William M Briggs

Pope Francis unfolds his outlook on climate change in Laudato Si (2015) and Laudate Deum (2023). We reflect on both encyclicals, though we do not assess the scientific information on climate change as such. Instead, we examine the Pope’s use and understanding of models, and delve deeper into the overarching philosophy that sustains the encyclicals...

Jaynes work on probability theory, which he rightly called the logic of science, needs to be better known. We attempt this in showing how logical probability can be used to analyze how opinions can grow farther apart, even when people agree on new evidence. This has important consequences in medicine, economics, and really any area in which people...

Purpose This study aims to find suitable replacements for hypothesis testing and variable-importance measures. Design/methodology/approach This study explores under-used predictive methods. Findings The study's hypothesis testing can and should be replaced by predictive methods. It is the only way to know if models have any value. Originality/va...

We investigate what makes a good model. Simple measures like unconditional predictive ability on past observations, or parameter estimation fail. Ideally the truth or high probability of model constituents, based on accepted assumptions, along with predictive ability, are what make a model good. The best model is one in which the complete cause of...

Background: The COVID-19 pandemic profoundly affected healthcare services, including HIV patient care. This study assessed the impact of the pandemic on diverse aspects of care for individuals living with HIV (PLWH). Methods: Patient data from 2019 to 2021 were collected using the Cascades template, provided by the New York State Department of Heal...

Dit schrijven is gemotiveerd door de manier waarop de Raad van State (RvS) het woord "significant" gebruikt in belangrijke stikstof-uitspraken. Dit woord wordt tientallen malen gebruikt in drie uitspraken die de onderzoekers van dit artikel hebben bestudeerd. Middels een uitgebreide analyse van de auteurs blijkt dat de RvS in haar stikstofuitsprake...

We review the paper “Causal emergence is widespread across measures of causation” by Renzo Comolatti and Erik Hoel, which purports to derive (automatic) mathematical formula, which are not entirely probability based, to discover cause. We disagree with the paper’s central arguments, show where they are flawed, and argue that cause is much more diff...

A statistical analysis was applied to Northern Hemisphere land surface temperatures (1850–2018) to try to identify the main drivers of the observed warming since the mid-19th century. Two different temperature estimates were considered—a rural and urban blend (that matches almost exactly with most current estimates) and a rural-only estimate. The r...

Background Black adults have higher incidence of all-cause death and worse cardiovascular outcomes when compared to other populations. The Duffy chemokine receptor is not expressed in a large majority of Black adults and the clinical implications of this are unclear. Methods Here, we investigated the relationship of Duffy receptor status, high-sen...

Purpose Important research once thought unassailable has failed to replicate. Not just in economics, but in all science. The problem is therefore not in dispute nor are some of the causes, like low power, selective reporting, the file drawer effect, publicly unavailable data and so forth. Some partially worthy solutions have already been offered, l...

We present a simple, superior method for estimating the upstream to downstream differences in nitrate and chlorine in a well studied catchment in the Netherlands, using data from the Water Board in Vechtstromen, from 1985 to 2018, in answer to a paper by Kaandorp et al. (2021). Agricultural sites are mostly downstream; nevertheless, less nitrate, a...

In dit document leggen ondergetekenden een aantal vragen voor aan de Raad van State (RvS) die betrekking hebben op uitspraken gedaan door dit college omtrent het stikstofbeleid. Deze vragen richten zich specifiek op het verstaan van het programma AERIUS(OPS), het gebruik van kritische depositiewaarden, het gebruik van het voorzorgbeginsel en het ve...

The RIVM responded to our paper“Criticizing AERIUS/OPS model performance”. We rebut those critiques below. In brief: RIVM agrees that OPS performs poorly in the short term, but believes it performs well over long periods. Yet they failed to address our demonstration on how averaging over these longer terms can cause spurious “good results.” That i...

We investigate the AERIUS/OPS model predictive skill. It has none compared to a simple “mean” model. Skill is the demonstrated superiority of one model over another, given specific verification mea- sures. OPS does not have skill compared to a simple “mean” model, which beats OPS using some measures. Further, the verification measures used are them...

Background Publications are an important component of academic careers.AimsWe investigated the financial costs to authors for submitting and publishing manuscripts in gastroenterology (GI) journals in the United States (US), United Kingdom (UK), and elsewhere.Methods This was a cross-sectional study carried out from 11/1/2020 to 12/31/2020. We used...

This article evaluates the pregnancy experiences of American women by comparing their spontaneous or non-surrogate pregnancies with their gestational surrogate pregnancies. Data were collected through structured interviews using an online video platform. In total, 96 interviews were conducted. Data revealed that a woman was more likely to have a pr...

A brief survey of the strategies used to produce coronavirus forecasts. And a detailed look at the Imperial College of London death forecast that was responsible for the start of the panic. It was shockingly unrealistic but presented in a way its flaws were not easily seen. Forecasts improved after that, but by then it was too late.

The skill of a model is defined as its ability to predict better than a simpler or default model. These default models almost always exist. Models without skill should not be used. All predictions are based on models, tacit or formal. Predictions to be useful must therefore be skillful. Some predictions are influential in the sense that the observa...

Nitrogen Critical Loads (NCL), as purported ecological dose-response outcomes for nitrogen deposition from anthropogenic sources, play a central role in environmental policies around the world. In the Netherlands, these NCL are used to assess, via calculations using the model AERIUS, to what extent NCL are exceeded for different habitats as a resul...

This short note is a reminder that all models only say what they are told to say. There can therefore be no discovery by models—discoveries go into models—and thus models should only be used in their predictive form, and only trusted when they have demonstrated independent success.

Introduction Determine the consistency, accessibility, and adequacy of parental leave policies for adult and pediatric medicine fellowship programs. Methods We administered a 40-question survey to fellowship program directors (PDs) and trainees in adult and pediatric cardiology, hematology/oncology, gastroenterology, and pulmonology/critical care...

Purpose: To evaluate the retrospective pregnancy experiences of American women by comparing spontaneous pregnancies with gestational surrogate pregnancies. Methods: Data were collected via structured interviews following an approved survey tool utilizing an online video platform. In total, 97 interviews were conducted. Results: Demographic data was...

Purpose To evaluate reviewers’ timeliness and review quality for the International Journal of Radiation Oncology, Biology, and Physics (IJROBP) by sex and seniority. Methods and Materials The IJROBP editorial office provided data on 3962 individuals invited to review manuscripts from 2011 through 2014. We identified 1657 reviewers who had been inv...

Classical probability and the statistical methods built around it, like hypothesis testing, have been shown to have many glaring weaknesses, as the work of Hung Nguyen has shown with clarity and vigor. It is time for a major renovation in probability. The need for new methods is pressing. Older ways of thinking about probability and decision are in...

There is no reason to use traditional hypothesis testing. If one’s goal is to assess past performance of a model, then a simple measure or performance with no uncertainty will do. If one’s goal is to ascertain cause, then because probability models can’t identify cause, testing does not help. If one’s goal is to decide in the face of uncertainty, t...

The reason probability models are used is to characterize uncertainty in observables. Typically, certainty in the parameters of fitted models based on their parametric posterior distributions is much greater than the predictive uncertainty of new (unknown) observables. Consequently, when model results are reported, uncertainty in the observable sho...

Objectives: Investigate whether or not race is associated with differences in hospitalization and survival to discharge among patients with coronavirus disease-2019 (COVID-19) at the height of the pandemic in New York City (NYC). Methods: Single-center retrospective cohort study of COVID-19 patients hospitalized at our university-affiliated NYC...

Background/aims: Studies comparing the utility of endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) and endoscopic ultrasound-guided fine needle biopsy (EUS-FNB) for solid pancreatic lesions have been inconclusive with no clear superiority. The aim of this meta-analysis was to compare the diagnostic accuracy and safety between the two...

INTRODUCTION Acute portal vein thrombosis (PVT) is a rare diagnosis frequently associated with cirrhosis. Clinical presentation is typically nonspecific with potentially catastrophic short-term complications including sepsis, bowel infarction, and death. Management strategies differ for acute and chronic PVT. Guidelines for treating acute PVT recom...

INTRODUCTION Treatment options for pancreatic cancer are well-established, but patients do not necessarily receive the same treatments for various reasons including unequal access to care, differences in medical literacy, or cultural barriers. We investigated whether or not disparities existed in the management of pancreatic cancer based on sex and...

INTRODUCTION Palliative care is integral to cancer treatment. Our goal was to investigate the frequency of palliative care service contact for colon cancer patients and factors associated with their involvement. METHODS We carried out a retrospective analysis of all colon cancer patients diagnosed at our university-affiliated hospital between 1/1/...

We propose two simple fixes to the Ryden and McNeil ammonia flux model. These are necessary to prevent estimates from becoming unphysical, which very often happens and which has not yet been noted in the literature. The first fix is to constrain the limits of certain of the model's parameters; without this limit, estimates from the model are seen t...

We investigate trend identification in the LML and MAN atmospheric ammonia data. The signals are mixed in the LML data, with just as many positive, negative, and no trends found. The start date for trend identification is crucial, with the trends claimed changing sign and significance depending on the start date. The MAN data is calibrated to the L...

e23101 Background: Palliative care is integral to cancer treatment. Our goal was to investigate the factors associated with palliative care service involvement for hospitalized colon cancer patients. Methods: We carried out a retrospective study of all colon cancer patients diagnosed and hospitalized at our institution from 1/1/2010 through 12/31/2...

Background: Endoscopic ultrasound-guided cystogastrostomy has become the first-line treatment for symptomatic peripancreatic fluid collections. The aim of this study is to analyze the efficacy and safety of cystogastrostomy via a meta-analysis of the literature. Methods: We performed a systematic search of PubMed and Medline databases for studie...

Background Esophageal cancer (EC) has a dismal prognosis with 5-year survival < 19%. Black patients with EC have higher mortality than white patients, but the cause of this disparity is unclear. We sought to investigate the impact of race upon overall mortality (OM) among EC patients at our institution. Methods We performed a single-center retrosp...

Objectives: Adult Onset Still's Disease (AOSD) is a rare autoinflammatory disorder. There is relatively little known about the impact of social determinants of health on its outcomes. Our goal is to describe the racial/ethnic variations, morbidity and mortality of AOSD hospitalized patients in the US. Materials and methods: Adult US hospitalized...

P-values should not be used. They have no justification under frequentist theory; they are pure acts of will. Arguments justifying p-values are fallacious. P-values are not used to make all decisions about a model, where in some cases judgment overrules p-values. There is no justification for this in frequentist theory. Hypothesis testing cannot id...

Classical hypothesis testing, whether with p-values or Bayes factors, leads to over-certainty, and produces the false idea that causes have been identified via statistical methods. The limitations and abuses of in particular p-values are so well known and by now so egregious, that a new method is badly in need. We propose returning to an old idea,...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = .05 to .005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significance tes...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = .05 to .005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significance tes...

Background There is a dearth of epidemiological studies on Adult Onset Still’s Disease (AOSD). Majority of studies are from single centres or are regional. The largest AOSD epidemiological study till date describes 512 patients.¹ Objectives To describe the demographics, complications, mortality and trends of hospitalised patients with AOSD in Unit...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = 0.05 to p = 0.005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significan...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = 0.05 to p = 0.005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significan...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = 0.05 to p = 0.005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significan...

We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = .05 to .005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significance tes...

Classical statistical approaches used widely in econometrics centering around parameter estimation, hypothesis testing, and p-values should be abandoned. In their place, predictive modeling should be used. A predictive model answer the question all users of statistics have: if I change x, or leave it out of my model, what does this do to the uncert...

We argue that depending on p-values to reject null hypotheses, including a recent call for changing the canonical alpha level for statistical significance from .05 to .005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable criterion levels both are problematic, it is sensible to dispense...

Background: Presence of prominent left ventricular trabeculation satisfying criteria for left ventricular noncompaction (LVNC) on routine cardiac magnetic resonance examination is frequently encountered; however, the clinical and prognostic significance of these findings remain elusive. This registry aimed to assess LVNC prevalence by 4 current cr...

If it was not obvious before, after reading McShane and Gal, the conclusion is that p-values should be proscribed. There are no good uses for them; indeed, every use either violates frequentist theory, is fallacious, or is based on a misunderstanding. A replacement for p-values is suggested, based on predictive models.

Background There is a dearth of epidemiological studies in the US and worldwide on Adult Onset Still's Disease (AOSD). Currently, there is no consensus on its incidence and prevalence in different populations. Most studies report a majority of patients below the age of 35.[1] Objectives To describe the demographics, complications and mortality of...

De focus van onderliggend onderzoek ligt op ammoniakemissies bij bemesting en op trends in atmosfeer- concentraties. Daartoe hebben we van de Wageningen University & Research (WUR) enkele meetreeksen van bemestingsproeven ontvangen (overigens zonder vermelding van spreiding van meetdata en meetonzekerheid) tezamen met het rekenmodel om die metingen...

Context Over the past three decades, industry sponsored research expanded in the United States. Financial incentives can lead to potential conflicts of interest (COI) resulting in underreporting of negative study results. Objective We hypothesized that over the three decades, there would be an increase in: a) reporting of conflict of interest and...

Studies published in NEJM. Raw data NEJM. (XLS)

Studies published in LANCET. Raw data LANCET. (XLS)

Systematic review checklist. PRISMA 2009 checklist. (DOC)

Studies published in JAMA Raw data JAMA. (XLS)

Cause is analogical. There is not one type, flavor, or aspect of cause, but four. A formal, material, efficient, and final or teleological. Most causation concerns events which occur not separately, as in this before that, but simultaneously, where simultaneous events can be spread through time. Many causal data are embedded in time, and there two...

Logic is not an ontological property of things. You cannot, for instance, extract a syllogism from the existence of an object; the imagined syllogism is not somehow buried deep in the folds of the object waiting to be measured by some sophisticated apparatus. Logic is the relation between propositions, and these relations are not physical. A buildi...

Background: Recent studies suggest that papillary muscle infarction (PMI) following recent myocardial infarction (MI) correlates with adverse cardiovascular outcomes. The purpose of this study is to determine the prevalence and prognostic significance of PMI by cardiac magnetic resonance (CMR) in a large cohort of patients. Methods: Retrospectiv...

This book presents a philosophical approach to probability and probabilistic thinking, considering the underpinnings of probabilistic reasoning and modeling, which effectively underlie everything in data science. The ultimate goal is to call into question many standard tenets and lay the philosophical and probabilistic groundwork and infrastructure...

Objective: To assess the added value of pulmonary function tests (PFTs) and different classifications of chronic obstructive pulmonary disease (COPD) to the Society of Thoracic Surgeons (STS) risk model using a clinical definition of lung disease for predicting outcomes after cardiothoracic (CT) surgery. Methods: We evaluated consecutive patient...

Richardson et al. (Sci Bull, 2015. doi:10.1007/s11434-015-0806-z) suggest that the irreducibly simple climate model described in Monckton of Brenchley et al. (Sci Bull 60:122–135, 2015. doi:10.1007/s11434-014-0699-2) was not validated against observations, relying instead on synthetic test data based on underestimated global warming, illogical para...

There is a third way of implementing probability models and practicing. This is to answer questions put in terms of observables. This eliminates frequentist hypothesis testing and Bayes factors and it also eliminates parameter estimation. The Third Way is the logical probability approach, which is to make statements $\Pr(Y \in y | X,D,M)$ about obs...

Probability models are only useful at explaining the uncertainty of what we do not know, and should never be used to say what we already know. Probability and statistical models are useless at discerning cause. Classical statistical procedures, in both their frequentist and Bayesian implementations are, falsely imply they can speak about cause. No...

Agnotology is the study of how ignorance arises via circulation of misinformation calculated to mislead. Legates et al. (Sci Educ 22:2007-2017, 2013) had questioned the applicability of agnotology to politically-charged debates. In their reply, Bedford and Cook (Sci Educ 22:2019-2030, 2013), seeking to apply agnotology to climate science, asserted...

The so-called problem of grue was introduced by Nelson Goodman in 1954 as a "riddle" about induction, a riddle which has been widely thought to cast doubt on the validity and rationality of induction. That unnecessary doubt in turn is partly responsible for the reluctance to adopt the view that probability is part of logic. Several authors have poi...

An irreducibly simple climate-sensitivity model is designed to empower even non-specialists to research the question how much global warming we may cause. In 1990, the First Assessment Report of the Intergovernmental Panel on Climate Change (IPCC) expressed “substantial confidence” that near-term global warming would occur twice as fast as subseque...

Aims: To investigate the association of pericardial, mediastinal, and intrathoracic fat volumes with the presence and severity of coronary artery disease (CAD), metabolic syndrome (MS), and cardiac risk factors (CRFs). Methods and results: Two hundred and sixteen consecutive patients who underwent cardiac magnetic resonance (CMR) imaging and had...

Europe's push towards a single harmonised market that offers information on the benefits of foods is encapsulated in Regulation (EC) No 1924/2006, the Nutrition and Health Claims Regulation (NHCR). The NHCR will be the main focus of our contribution. Our contention is that this regulation not only stifles scientific research, limiting it to the rel...

Residents deemed at risk for low performance on standardized examinations require focused attention and remediation. To determine whether a remediation program for residents identified as at risk for failure on the Emergency Medicine (EM) Written Board Examination is associated with improved outcomes. All residents in 8 classes of an EM 1-3 program...

Agnotology has been defined in a variety of ways including “the study of ignorance and its cultural production” and “the study of how and why ignorance or misunderstanding exists.” More recently, however, it has been posited that agnotology should be used in the teaching of climate change science. But rather than use agnotology to enhance an unders...

A validated tool has long been sought to provide clinicians with a uniform and accurate method to assess hydration status in the pediatric emergency medicine population. Outpatient clinicians use CDC height- and weight-based curves for the assessment of physical development. In hospital, daily weights provide objective data; however, these are usua...

Postoperative pulmonary embolism (PE) is a leading cause of morbidity and mortality after bariatric surgery. However, the concurrent prophylactic placement of an inferior vena cava filter (CPIVCF) in patients undergoing bariatric operations remains controversial. This study used the Bariatric Outcomes Longitudinal Database (BOLD) to establish assoc...

The probability leakage of model M with respect to evidence E is defined. Probability leakage is a kind of model error. It occurs when M implies that events $y$, which are impossible given E, have positive probability. Leakage does not imply model falsification. Models with probability leakage cannot be calibrated empirically. Regression models, wh...

We should cease teaching frequentist statistics to undergraduates and switch to Bayes. Doing so will reduce the amount of confusion and over-certainty rife among users of statistics.

The current paradigm for the evaluation of patients with suspected acute coronary syndromes (ACS) in the emergency department (ED) is focused on the identification of patients with active underlying coronary disease. The majority of patients evaluated in the ED setting do not have active underlying cardiac disease. To measure the effect of bedside...

Abstract

Objectives We examined the use of point-of-care (POC) testing of cardiac biomarkers against standard core laboratory testing to determine the time-savings and estimate a cost-benefit ratio at our institution.

We examined the use of point-of-care (POC) testing of cardiac biomarkers against standard core laboratory testing to determine the time-savings and estimate a cost-benefit ratio at our institution. We prospectively enrolled 151 patients presenting to the emergency department undergoing evaluation for acute coronary syndrome and conducted both centr...

The statistical community is divided when it comes to graphical methods and models. Graphics researchers tend to disparage models and to focus on direct representations of data, mediated perhaps by research on perceptions but certainly not by probability distributions. From the other side, modelers tend to think of graphics as a cute toy for explor...

Insulin resistance is highly prevalent in Asian Indians and contributes to worldwide public health problems, including diabetes and related disorders. Surrogate measurements of insulin sensitivity/resistance are used frequently to study Asian Indians, but these are not formally validated in this population. In this study, we compared the ability of...