DOCSLIB.ORG

A Replication Crisis in Methodological Research?

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
A Replication Crisis in Methodological Research? STATISTICAL TOOLS A replication crisis in methodological research? Statisticians have been keen to critique statistical aspects of the “replication crisis” in other scientific disciplines. But new statistical tools are often published and promoted without any thought to replicability. This needs to change, argue Anne‑Laure Boulesteix, Sabine Hoffmann, Alethea Charlton and Heidi Seibold magine you need to take a drug. A to be more efficient than other statistical practices should also be avoided in the new drug is available that has been methods in a few example data sets selected development and reporting of new statistical investigated mainly through in vitro by the developer of the method. Would you methods. Iexperiments (i.e., in test tubes, rather feel confident using it? Weirdly, if you are a than in living organisms). It was shown to statistician, you probably would. Sins improve survival in a few patients selected Statisticians are among the first to call Table 1 sets out “seven sins of by the pharmaceutical company. Would for more rigour in clinical trials and other methodological research”, inspired by a you feel safe taking this drug? Probably applied fields of statistics. Yet, in their own recent Significance article by Held and not, especially if you are a statistician. You methodological research, statisticians Schwab.1 These practices include “fishing would ask why no pre-registered randomised commonly make claims on the performance expeditions” (i.e. running numerous different clinical trial was conducted to investigate the and utility of methods based merely on analyses in the hope that one will yield efficacy and safety of the drug. theory, limited simulations, or arbitrarily good results), then “selectively reporting” Now imagine you need to use a statistical selected real data examples. In the current the good results while leaving the others method for some data analysis. One of the replication crisis in science, statisticians in the metaphorical “file drawer”. In some available methods, a new method, was caution against questionable research cases, this “file drawer problem” affects investigated mainly through simulations practices in fields like psychology, biology whole projects, whose results are deemed (i.e. using synthetic data sets). It was shown and medicine. Yet the same questionable unexciting and are therefore not published 18 SIGNIFICANCE October 2020 © 2020 The Royal Statistical Society STATISTICAL TOOLS Table 1: The seven sins of methodological statistical research. The sesevenven sins ooff memethodologicalthodological rresearchesearch FFurtherurther rreadingeading Fishing expeditions/selective reporting Jelizarow et al.2; Hutson3 Publication bias Boulesteix et al.4 Lack of neutral comparison studies Boulesteix et al.5, 6 Lack of replication studies Liu and Meng7 Poor design of comparison studies Keogh and Kasetty8; Boulesteix et al.6; Christodoulou et al.9 Lack of meta-analyses Gardner et al.10 Lack of reporting guidelines (ourselves included) can stumble into this familiar with the various proposed methods. pitfall subconsciously, with no intention to The STRATOS initiative (stratos-initiative. “cheat”, encouraged by the fact that new org) is, we believe, a step in the right techniques are introduced in the scientific direction, aiming to provide guidance for the literature using only examples where they statistical analysis of observational medical seem to work perfectly. In a survey of papers studies. STRATOS emphasises the importance on new techniques, for example, we found of comparison studies performed by groups that all – without exception – were claimed to of experts from different “statistical schools”. perform better than existing competitors.11 There are also efforts such as OpenML Clearly, methodological results are affected (openml.org), which tries to tackle this issue by something akin to publication bias. in machine learning by opening up results of However, discussing publication bias, which thousands of machine learning benchmarks has attracted a lot of attention in medical to the public and allowing anyone to add and social sciences since the 1950s, seemed their own results. to be surprisingly taboo in methodological However, the pressure on researchers research until we tried to define the concept to publish in journals, and the reluctance in this context.4 of journals to accept the results of neutral Our contention is that, as a result of comparison studies, remains a crucial publication bias and fishing expeditions, obstacle. Contrast this with clinical the scientific literature is rife with statistical research, where clinical trials are considered Matt Artz/Unsplash.com Matt methods that supposedly perform better important pieces of scientific work, even if than all other methods – but which are never the treatment approach has been described compared to other methods except by their elsewhere before. If statistical methods (potentially biased) inventors. were treated like drugs, there would be a strong demand for neutral and well-planned at all, further exacerbating so-called Comparisons comparison studies: patients would refuse “publication bias”. The replicability of methodological research a drug that has not been reliably proven to In an intriguing example of how fishing findings has, to our knowledge, never be better, so why are we using statistical expeditions and selective reporting work, been systematically investigated, which methods based on the results of one Jelizarow et al.2 showed that they could is somewhat unexpected given the many (potentially biased) study? make a new discriminant analysis method empirical studies devoted to replicability in What is the role of replication studies? seem better than existing methods, simply by other scientific fields in the last decade. It is We all agree that they are needed in picking the best results using different data not hard to imagine, however, that claims applied research, but does this also hold sets, method variants and pre-processing about the superiority of new methods over true for methodological research? The approaches. In reality, the new method existing ones may be overly optimistic and goal of such studies would be to confirm was no better than those already in use. not replicable. Such concerns could be put the results of previous methodological Such problems are not limited to classical to rest if the statistical community were to papers, using, say, alternative simulation statistical methods. We see the same conduct more neutral comparison studies, designs, other real data sets and a issues in machine learning and artificial meaning studies that are not conducted with different implementation. Such formal intelligence.3 the aim of demonstrating the superiority of replication studies are rare to non-existent While most scientists would agree that a particular (new) method, and are authored in methodological research. Would they selective reporting is bad practice, many by researchers who are, on the whole, equally be deemed non-innovative and not October 2020 significancemagazine.com 19 STATISTICAL Anne‑Laure Boulesteix is a professor Sabine Hoffmann is a postdoctoral TOOLS of biometrics in the Institute for Medical researcher in the Institute for Medical Information Processing, Biometry Information Processing, Biometry and Epidemiology at LMU München, and Epidemiology at LMU München, Germany. Germany. worthy of publication by most renowned statistics journals? The pitfalls of existing methods are often discovered accidentally and demonstrated in the scientific literature many years after the original publication. This may result in flawed methods becoming widely used and, in the worst cases, accumulating years of potentially misleading results. The numerous reactions from the statistical community to a tweet on this general issue (see Figure 1) suggest that this is perceived to be a huge problem, and one prominent Figure 1: Co-author’s tweet, asking for examples of widely used, but ultimately flawed, statistical methods. example is the so-called magnitude-based 20 SIGNIFICANCE October 2020 Alethea Charlton is a student Heidi Seibold is a postdoctoral assistant in the Institute for Medical researcher at LMU München, Information Processing, Biometry Bielefeld University and Helmholz and Epidemiology at LMU München, Zentrum München, Germany. Germany. inference method, which was widely used of methods described in the methodological Ministry of Education and Research (BMBF; in sport statistics but eventually found to statistical literature are extremely rare, and grant no. 01IS18036A) for funding, and the be flawed.12 what is more, how they should be performed Twitter community who helped improve our is unclear. paper with valuable comments and literature Design Lastly, we should not fall at the final recommendations (see bit.ly/2EfmHyz and There is a clear need for more neutral hurdle: reporting, another important bit.ly/3jgu4EL). comparisons and replications of issue related to replicability. Appropriate methodological statistical research, but how reporting has been the subject of much References should such studies be performed? conversation over the past decade, in 1. Held, L. and Schwab, S. (2020) Improving the In many fields related to statistics, fields ranging from randomised clinical reproducibility of science. Significance, 17(1), 10–11. such as computational biology and trials to prediction models relying on 2. Jelizarow, M., Guillemot, V., Tenenhaus, A., Strimmer, bioinformatics,
Load more

Recommended publications
  • Arxiv:2102.03380V2 [Cs.AI] 29 Jun 2021
    Reproducibility in Evolutionary Computation MANUEL LÓPEZ-IBÁÑEZ, University of Málaga, Spain JUERGEN BRANKE, University of Warwick, UK LUÍS PAQUETE, University of Coimbra, CISUC, Department of Informatics Engineering, Portugal Experimental studies are prevalent in Evolutionary Computation (EC), and concerns about the reproducibility and replicability of such studies have increased in recent times, reflecting similar concerns in other scientific fields. In this article, we discuss, within the context of EC, the different types of reproducibility and suggest a classification that refines the badge system of the Association of Computing Machinery (ACM) adopted by ACM Transactions on Evolutionary Learning and Optimization (https://dlnext.acm.org/journal/telo). We identify cultural and technical obstacles to reproducibility in the EC field. Finally, we provide guidelines and suggest tools that may help to overcome some of these reproducibility obstacles. Additional Key Words and Phrases: Evolutionary Computation, Reproducibility, Empirical study, Benchmarking 1 INTRODUCTION As in many other fields of Computer Science, most of the published research in Evolutionary Computation (EC) relies on experiments to justify their conclusions. The ability of reaching similar conclusions by repeating an experiment performed by other researchers is the only way a research community can reach a consensus on an empirical claim until a mathematical proof is discovered. From an engineering perspective, the assumption that experimental findings hold under similar conditions is essential for making sound decisions and predicting their outcomes when tackling a real-world problem. The “reproducibility crisis” refers to the realisation that many experimental findings described in peer-reviewed scientific publications cannot be reproduced, because e.g. they lack the necessary data, they lack enough details to repeat the experiment or repeating the experiment leads to different conclusions.
    [Show full text]
  • The Reproducibility Crisis in Research and Open Science Solutions Andrée Rathemacher University of Rhode Island, [email protected] Creative Commons License
    University of Rhode Island DigitalCommons@URI Technical Services Faculty Presentations Technical Services 2017 "Fake Results": The Reproducibility Crisis in Research and Open Science Solutions Andrée Rathemacher University of Rhode Island, [email protected] Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 License. Follow this and additional works at: http://digitalcommons.uri.edu/lib_ts_presentations Part of the Scholarly Communication Commons, and the Scholarly Publishing Commons Recommended Citation Rathemacher, Andrée, ""Fake Results": The Reproducibility Crisis in Research and Open Science Solutions" (2017). Technical Services Faculty Presentations. Paper 48. http://digitalcommons.uri.edu/lib_ts_presentations/48http://digitalcommons.uri.edu/lib_ts_presentations/48 This Speech is brought to you for free and open access by the Technical Services at DigitalCommons@URI. It has been accepted for inclusion in Technical Services Faculty Presentations by an authorized administrator of DigitalCommons@URI. For more information, please contact [email protected]. “Fake Results” The Reproducibility Crisis in Research and Open Science Solutions “It can be proven that most claimed research findings are false.” — John P. A. Ioannidis, 2005 Those are the words of John Ioannidis (yo-NEE-dees) in a highly-cited article from 2005. Now based at Stanford University, Ioannidis is a meta-scientist who conducts “research on research” with the goal of making improvements. Sources: Ionnidis, John P. A. “Why Most
    [Show full text]
  • Why Replications Do Not Fix the Reproducibility Crisis: a Model And
    1 63 2 Why Replications Do Not Fix the Reproducibility 64 3 65 4 Crisis: A Model and Evidence from a Large-Scale 66 5 67 6 Vignette Experiment 68 7 69 8 Adam J. Berinskya,1, James N. Druckmanb,1, and Teppei Yamamotoa,1,2 70 9 71 a b 10 Department of Political Science, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139; Department of Political Science, Northwestern 72 University, 601 University Place, Evanston, IL 60208 11 73 12 This manuscript was compiled on January 9, 2018 74 13 75 14 There has recently been a dramatic increase in concern about collective “file drawer” (4). When publication decisions depend 76 15 whether “most published research findings are false” (Ioannidis on factors beyond research quality, the emergent scientific 77 16 2005). While the extent to which this is true in different disciplines re- consensus may be skewed. Encouraging replication seems to 78 17 mains debated, less contested is the presence of “publication bias,” be one way to correct a biased record of published research 79 18 which occurs when publication decisions depend on factors beyond resulting from this file drawer problem (5–7). Yet, in the 80 19 research quality, most notably the statistical significance of an ef- current landscape, one must also consider potential publication 81 20 fect. Evidence of this “file drawer problem” and related phenom- biases at the replication stage. While this was not an issue 82 21 ena across fields abounds, suggesting that an emergent scientific for OSC since they relied on over 250 scholars to replicate the 83 22 consensus may represent false positives.
    [Show full text]
  • Intro to Science Studies I
    PHIL 209A / SOCG 255A / HIGR 238 / COGR 225A Intro to Science Studies I Fall 2017 Instructor: Kerry McKenzie [email protected] Seminars: Tuesday 9.30-12.20pm, HSS 3027. Office Hours: Wednesday 2-4pm, HSS 8088. 1 Overview. This course is a philosophically slanted introduction to Science Studies. Our central question is a conceptual one, whose relevance to Science Studies should speak for itself – namely, what is science, and what distinguishes science from other fields? In grappling with this question we’ll familiarize ourselves with central works in the philosophy of science canon, and make glancing acquaintance with some more contemporary issues in scientific epistemology and metaphysics. But our guiding motif is a normative one: what, if anything, makes science entitled to the privileged status that it enjoys within culture? In more detail. The ‘question of demarcation’ – that of what, if anything, makes what we call ‘science’ science – was a central preoccupation of many of the major 20th century philosophers of science. While interest in this topic waned after the appearance of Larry Laudan’s ‘Demise of the Demarcation Problem’ in 1983, the question of what separates science from ‘pseudoscience’ is now making something of a comeback. In this course, we will review the approaches to demarcation offered by the philosophers Popper, Kuhn, and Lakatos – all of which serve as concise introductions to the dominant themes of their work as a whole – and then examine some more contemporary approaches more centred on pragmatics and the philosophy of language. We will then consider how homeopathy – for most a pseudoscience par excellence – fares with regard to the criteria we’ll have studied.
    [Show full text]
  • Psychology's Replication Crisis and the Grant Culture: Righting the Ship
    PPSXXX10.1177/1745691616687745LilienfeldRighting the Ship 687745research-article2017 Perspectives on Psychological Science 2017, Vol. 12(4) 660 –664 Psychology’s Replication Crisis and the © The Author(s) 2017 Reprints and permissions: Grant Culture: Righting the Ship sagepub.com/journalsPermissions.nav DOI:https://doi.org/10.1177/1745691616687745 10.1177/1745691616687745 www.psychologicalscience.org/PPS Scott O. Lilienfeld Department of Psychology, Emory University Abstract The past several years have been a time for soul searching in psychology, as we have gradually come to grips with the reality that some of our cherished findings are less robust than we had assumed. Nevertheless, the replication crisis highlights the operation of psychological science at its best, as it reflects our growing humility. At the same time, institutional variables, especially the growing emphasis on external funding as an expectation or de facto requirement for faculty tenure and promotion, pose largely unappreciated hazards for psychological science, including (a) incentives for engaging in questionable research practices, (b) a single­minded focus on programmatic research, (c) intellectual hyperspecialization, (d) disincentives for conducting direct replications, (e) stifling of creativity and intellectual risk taking, (f) researchers promising more than they can deliver, and (g) diminished time for thinking deeply. Preregistration should assist with (a), but will do little about (b) through (g). Psychology is beginning to right the ship, but it will need to confront the increasingly deleterious impact of the grant culture on scientific inquiry. Keywords replication, grants, preregistration, confirmation bias “Science is a struggle for truth against method­ psychological phenomena, such as behavioral priming, ological, psychological, and sociological obstacles” the effects of facial expressions on emotions, and the (Fanelli & Ioannidis, 2013, p.
    [Show full text]
  • A Bayesian Treatise on the Replication Crisis in Science
    A Bayesian Treatise on The Replication Crisis in Science by True Gibson A thesis submitted to Oregon State University Honors College in partial fulfillment of the requirements for the degree of Honors Baccalaureate of Science in Biochemistry and Biophysics Honors Scholar Presented May 25, 2018 Commencement June 2018 AN ABSTRACT OF THE THESIS OF True Gibson for the degree of Honors Baccalaureate of Science in Biochemistry and Biophysics presented on May 25, 2018. Title: A Bayesian Treatise on The Replication Crisis in Science. Abstract approved: __________________________________________________ Jonathan Kaplan Abstract Over the past decade, it has come to light that many published scientific findings cannot be reproduced. This has led to the replication crisis in science. Many researchers feel that they can no longer trust much of what they read in scientific journals, and the public is becoming ever more dubious of published research findings. I argue herein that the replication crisis is a result of the mistaken belief that the methods of classical statistical inference provide a coherent objective basis for evaluating scientific hypotheses. To solve the replication crisis, I suggest that the scientific community ought to invoke a Bayesian framework of statistical inference which integrates both successful and failed replication attempts to determine the confidence they should have in any given scientific hypothesis. Key Words: Inductive Reasoning, Replication Crisis, Reproducibility, Statistical Inference, Bayesian Statistics Corresponding
    [Show full text]
  • Researchers Overturn Landmark Study on the Replicability of Psychological Science
    Researchers overturn landmark study on the replicability of psychological science By Peter Reuell Harvard Staff Writer Category: HarvardScience Subcategory: Culture & Society KEYWORDS: psychology, psychological science, replication, replicate, reproduce, reproducibility, Center for Open Science, Gilbert, Daniel Gilbert, King, Gary King, Science, Harvard, FAS, Faculty of Arts and Sciences, Reuell, Peter Reuell Summary: A 2015 study claiming that more than half of all psychology studies cannot be replicated turns out to be wrong. Harvard researchers have discovered that the study contains several statistical and methodological mistakes, and that when these are corrected, the study actually shows that the replication rate in psychology is quite high – indeed, it is statistically indistinguishable from 100%. RELATED LINKS: According to two Harvard professors and their collaborators, a 2015 landmark study showing that more than half of all psychology studies cannot be replicated is actually wrong. In an attempt to determine the replicability of psychological science, a consortium of 270 scientists known as The Open Science Collaboration (OSC) tried to replicate the results of 100 published studies. More than half of them failed, creating sensational headlines worldwide about the “replication crisis” in psychology. But an in-depth examination of the data by Daniel Gilbert (Edgar Pierce Professor of Psychology at Harvard University), Gary King (Albert J. Weatherhead III University Professor at Harvard University), Stephen Pettigrew (doctoral student in the Department of Government at Harvard University), and Timothy Wilson (Sherrell J. Aston Professor of Psychology at the University of Virginia) has revealed that the OSC made some serious mistakes that make this pessimistic conclusion completely unwarranted: The methods of many of the replication studies turn out to be remarkably different from the originals and, according to Gilbert, King, Pettigrew, and Wilson, these “infidelities” had two important consequences.
    [Show full text]
  • The Replication Crisis, the Rise of New Research Practices and What It Means for Experimental Economics ESA Report
    The replication crisis, the rise of new research practices and what it means for experimental economics ESA Report Lionel Page* Charles N. Noussair Robert Slonim 1. Introduction In the wake of the replication crisis in psychology, a range of new approaches has been advocated to improve scientific practices and the replicability of published studies in the behavioural sciences. The ESA Executive Committee commissioned an ad hoc committee to review the issues raised by the replication crisis, and how they affect research in experimental economics. The present report is the result of this review. Its content has greatly benefited from the personal views and insights of a large number of ESA members. The views within the community of researchers in experimental economics are diverse. The present report does not aim at determining a strict ESA policy. Rather, it aims to bring to the community of experimental economists the collective wisdom spread among experimentalists. The report presents a discussion of the different issues related to replicability and discusses the different potential solutions, with their benefits and pitfalls. The report also contains a series of recommendations that aim to address the challenges presented by the replication crisis, while respecting the diversity of views within the ESA community. 2. The issues raised by the replication crisis In recent years, there has been a growing concern that, for a substantial proportion of studies published in scientific journals, the results are false (Ioannidis, 2005). This concern has been particularly strong in psychology, and it has spread to other social sciences, including economics. In psychology, many studies, some of which are very well-known and discussed in textbooks, have seen attempts at replication fail.
    [Show full text]
  • 1 Why Replication Is Overrated Current Debates About The
    Uljana Feest. Paper to be presented at PSA2018: The 26th Biennial Meeting of the Philosophy of Science Association, Nov. 1-4, 2018, Seattle Why Replication is Overrated Current debates about the replication crisis in psychology take it for granted that direct replication is valuable and focus their attention on questionable research practices in regard to statistical analyses. This paper takes a broader look at the notion of replication as such. It is argued that all experimentation/replication involves individuation judgments and that research in experimental psychology frequently turns on probing the adequacy of such judgments. In this vein, I highlight the ubiquity of conceptual and material questions in research, and I argue that replication is not as central to psychological research as it is sometimes taken to be. 1. Introduction: The “Replication Crisis” In the current debate about replicability in psychology, we can distinguish between (1) the question of why not more replication studies are done (e.g., Romero 2017) and (2) the question of why a significant portion (more than 60%) of studies, when they are done, fail to replicate (I take this number from the Open Science Collaboration, 2015). Debates about these questions have been dominated by two assumptions, namely, first, that it is in general desirable that scientists conduct replication studies that come as close as possible to the original, and second, that the low replication rate can often be attributed to statistical problems with many initial studies, sometimes referred to as “p-hacking” and “data-massaging.”1 1 An important player in this regard is the statistician Andrew Gelman who has been using his blog as a public platform to debate methodological problems with mainstream social psychology (http://andrewgelman.com/).
    [Show full text]
  • Why Has Personality Psychology Played an Outsized Role in the Credibility Revolution?
    Theory: State of the Art Review [Invited Paper] Why Has Personality Psychology Played an Outsized Role in the Credibility Revolution? Olivia E. Atherton 1 , Joanne M. Chung 2 , Kelci Harris 3 , Julia M. Rohrer 4 , David M. Condon 5 , Felix Cheung 6 , Simine Vazire 7 , Richard E. Lucas 8 , M. Brent Donnellan 8, Daniel K. Mroczek 1,9 , Christopher J. Soto 10 , Stephen Antonoplis 11 , Rodica Ioana Damian 12 , David C. Funder 13 , Sanjay Srivastava 5 , R. Chris Fraley 14, Hayley Jach 7 , Brent W. Roberts 14,15 , Luke D. Smillie 7 , Jessie Sun 16 , Jennifer L. Tackett 9 , Sara J. Weston 5 , K. Paige Harden 17,18 , Katherine S. Corker 19 [1] Department of Medical Social Sciences, Northwestern University, Chicago, IL, USA. [2] Department of Psychology, University of Toronto, Mississauga , Canada. [3] Department of Psychology, University of Victoria, Victoria, Canada. [4] Department of Psychology, Leipzig University, Leipzig, Germany. [5] Department of Psychology, University of Oregon, Eugene, OR, USA. [6] Department of Psychology, University of Toronto, Toronto, Canada. [7] School of Psychological Sciences, University of Melbourne, Melbourne, Australia. [8] Department of Psychology, Michigan State University, East Lansing, MI, USA. [9] Department of Psychology, Northwestern University, Evanston, IL, USA. [10] Department of Psychology, Colby College, Waterville, ME, USA. [11] Department of Psychology, University of California, Berkeley, CA, USA. [12] Department of Psychology, University of Houston, Houston, TX, USA. [13] Department of Psychology, University of California, Riverside, CA, USA. [14] Department of Psychology, University of Illinois, Champaign, IL, USA. [15] Hector Research Institute of Education and Sciences and Psychology, University of Tübingen, Tübingen, Germany.
    [Show full text]
  • The Statistical Crisis in Science: How Is It Relevant to Clinical Neuropsychology?∗ 1. Introduction
    The statistical crisis in science: How is it relevant to clinical neuropsychology?∗ Andrew Gelmany and Hilde M. Geurtsz 2 Jan 2017 Abstract There is currently increased attention to the statistical (and replication) crisis in science. Biomedicine and social psychology have been at the heart of this crisis, but similar problems are evident in a wide range of fields. We discuss three examples of replication challenges from the field of social psychology and some proposed solutions, and then consider the applicability of these ideas to clinical neuropsychology. In addition to procedural developments such as pre- registration and open data and criticism, we recommend that data be collected and analyzed with more recognition that each new study is a part of a learning process. The goal of improv- ing neuropsychological assessment, care, and cure is too important to not take good scientific practice seriously. 1. Introduction In the last few years psychology and other experimental sciences have been rocked with what has been called a replication crisis. Recent theoretical and experimental results have cast doubt on what previously had been believed to be solid findings in various fields (for examples, see Begley and Ellis, 2012, Button et al., 2013, Baker, 2016, Dumas-Mallet et al., 2016, Ioannidis and Panagiotou, 2011). Here we focus on psychology, a field in which big steps have been made to try to address the crisis. Where do we refer to when we speak of the statistical crisis in science? From the theoretical direction a close examination of the properties of hypothesis testing has made it clear that conven- tional “statistical significance” does not necessarily provide a strong signal in favor of scientific claims (Cohen, 1994, Ioannidis, 2005, Simmons, Nelson, and Simonsohn, 2011, Francis, 2013, Button et al., 2013, Gelman and Carlin, 2014).
    [Show full text]
  • Towards a More Robust and Replicable Science of Infant Development
    Towards a more robust and replicable science of infant development Michael C. Frank Department of Psychology, Stanford University Please address correspondence to: Michael C. Frank, 450 Serra Mall, Stanford, CA 94305. [email protected]. Towards a more robust and replicable science of infant development If you scroll through the table of contents of Infant Behavior and Development ten years ​ ​ from now, what mix of articles should you find? If the past predicts the future, most articles will be empirical reports: one or a series of experiments conducted at a single site, typically investigating a novel phenomenon or with a new take on a previous experimental paradigm. On the other hand, based on recent changes in psychology more generally, we might expect a broader range of articles. Some might still be new empirical reports from a single laboratory; but others might be larger-scale collaborative studies; still others will be confirmatory replication research; and others will be new methodological and statistical innovations. These changes have been triggered by a host of different factors, but two threads stand out. The first was a recognition that many of the analytic practices followed by psychologists could substantially inflate the probability of a spurious finding being reported (Simmons, Nelson, ​ & Simonsohn, 2011). The second was initial experimental evidence for the low rate of ​ replicability – finding the same conclusions from a new dataset – in a sample of high-profile psychology findings (Open Science Collaboration, 2015). These two initial threads have become ​ ​ part of a rich fabric of discussion surrounding the nature of scientific practices and their consequences for the robustness of the research literature (Munafò et al., 2017).
    [Show full text]