Using Bayes to get the most out of non-significant results
Reads0
Chats0
TLDR
It is argued Bayes factors allow theory to be linked to data in a way that overcomes the weaknesses of the other approaches, and provides a coherent approach to determining whether non-significant results support a null hypothesis over a theory, or whether the data are just insensitive.Abstract:
No scientific conclusion follows automatically from a statistically non-significant result, yet people routinely use non-significant results to guide conclusions about the status of theories (or the effectiveness of practices). To know whether a non-significant result counts against a theory, or if it just indicates data insensitivity, researchers must use one of: power, intervals (such as confidence or credibility intervals), or else an indicator of the relative evidence for one theory over another, such as a Bayes factor. I argue Bayes factors allow theory to be linked to data in a way that overcomes the weaknesses of the other approaches. Specifically, Bayes factors use the data themselves to determine their sensitivity in distinguishing theories (unlike power), and they make use of those aspects of a theory’s predictions that are often easiest to specify (unlike power and intervals, which require specifying the minimal interesting value in order to address theory). Bayes factors provide a coherent approach to determining whether non-significant results support a null hypothesis over a theory, or whether the data are just insensitive. They allow accepting and rejecting the null hypothesis to be put on an equal footing. Concrete examples are provided to indicate the range of application of a simple online Bayes calculator, which reveal both the strengths and weaknesses of Bayes factors.read more
Citations
More filters
Journal ArticleDOI
Effects of age on across-participant variability of cortical reinstatement effects
TL;DR: There was little evidence to support the hypothesis that across‐participant variability of retrieval‐related cortical reinstatement differs with age, and the findings extend prior evidence by demonstrating that content‐selective cortex reinstatement is sufficiently invariant to support across-participant multi‐voxel classification across the healthy adult lifespan.
Journal ArticleDOI
Individually tailored internet-based cognitive-behavioral therapy for daily functioning in patients with Parkinson’s disease: A randomized controlled trial
Martin Kraepelien,Robert Schibbye,Kristoffer N.T. Månsson,Kristoffer N.T. Månsson,Christopher Sundström,Christopher Sundström,Sara Riggare,Gerhard Andersson,Gerhard Andersson,Nils Lindefors,Per Svenningsson,Viktor Kaldo,Viktor Kaldo +12 more
TL;DR: ICBT as an addition to standard medical treatment was credible and improved functioning for some individuals with PD, and the treatment needs further development in order to help a larger proportion of individuals withPD.
Journal ArticleDOI
Phenomenological control as cold control
Zoltan Dienes,Peter Lush,Bence Palfi,Warrick Roseboom,Ryan B. Scott,Ben Parris,Anil K. Seth,Max Lovell +7 more
TL;DR: In this article, a new theory of intentional binding is proposed to measure the absence of conscious intentions in the hypnotic context, and the negative correlation between mindfulness and cold control is explored as a lack of mindfulness of intentions.
Journal ArticleDOI
Evaluating the effectiveness of the smartphone app, Drink Less, compared with the NHS alcohol advice webpage, for the reduction of alcohol consumption among hazardous and harmful adult drinkers in the UK at 6-month follow-up: protocol for a randomised controlled trial.
Claire Garnett,Melissa Oldham,Colin Angus,Emma Beard,Robyn Burton,Matt Field,Felix Greaves,Felix Greaves,Matthew Hickman,Eileen Kaner,Gemma Loebenberg,Susan Michie,Marcus R. Munafò,Elena Pizzo,Jamie Brown +14 more
TL;DR: This study will establish the effectiveness and cost-effectiveness of the Drink Less app at reducing alcohol consumption among hazardous and harmful adult drinkers and will be the first randomised controlled trial of an alcohol reduction app for the general population in the UK.
Dissertation
Human values and value instantiations : similarities and differences between countries and their implications
TL;DR: In this paper, the authors examined similarities between groups on 22 social variables (e.g., types of human values, trust, moral attitudes) within six commonly used social categories: gender, age, education, income, nation of residence, and religious denomination.
References
More filters
Book
Statistical Power Analysis for the Behavioral Sciences
TL;DR: The concepts of power analysis are discussed in this paper, where Chi-square Tests for Goodness of Fit and Contingency Tables, t-Test for Means, and Sign Test are used.
Book
Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach
TL;DR: The second edition of this book is unique in that it focuses on methods for making formal statistical inference from all the models in an a priori set (Multi-Model Inference).
Journal ArticleDOI
Statistical power analyses using G*Power 3.1: tests for correlation and regression analyses.
TL;DR: In the new version, procedures to analyze the power of tests based on single-sample tetrachoric correlations, comparisons of dependent correlations, bivariate linear regression, multiple linear regression based on the random predictor model, logistic regression, and Poisson regression are added.
Journal ArticleDOI
Bayesian data analysis.
TL;DR: A fatal flaw of NHST is reviewed and some benefits of Bayesian data analysis are introduced and illustrative examples of multiple comparisons in Bayesian analysis of variance and Bayesian approaches to statistical power are presented.
Journal ArticleDOI
Power failure: why small sample size undermines the reliability of neuroscience
Katherine S. Button,John P. A. Ioannidis,Claire Mokrysz,Brian A. Nosek,Jonathan Flint,Emma S J Robinson,Marcus R. Munafò +6 more
TL;DR: It is shown that the average statistical power of studies in the neurosciences is very low, and the consequences include overestimates of effect size and low reproducibility of results.