This article came out on Monday on our Summer Seminar in Philosophy of Statistics in Virginia Tech News Daily magazine.
October 28, 2019
.
From universities around the world, participants in a summer session gathered to discuss the merits of the philosophy of statistics. Co-director Deborah Mayo, left, hosted an evening for them at her home.
11 August 1895 – 12 June 1980
In marking Egon Pearson’s birthday (Aug. 11), I’ll post some Pearson items this week. They will contain some new reflections on older Pearson posts on this blog. Today, I’m posting “Statistical Concepts in Their Relation to Reality” (Pearson 1955). I’ve linked to it several times over the years, but always find a new gem or two, despite its being so short. E. Pearson rejected some of the familiar tenets that have come to be associated with Neyman and Pearson (N-P) statistical tests, notably the idea that the essential justification for tests resides in a long-run control of rates of erroneous interpretations–what he termed the “behavioral” rationale of tests. In an unpublished letter E. Pearson wrote to Birnbaum (1974), he talks about N-P theory admitting of two interpretations: behavioral and evidential:
“I think you will pick up here and there in my own papers signs of evidentiality, and you can say now that we or I should have stated clearly the difference between the behavioral and evidential interpretations. Certainly we have suffered since in the way the people have concentrated (to an absurd extent often) on behavioral interpretations”.
(Nowadays, it might be said that some people concentrate to an absurd extent on “science-wise error rates” in their view of statistical tests as dichotomous screening devices.) Continue reading
Ship StatInfasST
This was published today on the American Philosophical Association blog.
“[C]onfusion about the foundations of the subject is responsible, in my opinion, for much of the misuse of the statistics that one meets in fields of application such as medicine, psychology, sociology, economics, and so forth.” (George Barnard 1985, p. 2)
“Relevant clarifications of the nature and roles of statistical evidence in scientific research may well be achieved by bringing to bear in systematic concert the scholarly methods of statisticians, philosophers and historians of science, and substantive scientists…” (Allan Birnbaum 1972, p. 861).
“In the training program for PhD students, the relevant basic principles of philosophy of science, methodology, ethics and statistics that enable the responsible practice of science must be covered.” (p. 57, Committee Investigating fraudulent research practices of social psychologist Diederik Stapel)
I was the lone philosophical observer at a special meeting convened by the American Statistical Association (ASA) in 2015 to construct a non-technical document to guide users of statistical significance tests–one of the most common methods used to distinguish genuine effects from chance variability across a landscape of social, physical and biological sciences.
It was, by the ASA Director’s own description, “historical”, but it was also highly philosophical, and its ramifications are only now being discussed and debated. Today, introspection on statistical methods is rather common due to the “statistical crisis in science”. What is it? In a nutshell: high powered computer methods make it easy to arrive at impressive-looking ‘findings’ that too often disappear when others try to replicate them when hypotheses and data analysis protocols are required to be fixed in advance.
E.S. Pearson: 11 Aug 1895-12 June 1980.
Today is Egon Pearson’s birthday. In honor of his birthday, I am posting “Statistical Concepts in Their Relation to Reality” (Pearson 1955). I’ve posted it several times over the years, but always find a new gem or two, despite its being so short. E. Pearson rejected some of the familiar tenets that have come to be associated with Neyman and Pearson (N-P) statistical tests, notably the idea that the essential justification for tests resides in a long-run control of rates of erroneous interpretations–what he termed the “behavioral” rationale of tests. In an unpublished letter E. Pearson wrote to Birnbaum (1974), he talks about N-P theory admitting of two interpretations: behavioral and evidential:
“I think you will pick up here and there in my own papers signs of evidentiality, and you can say now that we or I should have stated clearly the difference between the behavioral and evidential interpretations. Certainly we have suffered since in the way the people have concentrated (to an absurd extent often) on behavioral interpretations”.
.
Below are the slides from my June 14 presentation at the X-Phil conference on Reproducibility and Replicability in Psychology and Experimental Philosophy at University College London. What I think must be examined seriously are the “hidden” issues that are going unattended in replication research and related statistics wars. An overview of the “hidden controversies” are on slide #3. Although I was presenting them as “hidden”, I hoped they wouldn’t be quite as invisible as I found them through the conference. (Since my talk was at the start, I didn’t know what to expect–else I might have noted some examples that seemed to call for further scrutiny). Exceptions came largely (but not exclusively) from a small group of philosophers (me, Machery and Fletcher). Then again,there were parallel sessions, so I missed some. However, I did learn something about X-phil, particularly from the very interesting poster session [1]. This new area should invite much, much more scrutiny of statistical methodology from philosophers of science.
[1] The women who organized and ran the conference did an excellent job: Lara Kirfel, a psychology PhD student at UCL, and Pascale Willemsen from Ruhr University.
27 May 1923-1 July 1976
Today is Allan Birnbaum’s Birthday. Birnbaum’s (1962) classic “On the Foundations of Statistical Inference,” in Breakthroughs in Statistics (volume I 1993), concerns a principle that remains at the heart of today’s controversies in statistics–even if it isn’t obvious at first: the Likelihood Principle (LP) (also called the strong likelihood Principle SLP, to distinguish it from the weak LP [1]). According to the LP/SLP, given the statistical model, the information from the data are fully contained in the likelihood ratio. Thus, properties of the sampling distribution of the test statistic vanish (as I put it in my slides from this post)! But error probabilities are all properties of the sampling distribution. Thus, embracing the LP (SLP) blocks our error statistician’s direct ways of taking into account “biasing selection effects” (slide #10). [Posted earlier here.] Interesting, as seen in a 2018 post on Neyman, Neyman did discuss this paper, but had an odd reaction that I’m not sure I understand. (Check it out.) Continue reading
.
“If a statistical analysis is clearly shown to be effective … it gains nothing from being … principled,” according to Terry Speed in an interesting IMS article (2016) that Harry Crane tweeted about a couple of days ago [i]. Crane objects that you need principles to determine if it is effective, else it “seems that a method is effective (a la Speed) if it gives the answer you want/expect.” I suspected that what Speed was objecting to was an appeal to “principles of inference” of the type to which Neyman objected in my recent post. This turns out to be correct. Here are some excerpts from Speed’s article (emphasis is mine): Continue reading
.A world beyond p-values?
I was asked to write something explaining the background of my slides (posted here) in relation to the recent ASA “A World Beyond P-values” conference. I took advantage of some long flight delays on my return to jot down some thoughts:
The contrast between the closing session of the conference “A World Beyond P-values,” and the gist of the conference itself, shines a light on a pervasive tension within the “Beyond P-Values” movement. Two very different debates are taking place. First there’s the debate about how to promote better science. This includes welcome reminders of the timeless demands of rigor and integrity required to avoid deceiving ourselves and others–especially crucial in today’s world of high-powered searches and Big Data. That’s what the closing session was about. [1] Continue reading
G.A. Barnard: 23 Sept.1915 – 9 Aug.2002
Today is George Barnard’s birthday. I met him in the 1980s and we corresponded off and on until 1999. Here’s a snippet of his discussion with Savage (1962) (link below [i]) that connects to issues often taken up on this blog: stopping rules and the likelihood principle. (It’s a slightly revised reblog of an earlier post.) I’ll post some other items related to Barnard this week, in honor of his birthday.
Happy Birthday George!
Barnard: I have been made to think further about this issue of the stopping rule since I first suggested that the stopping rule was irrelevant (Barnard 1947a,b). This conclusion does not follow only from the subjective theory of probability; it seems to me that the stopping rule is irrelevant in certain circumstances. Since 1947 I have had the great benefit of a long correspondence—not many letters because they were not very frequent, but it went on over a long time—with Professor Bartlett, as a result of which I am considerably clearer than I was before. My feeling is that, as I indicated [on p. 42], we meet with two sorts of situation in applying statistics to data One is where we want to have a single hypothesis with which to confront the data. Do they agree with this hypothesis or do they not? Now in that situation you cannot apply Bayes’s theorem because you have not got any alternatives to think about and specify—not yet. I do not say they are not specifiable—they are not specified yet. And in that situation it seems to me the stopping rule is relevant. Continue reading
E.S. Pearson: 11 Aug 1895-12 June 1980.
Here’s one last entry in honor of Egon Pearson’s birthday: “Statistical Concepts in Their Relation to Reality” (Pearson 1955). I’ve posted it several times over the years (6!), but always find a new gem or two, despite its being so short. E. Pearson rejected some of the familiar tenets that have come to be associated with Neyman and Pearson (N-P) statistical tests, notably the idea that the essential justification for tests resides in a long-run control of rates of erroneous interpretations–what he termed the “behavioral” rationale of tests. In an unpublished letter E. Pearson wrote to Birnbaum (1974), he talks about N-P theory admitting of two interpretations: behavioral and evidential:
“I think you will pick up here and there in my own papers signs of evidentiality, and you can say now that we or I should have stated clearly the difference between the behavioral and evidential interpretations. Certainly we have suffered since in the way the people have concentrated (to an absurd extent often) on behavioral interpretations”.
(Nowadays, some people concentrate to an absurd extent on “science-wise error rates in dichotomous screening”.) Continue reading
27 May 1923-1 July 1976
Today is Allan Birnbaum’s birthday. In honor of his birthday, I’m posting the articles in the Synthese volume that was dedicated to his memory in 1977. The editors describe it as their way of “paying homage to Professor Birnbaum’s penetrating and stimulating work on the foundations of statistics”. I paste a few snippets from the articles by Giere and Birnbaum. If you’re interested in statistical foundations, and are unfamiliar with Birnbaum, here’s a chance to catch up. (Even if you are, you may be unaware of some of these key papers.)
HAPPY BIRTHDAY ALLAN!
Synthese Volume 36, No. 1 Sept 1977: Foundations of Probability and Statistics, Part I
Editorial Introduction:
This special issue of Synthese on the foundations of probability and statistics is dedicated to the memory of Professor Allan Birnbaum. Professor Birnbaum’s essay ‘The Neyman-Pearson Theory as Decision Theory; and as Inference Theory; with a Criticism of the Lindley-Savage Argument for Bayesian Theory’ was received by the editors of Synthese in October, 1975, and a decision was made to publish a special symposium consisting of this paper together with several invited comments and related papers. The sad news about Professor Birnbaum’s death reached us in the summer of 1976, but the editorial project could nevertheless be completed according to the original plan. By publishing this special issue we wish to pay homage to Professor Birnbaum’s penetrating and stimulating work on the foundations of statistics. We are grateful to Professor Ronald Giere who wrote an introductory essay on Professor Birnbaum’s concept of statistical evidence and who compiled a list of Professor Birnbaum’s publications.
THE EDITORS
Slides from my March 17 presentation on “Severe Testing: The Key to Error Correction” given at the Boston Colloquium for Philosophy of Science Alfred I.Taub forum on “Understanding Reproducibility and Error Correction in Science.”
Download the 57th Annual Program
The Alfred I. Taub forum:
UNDERSTANDING REPRODUCIBILITY & ERROR CORRECTION IN SCIENCE
Cosponsored by GMS and BU’s BEST at Boston University.
Friday, March 17, 2017
1:00 p.m. – 5:00 p.m.
The Terrace Lounge, George Sherman Union
775 Commonwealth Avenue
Objectivity in statistics, as in science more generally, is a matter of both aims and methods. Objective science, in our view, aims to find out what is the case as regards aspects of the world [that hold] independently of our beliefs, biases and interests; thus objective methods aim for the critical control of inference and hypotheses, constraining them by evidence and checks of error. (Cox and Mayo 2010, p. 276)
I. The myth of objectivity. Whenever you come up against blanket slogans such as “no methods are objective” or “all methods are equally objective and subjective,” it is a good guess that the problem is being trivialized into oblivion. Yes, there are judgments, disagreements, and values in any human activity, which alone makes it too trivial an observation to distinguish among very different ways that threats of bias and unwarranted inferences may be controlled. Is the objectivity-subjectivity distinction really toothless as many will have you believe? I say no.
Cavalier attitudes toward objectivity are in tension with widely endorsed movements to promote replication, reproducibility, and to come clean on a number of sources behind illicit results: multiple testing, cherry picking, failed assumptions, researcher latitude, publication bias and so on. The moves to take back science–if they are not mere lip-service–are rooted in the supposition that we can more objectively scrutinize results,even if it’s only to point out those that are poorly tested. The fact that the term “objectivity” is used equivocally should not be taken as grounds to oust it, but rather to engage in the difficult work of identifying what there is in “objectivity” that we won’t give up, and shouldn’t. Continue reading
Allan Birnbaum: May 27, 1923- July 1, 1976
Allan Birnbaum died 40 years ago today. He lived to be only 53 [i]. From the perspective of philosophy of statistics and philosophy of science, Birnbaum is best known for his work on likelihood, the Likelihood Principle [ii], and for his attempts to blend concepts of likelihood with error probability ideas to arrive at what he termed “concepts of statistical evidence”. Failing to find adequate concepts of statistical evidence, Birnbaum called for joining the work of “interested statisticians, scientific workers and philosophers and historians of science”–an idea I have heartily endorsed. While known for a result that the (strong) Likelihood Principle followed from sufficiency and conditionality principles (a result that Jimmy Savage deemed one of the greatest breakthroughs in statistics), a few years after publishing it, he turned away from it, perhaps discovering gaps in his argument. A post linking to a 2014 Statistical Science issue discussing Birnbaum’s result is here. Reference [5] links to the Synthese 1977 volume dedicated to his memory. The editors describe it as their way of “paying homage to Professor Birnbaum’s penetrating and stimulating work on the foundations of statistics”. Ample weekend reading! Continue reading
27 May 1923-1 July 1976
Today is Allan Birnbaum’s birthday. In honor of his birthday this year, I’m posting the articles in the Synthese volume that was dedicated to his memory in 1977. The editors describe it as their way of “paying homage to Professor Birnbaum’s penetrating and stimulating work on the foundations of statistics”. I paste a few snippets from the articles by Giere and Birnbaum. If you’re interested in statistical foundations, and are unfamiliar with Birnbaum, here’s a chance to catch up.(Even if you are,you may be unaware of some of these key papers.)
HAPPY BIRTHDAY ALLAN!
Synthese Volume 36, No. 1 Sept 1977: Foundations of Probability and Statistics, Part I
Editorial Introduction:
This special issue of Synthese on the foundations of probability and statistics is dedicated to the memory of Professor Allan Birnbaum. Professor Birnbaum’s essay ‘The Neyman-Pearson Theory as Decision Theory; and as Inference Theory; with a Criticism of the Lindley-Savage Argument for Bayesian Theory’ was received by the editors of Synthese in October, 1975, and a decision was made to publish a special symposium consisting of this paper together with several invited comments and related papers. The sad news about Professor Birnbaum’s death reached us in the summer of 1976, but the editorial project could nevertheless be completed according to the original plan. By publishing this special issue we wish to pay homage to Professor Birnbaum’s penetrating and stimulating work on the foundations of statistics. We are grateful to Professor Ronald Giere who wrote an introductory essay on Professor Birnbaum’s concept of statistical evidence and who compiled a list of Professor Birnbaum’s publications.
THE EDITORS
27 May 1923-1 July 1976
Today is Allan Birnbaum’s Birthday. Birnbaum’s (1962) classic “On the Foundations of Statistical Inference,” in Breakthroughs in Statistics (volume I 1993), concerns a principle that remains at the heart of today’s controversies in statistics–even if it isn’t obvious at first: the Likelihood Principle (LP) (also called the strong likelihood Principle SLP, to distinguish it from the weak LP [1]). According to the LP/SLP, given the statistical model, the information from the data are fully contained in the likelihood ratio. Thus, properties of the sampling distribution of the test statistic vanish (as I put it in my slides from my last post)! But error probabilities are all properties of the sampling distribution. Thus, embracing the LP (SLP) blocks our error statistician’s direct ways of taking into account “biasing selection effects” (slide #10).
Intentions is a New Code Word: Where, then, is all the information regarding your trying and trying again, stopping when the data look good, cherry picking, barn hunting and data dredging? For likelihoodists and other probabilists who hold the LP/SLP, it is ephemeral information locked in your head reflecting your “intentions”! “Intentions” is a code word for “error probabilities” in foundational discussions, as in “who would want to take intentions into account?” (Replace “intentions” (or the “researcher’s intentions”) with “error probabilities” (or the method’s error probabilities”) and you get a more accurate picture.) Keep this deciphering tool firmly in mind as you read criticisms of methods that take error probabilities into account[2]. For error statisticians, this information reflects real and crucial properties of your inference procedure.
Memory Lane: 3 years ago. Oxford Jail (also called Oxford Castle) is an entirely fitting place to be on (and around) Halloween! Moreover, rooting around this rather lavish set of jail cells (what used to be a single cell is now a dressing room) is every bit as conducive to philosophical reflection as is exile on Elba! (It is now a boutique hotel, though many of the rooms are still too jail-like for me.) My goal (while in this gaol—as the English sometimes spell it) is to try and free us from the bogeymen and bogeywomen often associated with “classical” statistics. As a start, the very term “classical statistics” should, I think, be shelved, not that names should matter.
In appraising statistical accounts at the foundational level, we need to realize the extent to which accounts are viewed through the eyeholes of a mask or philosophical theory. Moreover, the mask some wear while pursuing this task might well be at odds with their ordinary way of looking at evidence, inference, and learning. In any event, to avoid non-question-begging criticisms, the standpoint from which the appraisal is launched must itself be independently defended. But for (most) Bayesian critics of error statistics the assumption that uncertain inference demands a posterior probability for claims inferred is thought to be so obvious as not to require support. Critics are implicitly making assumptions that are at odds with the frequentist statistical philosophy. In particular, they assume a certain philosophy about statistical inference (probabilism), often coupled with the allegation that error statistical methods can only achieve radical behavioristic goals, wherein all that matters are long-run error rates (of some sort)
Criticisms then follow readily: the form of one or both:
Abbreviated Table of Contents:
Here are some items for your Saturday-Sunday reading.
Link to complete discussion:
Mayo, Deborah G. On the Birnbaum Argument for the Strong Likelihood Principle (with discussion & rejoinder). Statistical Science 29 (2014), no. 2, 227-266.
Links to individual papers:
Mayo, Deborah G. On the Birnbaum Argument for the Strong Likelihood Principle. Statistical Science 29 (2014), no. 2, 227-239.
Dawid, A. P. Discussion of “On the Birnbaum Argument for the Strong Likelihood Principle”. Statistical Science 29 (2014), no. 2, 240-241.
Evans, Michael. Discussion of “On the Birnbaum Argument for the Strong Likelihood Principle”. Statistical Science 29 (2014), no. 2, 242-246.
Martin, Ryan; Liu, Chuanhai. Discussion: Foundations of Statistical Inference, Revisited. Statistical Science 29 (2014), no. 2, 247-251.
Fraser, D. A. S. Discussion: On Arguments Concerning Statistical Principles. Statistical Science 29 (2014), no. 2, 252-253.
Hannig, Jan. Discussion of “On the Birnbaum Argument for the Strong Likelihood Principle”. Statistical Science 29 (2014), no. 2, 254-258.
Bjørnstad, Jan F. Discussion of “On the Birnbaum Argument for the Strong Likelihood Principle”. Statistical Science 29 (2014), no. 2, 259-260.
Mayo, Deborah G. Rejoinder: “On the Birnbaum Argument for the Strong Likelihood Principle”. Statistical Science 29 (2014), no. 2, 261-266.
Abstract: An essential component of inference based on familiar frequentist notions, such as p-values, significance and confidence levels, is the relevant sampling distribution. This feature results in violations of a principle known as the strong likelihood principle (SLP), the focus of this paper. In particular, if outcomes x∗ and y∗ from experiments E1 and E2 (both with unknown parameter θ), have different probability models f1( . ), f2( . ), then even though f1(x∗; θ) = cf2(y∗; θ) for all θ, outcomes x∗ and y∗may have different implications for an inference about θ. Although such violations stem from considering outcomes other than the one observed, we argue, this does not require us to consider experiments other than the one performed to produce the data. David Cox [Ann. Math. Statist. 29 (1958) 357–372] proposes the Weak Conditionality Principle (WCP) to justify restricting the space of relevant repetitions. The WCP says that once it is known which Ei produced the measurement, the assessment should be in terms of the properties of Ei. The surprising upshot of Allan Birnbaum’s [J.Amer.Statist.Assoc.57(1962) 269–306] argument is that the SLP appears to follow from applying the WCP in the case of mixtures, and so uncontroversial a principle as sufficiency (SP). But this would preclude the use of sampling distributions. The goal of this article is to provide a new clarification and critique of Birnbaum’s argument. Although his argument purports that [(WCP and SP), entails SLP], we show how data may violate the SLP while holding both the WCP and SP. Such cases also refute [WCP entails SLP].
Key words: Birnbaumization, likelihood principle (weak and strong), sampling theory, sufficiency, weak conditionality
Regular readers of this blog know that the topic of the “Strong Likelihood Principle (SLP)” has come up quite frequently. Numerous informal discussions of earlier attempts to clarify where Birnbaum’s argument for the SLP goes wrong may be found on this blog. [SEE PARTIAL LIST BELOW.[i]] These mostly stem from my initial paper Mayo (2010) [ii]. I’m grateful for the feedback.
In the months since this paper has been accepted for publication, I’ve been asked, from time to time, to reflect informally on the overall journey: (1) Why was/is the Birnbaum argument so convincing for so long? (Are there points being overlooked, even now?) (2) What would Birnbaum have thought? (3) What is the likely upshot for the future of statistical foundations (if any)?
I’ll try to share some responses over the next week. (Naturally, additional questions are welcome.)
[i] A quick take on the argument may be found in the appendix to: “A Statistical Scientist Meets a Philosopher of Science: A conversation between David Cox and Deborah Mayo (as recorded, June 2011)”
UPhils and responses
.
1.An Assumed Law of Statistical Evidence (law of likelihood)
Nearly all critical discussions of frequentist error statistical inference (significance tests, confidence intervals, p- values, power, etc.) start with the following general assumption about the nature of inductive evidence or support:
Data x are better evidence for hypothesis H1 than for H0 if x are more probable under H1 than under H0.
Ian Hacking (1965) called this the logic of support: x supports hypotheses H1 more than H0 if H1 is more likely, given x than is H0:
Pr(x; H1) > Pr(x; H0).
[With likelihoods, the data x are fixed, the hypotheses vary.]*
Or,
x is evidence for H1 over H0 if the likelihood ratio LR (H1 over H0 ) is greater than 1.
It is given in other ways besides, but it’s the same general idea. (Some will take the LR as actually quantifying the support, others leave it qualitative.)
In terms of rejection:
“An hypothesis should be rejected if and only if there is some rival hypothesis much better supported [i.e., much more likely] than it is.” (Hacking 1965, 89)
2. Barnard (British Journal of Philosophy of Science )
But this “law” will immediately be seen to fail on our minimal severity requirement. Hunting for an impressive fit, or trying and trying again, it’s easy to find a rival hypothesis H1 much better “supported” than H0 even when H0 is true. Or, as Barnard (1972) puts it, “there always is such a rival hypothesis, viz. that things just had to turn out the way they actually did” (1972 p. 129). H0: the coin is fair, gets a small likelihood (.5)k given k tosses of a coin, while H1: the probability of heads is 1 just on those tosses that yield a head, renders the sequence of k outcomes maximally likely. This is an example of Barnard’s “things just had to turn out as they did”. Or, to use an example with P-values: a statistically significant difference, being improbable under the null H0 , will afford high likelihood to any number of explanations that fit the data well.
3.Breaking the law (of likelihood) by going to the “second,” error statistical level:
How does it fail our severity requirement? First look at what the frequentist error statistician must always do to critique an inference: she must consider the capability of the inference method that purports to provide evidence for a claim. She goes to a higher level or metalevel, as it were. In this case, the likelihood ratio plays the role of the needed statistic d(X). To put it informally, she asks:
What’s the probability the method would yield an LR disfavoring H0 compared to some alternative H1 even if H0 is true?
