search process. Mutation, survival of the fittest and repopulation are the components of evolutionary search. Evolutionary search computer programs used by computer scientists for design are typically teleological — they have a goal in mind. This is a significant departure from the off-heard [sic] claim that Darwinian evolution has no goal in mind.

Chapter 3, “Design Search in Evolution and the Requirement of Intelligence”

My implementation of the Glass model tracks only fitnesses, not associated traits, so there cannot be a goal or problem specified independently of the evolutionary process.

Evolutionary models to date point strongly to the necessity of design. Indeed, all current models of evolution require information from an external designer in order to work. All current evolutionary models simply do not work without tapping into an external information source.

Preface to Introduction to Evolutionary Informatics


The sources of information in the fundamental Darwinian evolutionary model include (1) a large population of agents, (2) beneficial mutation, (3) survival of the fittest and (4) initialization.

Chapter 5, “Conservation of Information in Computer Search”

The enumerated items are attributes of an evolutionary process. Change the attributes, and you do not inform the process to search, but instead define a different process. Fitness is the probabilistic propensity of a type of organism to leave offspring, not search guidance coming from an “external information source.” The components of evolution in the Glass model are differential reproduction of individuals as a consequence of their differences in heritable traits, variety in the heritable traits of offspring resulting from recombination and mutation of parental traits, and a greater number of offspring than available resources permit to survive and reproduce. That, and nothing you will find in Introduction to Evolutionary Informatics, is a fundamental Darwinian account.

1,439 thoughts on “Evo-Info 3: Evolution is not search

  1. DNA_Jock: Who said it was a regular deck of cards?

    Let me repeat this. No one. You seem to think I never thought it possible that it might not be a regular deck of cards. If so, you were wrong.

    The first hint I gave you was by specifying that the deck was a regular deck.

    The second hint I gave you was by assuming that the deck was a regular deck.

    Far be it from you to point out the obvious, that the probability is unknown, so far be it from me then to state the obvious, which is that I don’t know what the probability is.

    So what’s the next step in your grand scheme to convince me that you can be certain the temperature went up without having any clue whatsoever what the temperature was like before it went up? I really would like to know.

  2. keiths: You might want to read this thread and reevaluate.

    Isn’t it past time for you to bring up Theobold again? r maybe drag in another topic from some bygone thread? Have you paused to assess just how little of substance you’ve brought to this thread?

    And still haven’t admitted that you were wrong, by the way. All the while expecting it from others. tch. tch.

  3. keiths: Jock knows something you don’t, so your epistemic probabilities differ.

    So?

    When you start playing the game and losing money hand over fist to Jock, you will — unless you are even stupider than we’d realized — revise your epistemic probabilities.

    Which part of I wouldn’t play the game did you miss?

    wow. simply stunning.

    And I don’t know why you keep insisting on jumping in and mouthing off without having acquainted yourself with the context.

  4. DNA_Jock: Excellent! So we have established that you understand the situation, both the meaning of the phrase “draw a heart”, and the realization that, knowing DNA_Jock, it is NOT a regular deck.

    Oh crap. I missed that. You mean I can’t trsut DNA_Jock? My second “guesstimate” was based on thinking he would never wish to deceive me. Well, i guess I have to adjust my probabilities again!

  5. keiths:
    Mung: How do I know he has a probability in mind?

    keiths: Um, the fact that he said so.

    You’ll back this up, of course. Because you always defend all your claims.

    Where did DNA_Jock claim to have a probability in mind?

  6. Rumraket: So I haven’t followed this discussion these last few days…

    Lucky you. 🙂

    …anything interesting have transpired?

    keiths reading minds again, is all. Yours in particular. And at such great distance. Such powers!

    He claims that what you really had in mind were “epistemic probabilities,” even though you never quite managed to say so. And even if you didn’t say it, it’s what you really meant, because that’s what keiths wants and needs for you to have meant.

    Not only that, but keiths has decided that DNA_Jock too has been trying to teach me about “epistemic probabilities” even though DNA_Jock never said so.

    Welcome back.

  7. keiths: I hate to break it to you, but the brighter folks have already figured that out.

    phoodoo, why didn’t you tell me you had figured it out. Leaving me to flounder on my own. Not cool bro. Not cool.

  8. Rumraket: I get that back when I agreed with the statement that with evolution eyes are likely, and without they’re not, the reasons for this might not have been initially clear.

    ok, let’s talk about this claim. That with evolution, eyes are more likely. What is the probability of an eye, without evolution? Best guess.

  9. Mung,

    ok, let’s talk about this claim. That with evolution, eyes are more likely. What is the probability of an eye, without evolution? Best guess.

    Lower.

  10. DNA_Jock: A frequentist would note that, if we repeated this experiment a million times, the proportion of hearts observed would converge on the actual probability. Not really relevant though.

    You had more worried for just a second there. Because Rumraket was appealing to frequentist probability. And if this isn’t relevant to Rumraket’s argument, well, then keiths is just wrong. Again.

  11. DNA_Jock: Not at all clear to Mung, perhaps, reinforcing yet again Allan Miller’s assessment of Mung’s mindset.

    And Allan’s assessments have been so reliable in the past. Yet another entry into the Mindreader’s Guild.

  12. Reading up on epistemic probability, and things are exactly opposite what keiths has claimed.

    Since I can no longer trust keiths, from now on he shall be asked to support his claims. Which, if the past is any indication, he won’t.

  13. keiths: Jock knows something you don’t, so your epistemic probabilities differ.

    If Jock knows something that I do not know, then his calculation of the probability is conditional. Not only that, but his argument quite plainly decries the need to calculate probabilities at all. The two of you are rather obviously not on the same page. Do try again!

  14. Mung: Far be it from you to point out the obvious, that the probability is unknown, so far be it from me then to state the obvious, which is that I don’t know what the probability is.

    There you go, Mung, you got there eventually. Don’t be shy about stating the obvious.

    So:

    I present you with a well-shuffled deck of cards, and ask you “What’s the probability that you draw a heart from the deck?”

    And the answer is “I don’t know”.

    Awesome!
    Next, I remove a card from the deck, and show it to you — it’s the ten of hearts — and burn it. I also show you the seven of spades, but return that card to the deck.
    Now I ask you two more questions:
    1) “What’s the probability that you draw a heart from this deck?”
    2) “Has the probability decreased since I first asked you?”
    Now, if you are being honest, your answers will be “I don’t know” and “Yes, the probability has gone down”

    Now might be a good time to re-evaluate your disagreement with the statement

    One does not need to be able to estimate the probability of an event in order to be able to describe situations in which the probability has increased or decreased.

    Or not.
    ET avoid weaseling

  15. DNA_Jock: And the answer is “I don’t know”.

    It’s amazing it took us so long to get here. 🙂

    I don’t think I was shy about stating that I don’t know. I think I quoted myself saying that I don’t know.

    But how do you know? Keiths claims that you know. If you don’t know either, then, well, keiths is full of shit. Right?

    DNA_Jock
    Now, if you are being honest, your answers will be “I don’t know” and “Yes, the probability has gone down”

    I agree that given a single draw of a heart that this does not provide me with the information I would need in order to infer what the probability of drawing a heart is. I’m still at “I don’t know.”

    Do you think these ‘revelations’ contradict anything I’ve said previously? And, why hasn’t my “epistemic probability” changed?

    Because, after all, we’re talking epistemic probabilities, aren’t we? Keiths says that’s what this is all about. And he can’t possibly be wrong.

  16. DNA_Jock: Now, if you are being honest, your answers will be “I don’t know” and “Yes, the probability has gone down”

    ok. so my first answer, according to you, was an honest answer. Because I admit I don’t know. But maybe I just got lucky. Perhaps I flipped a coin. What’s the probability, given my answer, that it was due to “honesty”? Give it your best shot.

    Now, because I have an obvious aversion to being honest, my answer to your second question is that I now know that there as it least one spade [a non heart] in the deck. You’ve taken one card out of the deck and not replaced it, and you’ve taken a second card out of the deck and replaced it.

    So in the first case we have sampling without replacement, and in the second case we have sampling with replacement. Apples and oranges. If not, why not?

    What happens if we keep both cards out, or put both cards back in?

  17. Holy shit. The penny still hasn’t dropped.
    😮
    Move along, folks. Nothing to see here.

  18. DNA_Jock: Holy shit. The penny still hasn’t dropped.

    Perhaps you should cease with the evasions and at least try being honest. 🙂

  19. This thread has been a pretty spectacular failure for you, Mung.

    Congrats. It couldn’t have happened to a more deserving guy.

  20. Let shuffle the deck.

    I present you with a well-shuffled deck of cards, and ask you “What’s the probability that you draw a heart from the deck?”

    And your answer is “I don’t know”.

    Awesome!
    Next, I remove a card from the deck, and show it to you — it’s the ten of hearts — and burn it. I also show you the seven of spades, but return that card to the deck.
    Now I ask you one more question:
    “What’s the probability that you draw a heart from this deck?”

    Are you, DNA_Jock, in possession of information that I don’t have? Or is that just another of those things that is not relevant?

  21. keiths: This thread has been a pretty spectacular failure for you, Mung.

    Meanwhile, your contribution hovers quite steadily around 0. Give yourself a well-deserved pat on the back.

  22. keiths: Cue phoodoo to stumble in at any moment asking “Wait, what?”

    Cue keiths to stumble in at any moment asking, “someone demanded that I defend my bullshit claims? Wah! Wah!”

  23. Mung,

    Why not stop digging and sleep on it? The situation will be just as bleak for you in theornong.

  24. keiths, your posts exhibit a decided proclivity for being puerile. Do grow up.

    It’s pretty obvious to any impartial observer that you’ve exhausted your capabilities. Move along now.

  25. DNA_Jock, would you care to explain why it is that in the case of the ten of hearts you chose to not return it to the deck, whereas in the case of the seven of spades you chose to return it to the deck?

    What motivated those decisions, other than your desire to consciously manipulate the probabilities?

    If humans consciously and intentionally manipulate the probabilities, then the probabilities will change. Some people call this cheating. keiths calls it “epistemic probabilities.” Some people call this design.

  26. Allan Miller: I don’t get this ‘relative’ thing. You are just sampling the bag. Your sample is the information, relative to nothing else.

    Then how do you justify the decision to not put the heart back into the deck and the decision to put the spade back into the deck?

  27. Mung: If you don’t know either, then, well, keiths is full of shit. Right?

    I believe Newton refers to this as a discovery frequency of 1.

    But his calculations are way low.

  28. phoodoo: But his calculations are way low.

    Sampling error. Obviously. My opinion of keiths will rise exponentially if I put him back on Ignore.

  29. I love this shit. (Pardon my Urdu.)

    For example, if you draw a card from a deck of 52 playing cards which has been thoroughly shuffled, it is equally likely that the card you choose is a spade, heart, diamond or club.

    – Teach Yourself Statistics. p. 219-220

    Thank Fortuna that DNA_Jock was here to set us straight on that! Frequency that statistics books are wrong = 1.

  30. EXERCISE 12.2 Events, outcomes and probability

    Table 12.2 shows how probabilities of outcomes are usually calculated. Check that you understand the first two and fill in the rest for yourself.

    row 3. event: choosing a playing card. outcome: The suit being ‘hearts’.

    Yes. Really. “I don’t know” appears to be the honest answer, if you believe DNA_Jock.

  31. Rumraket: This is too simplistic phoodoo. Admittedly the references to the frequentist interpreation of probability used has been simplistic, so I can see why you’d think we are proposing to draw a conclusion from a sample size of 1. But we aren’t actually doing that, and wouldn’t do that in a situation where we are completely ignorant about the contents of the bag (and the size of the bag and so on).

    In statistics you want what is called statistical significance. That means that the number of samples you draw must constitute a fraction of the total sample space that is large enough that you can have some reasonable confidence that the samples you took are representative of the sample space.

    Counterintuitively (and IIRC) sample sizes can be as low as a few hundred, for a total sample space of hundreds of millions, and you can still be 95% confident that your few hundred samples are representative. These are just elementary statistical facts. But they do come with some confounding assumptions, which if they are violated, undermine your confidence in the result.

    One of those assumptions is that the contents of the bag are pretty well mixed. In other words, if it’s full of black and white balls, all the black balls are properly mixed with the white balls. If the bag contains 350 million well-mixed black and white balls, drawing a few hundred from the bag is enough to get well into the 90’s % confidence interval.

    If all the black balls are at the bottom of the bag, and you assume they’re well mixed, drawing a range of whites will of course lead you to the wrong conclusion. Noone here is under any illusions about these elementary axioms of statistics. You should stop arguing as if people you disagree with about evolution, also disagree about the basics of statistical reasoning.

    Just out of curiosity, is there anyone here who disagrees with this statement of Rumraket’s. I agree with it, especially the point regarding mixing arguments about statistics and probability in general with models of evolution that employ statistical or probabilistic elements.

  32. Mung: ok, let’s talk about this claim. That with evolution, eyes are more likely. What is the probability of an eye, without evolution? Best guess.

    Practically zero is my best guess, since we know of no other process than evolution by which they would come about, nor do we have even hints of evidence that eyes spontaneously form anywhere. There is no large stacks of eyes sitting around in the rock layers, on any planet or moon, or anything at all that hints there was once eyes just popping into existence.

    You could speculate that a designer could just make an eye appear somehow, somewhere on a barren planet, but we’ve got no evidence that such an event ever transpired (and why the hell would the designer do that, anyway?), so I’d still say the probability of eyes without evolution, but with design, are extremely low. The picture changes of course if you assume there is already life, and the designer wants to design the life to be able to see. Then assuming a lot of stuff about the competence and capabilities of the designer, eyes would be pretty much guaranteed of course. But we don’t have any evidence of this, so that leaves evolution.

    We seem to have only one history of life on this planet, and eyes have evolve over fifty times at least, and many of them are very different and began in different ways. This implies that evolution has an easy time making eyes (that there are many different pathways to eyes). So my best guess is that with evolution, the probability of eyes is almost 100%. As in, you roll back the tape of the history of life, and press play again, eyes would evolve again. And if you did it again, they would evolve again. And they’d probably do this close to 100% of the time. Which in turn I take to imply that if you moved to another planet that had large bodies of liquid and landmasses that were exposed to light and could support life, eyes would evolve there too, basically every time. For the same reasons, that there appears to be many pathways to eyes and that a single incident of evolution has done it independently at least fifty times.

    So with evolution, eyes are practically guaranteed to occur. And without it, eyes are practically guaranteed not to occur. That’s my best guess.

  33. Mung,

    This from the guy who doesn’t get “this ‘relative’ thing”? Funny.

    Word lawyering. Funny.

    Mung: “Information must be relative to something else”
    Allan “Sorry, I don’t get it”

    Time passes …

    Allan: “A is less than B”
    Mung: “AHA! GOTCHA!!!!”

  34. Mung,

    And Allan’s assessments have been so reliable in the past. Yet another entry into the Mindreader’s Guild.

    There is a reason – one subject to some hidden information – why Allan Miler’s assessments carry double weight, when they don’t cancel each other out …

    But, one doesn’t need to be a mindreader to see that you have a strong tendency to argue against anything an evolutionist may say, on any topic.

  35. Mung,

    Then how do you justify the decision to not put the heart back into the deck and the decision to put the spade back into the deck?

    Don’t ask me – that was some other guy!

    I think a source of confusion is between the known and the unknown. We flip between cards, coins, roulette wheels and bags of unknown constitution without apparently realising that different things are going on in relation to the state of knowledge we have. That’s why I tried to deflect ideas of straight flushes and runs of heads and talk about bags of balls (to Rumraket’s apparent irritation!).

    Soon as we start talking about cards, you already know everything you are going to know … provided we have a standard 52 card deck. So sampling the thing isn’t going to gain you information you don’t already have. A deck of unknown size and composition, however … but then, one has to be aware of the interaction between the sampling process and the population itself ***.

    Obviously, this is totally irrelevant to evolution, because we are not sampling without replacement there. Even if we were, the ‘bag’ is so huge that our sampling process makes no difference anyway. But, people are legitimately trying to clear up misonceptions on that score.

    *** Side note, somewhat relevant – there was a joke in the Marine Biology lab when I was at Uni that one researcher was such a assiduous collector of winkles for his research project that he was North Wales’s principal predator of winkles!

  36. Alan Fox,

    As I have pointed out already Alan, the problem with it is not the silly details about making sure the bag is mixed properly or this and that, it is more fundamental, when you are selecting from an unknown set, you have no way of telling when it is that your selection is a normal sampling or an aberration. Is what you have pulled a representative sample of what’s inside or it is an anomaly. Is what’s left similar to what has already been seen, or quite different. You can never know the answer to this, and you most certainly can’t even make a good guess by sampling .01 percent, or .000001 percent. How would you know when you just flipped ten heads in a row, of a two sided coin, if you don’t know if the coin has two sides? You don’t. You might just assume it only has one side, because you have never seen the other side. How many flips in a row will tell you if you have a two sided coin-there is no answer to this. And that’s just with two sides. What happens when the coin has 5000 sides? When will you know you have sampled all the sides? Never.

    So I find the qualifications about making sure the bag is mixed to be very trivial, and well short of identifying the real problems.

  37. phoodoo,

    winkle
    ˈwɪŋk(ə)l/
    noun
    noun: winkle; plural noun: winkles

    1.
    a small herbivorous shore-dwelling mollusc with a spiral shell.
    2.
    informal
    a child’s term for a penis.

  38. Mung: Are you, DNA_Jock, in possession of information that I don’t have? Or is that just another of those things that is not relevant?

    I may or may not be. It is irrelevant.

    Mung: DNA_Jock, would you care to explain why it is that in the case of the ten of hearts you chose to not return it to the deck, whereas in the case of the seven of spades you chose to return it to the deck?

    What motivated those decisions, other than your desire to consciously manipulate the probabilities?

    If humans consciously and intentionally manipulate the probabilities, then the probabilities will change.

    I was motivated by my desire to describe a situation in which the probabilities have changed. If you feel I am “cheating”, here’s an alternative scenario: Before shuffling the first time, I show you two cards, a heart and a club. After asking the first time “What’s the probability?”, I remove a card at random, show it to you, then ask the second and third questions. In this situation, neither of us knows the first or second probabilities, but we both know that the probability has changed. You know whether the probability has increased or decreased.
    As I said:

    One does not need to be able to estimate the probability of an event in order to be able to describe situations in which the probability has increased or decreased.

    Care to re-evaluate?

  39. Winky is the word I learned.

    There was a children’s TV show, Winky Dink And You. TV in the 50s was full of sly puns that got past the censors.

    Winkle, tinkle. Something about that sound.

  40. phoodoo: You can never know the answer to this, and you most certainly can’t even make a good guess by sampling .01 percent, or .000001 percent

    LOL, you should know by now that you are mathematically illiterate and you should really refrain from pretending you know shit about this stuff. It’s embarrassing

  41. phoodoo:
    Alan Fox,

    As I have pointed out already Alan, the problem with it is not the silly details about making sure the bag is mixed properly or this and that, it is more fundamental, when you are selecting from an unknown set, you have no way of telling when it is that your selection is a normal sampling or an aberration.

    I’ve recently been contracted for some translation work on behalf of an exploratory drilling company tendering for a contract to investigate the extent and content of a suspected iron ore deposit in Central Africa. The tender is to drill and extract core samples at stipulated points across a large area. It seems to me reasonable to form an opinion as to what might lie under the whole area by extrapolating from 40mm cores a few kilometres apart. It’s sampling, and governments are prepared to pay for it.

    Is what you have pulled a representative sample of what’s inside or it is an anomaly.Is what’s left similar to what has already been seen, or quite different.You can never know the answer to this, and you most certainly can’t even make a good guess by sampling .01 percent, or .000001 percent.

    Disagree. Air samples, water samples. I don’t see the problem.

    How would you know when you just flipped ten heads in a row, of a two sided coin, if you don’t know if the coin has two sides? You don’t.You might just assume it only has one side, because you have never seen the other side. How many flips in a row will tell you if you have a two sided coin-there is no answer to this. And that’s just with two sides. What happens when the coin has 5000 sides? When will you know you have sampled all the sides? Never.

    You can test your estimated calculation of probability by experiment. What is the problem?

    So I find the qualifications about making sure the bag is mixed to be very trivial, and well short of identifying the real problems.

    I agree that it is trivial. It should go without saying that we should, when sampling, take great care that our sample is a representative one. The simplest way to do this is to take another sample and see if results agree.

  42. phoodoo,

    You can never know the answer to this, and you most certainly can’t even make a good guess by sampling .01 percent, or .000001 percent.

    I already explained to you why this is wrong, and I even showed you how the math works.

    Statisticians use sampling routinely, with excellent results. The fact that you are confused about this does not mean that statistics is fatally flawed. It just means that you are confused.

Leave a Reply