Andrew Gelman has an item in his handy statistical lexicon that he calls “The ‘All Else Equal’ Fallacy,” summarized as: Assuming that everything else is held constant, even when it’s not gonna be. Since that idea that “all else is (or would be) equal” is often represented by the Latin ceteris paribus, and the point of Gelman’s fallacy is that (in cases where it applies) the assumption is simply ridiculous (parodic), perhaps we can humorously...

Although the philosophical literature on animal ethics is quite sizable, articles relating to the ethics of animal research only rarely appear in scientific journals, with scientists seldom publishing on the issue in other forums. When such articles from the scientific community do appear, they tend to be short, tend not to substantively engage ethical criticisms and arguments relevant to animal research, and are all too often highly inflammatory. - Rossi & Garner (2018) The above...

Last quarter I gave a presentation in our Introductory Epidemiology course on the late Austin Bradford Hill and his seminal talk on causal inference in population health research. I had a great opportunity to contrast Hill’s original observations with their evaluation by John P. A. Ioannidis and offer my own interpretations. I thought my slides might be useful to others outside our (relatively) small class, so they are posted below, with references at the end....

Conflicts of interest (COIs), financial or otherwise, are obviously a major concern across the scientific process. Although it can be argued that transparent disclosure of one’s interests and affiliations is not the most important goal to pursue (and I might agree), the absence of such disclosure feels (to me) like a reporting deficiency. Of course, all disclosures are not created equal. In terms of completeness, statistician Stephen Senn may take the cake with his declaration...

When I was learning the basics of probability for the first time, I found that I needed to justify the Addition Law of Probability for myself beyond the standard Venn diagram illustration of overlapping sets. This felt unusual, because I’m normally a highly visual learner, but for whatever reason I felt that I needed a more explicit demonstration that the law had to be formulated as it was, rather than fitting the illustration simply by...

I have recently posted my first ever preprint, an essentially finished draft of my essay, “An Introductory Concept of Evidence for Medicine,” to the Open Science Framework’s native preprint server (OSF Preprints). I was surprised it took me as long as it did to find OSF Preprints as a hosting option, which I suppose is simply because I didn’t explore the Center for Open Science (COS) and Open Science Framework (OSF) for myself at first....

“…Harry stared back into the face that had haunted his nightmares for three years. Whiter than a skull, with wide, livid scarlet eyes, and a nose that was as flat as a snake’s, with slits for nostrils...” (Harry Potter and the Goblet of Fire) Brian Earp has a great publication ethics piece in the Spring 2016 HealthWatch UK Newsletter titled “The Unbearable Asymmetry of Bullshit” where he discusses a particular kind of illegitimate scientific publishing...

The latest post over at Bayesian Spectacles, entitled “A Bayesian Perspective on the Proposed FDA Guidelines for Adaptive Clinical Trials,” is of special interest to the medical field. Eric-Jan Wagenmakers, Quentin F. Gronau, Angelika Stefan, Gilles Dutilh, and Felix Schönbrodt comment extensively on the recent draft version of FDA guidelines for this category of more-efficient trial designs. A major hook for this read is available from the beginning: Unfortunately, the FDA document approaches the adaptive...

Following Part 1, here I will discuss the remainder of Chapman’s (2018) editorial regarding the historical review by Fairchild and colleagues (2018). “A Perverse Ethics” In the final section of his editorial, Chapman addresses the question “is it unethical to upset?” He concludes in part with this statement: It is a perverse ethics that sees it as virtuous to keep powerful, life-changing information away from the community simply because it upsets some people. It should...

To my ear, the term “fearmongering” has a pejorative connotation, but in writing this post I was surprised to find that my dictionary did not indicate this in its definition: “the action of deliberately arousing public fear or alarm about a particular issue” (New Oxford American Dictionary) “Fearmongering” would then seem to be a suitable label for the subject of a recent historical review and accompanying commentary in the American Journal of Public Health. The...

Earlier this year Marquardsen and colleagues published a sobering study in the Journal of the Royal Society of Medicine entitled “Redactions in protocols for drug trials: what industry sponsors concealed,” in which the authors requested a number of clinical trial protocols (and any related documents) and surveyed the materials received for censorship. They note at the outset that commercial entities are well-known to be uncomfortable with releasing such materials, often claiming that “they contain commercially...

Alexeyev and colleagues recently published a letter in the British Journal of Dermatology entitled, “Why we continue to the use the name Propionibacterium acnes,” in which they defended retaining this binomial nomenclature in opposition to the recent proposal to reclassify the Propionibacterium genus (Scholz & Kilian, 2016). The proposed reclassification would split the existing Propionibacterium species to genera Acidopropionibacterium, Pseudopropionibacterium, and Cutibacterium, with this last category containing the (in)famous P. acnes firmly implicated in the...

I’ve begun to find it strange when single authors self-refer using “we” in certain circumstances within the academic literature. Certainly it makes sense if one is speaking of oneself and the audience inclusive, in the vein of, “…we shall see that a formal analysis demonstrates the relationships to be identical.” However, I’ve noticed that it’s not uncommon to see single authors use “we” in senses where it clearly refers only to the speaker (writer) and...

It seems to me that a natural extension of the pincushion prior concept is to use the head of the pin to represent the probability mass attributed to the spike. When comparing to spike-and-slab models attributing different masses to the spikes(regardless of the respective slab models), the size of the pinhead can be illustrated such that is proportional to the respective probability mass. Thus, for two spike-and-slab models and given as the areas (A) of...

So-called “spike-and-slab” models are a prominent choice for prior distributions of parameters in Bayesian analysis, consisting of a probability “spike” at a value of a priori interest (often a “null” value) and a “slab” distributing the remaining probability mass across the parameter space. Rouder and colleagues (2018) provide an excellent discussion of these archetypal models in Bayesian analysis, and provide a formulation of the spike-and-slab prior using a Dirac delta “function” to represent the spike...

In these posts, I will log brief thoughts, observations, and the like in a few digestible paragraphs or less. The name “Postscripts” seemed fitting for this series of entries on the blog, and as such titles of posts in this series will begin with P.S. (the obvious play on my initials and the site URL intended).

As “medical” readers might have guessed from the title, this post concerns the nomenclature of microbial resistance testing. For those unfamiliar, panels of antimicrobial compounds are tested against a sample of microbial pathogens (often cultured) from a patient. Technical specifics aside, when this sort of testing is ordered, the managing physician gets a report back that will often divide the tested drugs into groups, with (hopefully) some that will effective against the pathogen on one...

I recently published a correspondence item assessing Adams and O’Reilly’s original article in the Journal of Clinical Epidemiology, which they titled “A likelihood-based approach to P-value interpretation provided a novel, plausible, and clinically useful research study metric.” Adams responded to my critique, but I found that his rebuttals deserved to be addressed and my original criticisms clarified. I have provided the current rejoinder to do so. (Edit June 30, 2018: I have added this manuscript...

Jefferson & Jørgensen recently wrote an interesting editorial in BMJ Evidence-Based Medicine, “Redefining the ‘E’ in EBM,” discussing the nature of evidence and the messy search for it in the current research environment. A couple quotes are worth pulling out: “By the law of Garbage In Garbage Out, whatever we produce in our reviews will be systematically assembled and synthesised garbage with a nice Cochrane logo on it.”

I recently came across a remarkable case report in The American Journal of Medicine concerning a bodybuilder with hypervitaminosis D complicated by hypercalcemia and acute kidney injury, for which the intoxication was attributed to use of a vitamin D-containing dietary protein supplement. (Van et al. 2018) Finding the authors’ discussion intriguing, I offered some thoughts on the matter as a Letter to the Editor. As the Journal declined to publish my commentary, I offer it...

“Carotenodema in Popular Culture” was a brief essay I composed in early 2017. I had previously submitted it to JAMA Dermatology for consideration in their “Notable Notes” section, for which it was promptly rejected. Familiar readers may note that the topic and content of this essay (henceforth simply “Carotenoderma”) are remarkably similar to an essay by Hsiao & Clukay entitled “Orangeness–Peeling Back the Myths Behind Carotenemia” later published in JAMA Dermatol in Sep. 2017.