The New Statistics

Cumming, Geoff

doi:10.1177/0956797613504966

Cited by 2,724 publications

(2,443 citation statements)

References 59 publications

Supporting

Mentioning

2,290

Contrasting

Unclassified

Order By: Relevance

“…For the second part of this paper, we pooled the results of our models and examined them as part of meta‐analyses to provide a more robust test of the hypothesis that SES moderates the intention–behaviour gap, thus providing more precise estimates of effect sizes (see Cumming, 2014, for discussion and recommendation of this procedure). We conducted separate meta‐analyses for objective and self‐report measures of behaviours and different types of SES index (individual vs. area level).…”

Section: Methodsmentioning

confidence: 99%

Is the intention–behaviour gap greater amongst the more deprived? A meta‐analysis of five studies on physical activity, diet, and medication adherence in smoking cessation

Vasiljevic

Griffin

et al. 2015

British J Health Psychol

View full text Add to dashboard Cite

ObjectivesUnhealthy behaviour is more common amongst the deprived, thereby contributing to health inequalities. The evidence that the gap between intention and behaviour is greater amongst the more deprived is limited and inconsistent. We tested this hypothesis using objective and self‐report measures of three behaviours, both individual‐ and area‐level indices of socio‐economic status, and pooling data from five studies.DesignSecondary data analysis.MethodsMultiple linear regressions and meta‐analyses of data on physical activity, diet, and medication adherence in smoking cessation from 2,511 participants.ResultsAcross five studies, we found no evidence for an interaction between deprivation and intention in predicting objective or self‐report measures of behaviour. Using objectively measured behaviour and area‐level deprivation, meta‐analyses suggested that the gap between self‐efficacy and behaviour was greater amongst the more deprived (B = .17 [95% CI = 0.02, 0.31]).ConclusionsWe find no compelling evidence to support the hypothesis that the intention–behaviour gap is greater amongst the more deprived. Statement of contribution What is already known on this subject? Unhealthy behaviour is more common in those who are more deprived.This may reflect a larger gap between intentions and behaviour amongst the more deprived.The limited evidence to date testing this hypothesis is mixed. What does this study add? In the most robust study to date, combining results from five trials, we found no evidence for this explanation.The gap between intentions and behaviour did not vary with deprivation for the following: diet, physical activity, or medication adherence in smoking cessation.We did, however, find a larger gap between perceived control over behaviour (self‐efficacy) and behaviour in those more deprived.These findings add to existing evidence to suggest that higher rates of unhealthier behaviour in more deprived groups may be reduced by the following: Strengthening behavioural control mechanisms (such as executive function and non‐conscious processes) or Behaviour change interventions that bypass behavioural control mechanisms.

show abstract

Section: Methodsmentioning

confidence: 99%

Is the intention–behaviour gap greater amongst the more deprived? A meta‐analysis of five studies on physical activity, diet, and medication adherence in smoking cessation

Vasiljevic

Griffin

et al. 2015

British J Health Psychol

View full text Add to dashboard Cite

show abstract

“…Only when the statistical power is at least 90% is a repeat experiment likely to return a similar P value, such that interpretation of P for a single experiment is reliable. In such cases, the effect is so clear that statistical inference is probably not necessary 25 .…”

Section: Box 1 Power Analysis and Repeatabilitymentioning

confidence: 99%

The fickle P value generates irreproducible results

et al. 2015

View full text Add to dashboard Cite

The reliability and reproducibility of science are under scrutiny. However, a major cause of this lack of repeatability is not being considered: the wide sample-to-sample variability in the P value. We explain why P is fickle to discourage the ill-informed practice of interpreting analyses based predominantly on this statistic.Reproducible research findings are a cornerstone of the scientific method, providing essential validation. There has been recent recognition, however, that the results of published research can be difficult to replicate 1-7 , an awareness epitomized by a series in Nature entitled "Challenges in irreproducible research" and by the Reproducibility Initiative, a project intended to identify and reward reproducible research (http:// validation.scienceexchange.com/#/ reproducibilityinitiative). In a recent meeting at the American Association for the Advancement of Science headquarters involving many of the major journals reporting biomedical science research, a common set of principles and guidelines was agreed upon for promoting transparency and reproducibility 8 . These discussions and initiatives all focused on a number of issues, including aspects of statistical reporting 9 , levels of statistical power (i.e., sufficient statistical capacity to find an effect; a 'statistically significant' finding) 10 and inclusion-exclusion criteria. Yet a fundamental problem inherent in standard statistical methods, one that is pervasively linked to the lack of reproducibility in research, remains to be considered: the wide sample-to-sample variability in the P value. This omission reflects a general lack of awareness about this crucial issue, and we address this matter here.Focusing on the P value during statistical analysis is an entrenched culture [11][12][13] . The P value is often used without the realization that in most cases the statistical power of a study is too low for P to assist the interpretation of the data (Box 1). Among the many and varied reasons for a fearful and hidebound approach to statistical practice, a lack of understanding is prominent 14 . A better understanding of why P is so unhelpful should encourage scientists to reduce their reliance on this misleading concept.Readers may know of the long-standing philosophical debate about the value and validity of null-hypothesis testing [15][16][17] . Although the P value formalizes null-hypothesis testing, this article will not revisit these issues. Rather, we concentrate on how P values themselves are misunderstood.Although statistical power is a central element in reliability 18 , it is often considered only when a test fails to demonstrate a real effect (such as a difference between groups): a 'false negative' result (see Box 2 for a glossary of statistical terms used in this article). Many scientists who are not statisticians do not realize that the power of a test is equally relevant when considering statistically significant results, that is, when the null hypothesis appears to be untenable. This is because the statistical power o...

show abstract

“…For example, it has been suggested that instead of basing statistical inferences on p -values, one should consider effect sizes or confidence intervals (e.g. Cumming, 2014; for Bayesian alternatives to these, see Kruschke and Liddell, in press). Although useful, here we decided to focus on BHT as this is a Bayesian alternative to NHST, which is commonly used in our field.…”

Section: Discussionmentioning

confidence: 99%

Bayesian hypothesis testing for human threat conditioning research: an introduction and the condir R package

Krypotos

Klugkist

Engelhard

2017

European Journal of Psychotraumatology

View full text Add to dashboard Cite

Threat conditioning procedures have allowed the experimental investigation of the pathogenesis of Post-Traumatic Stress Disorder. The ﬁndings of these procedures have also provided stable foundations for the development of relevant intervention programs (e.g. exposure therapy). Statistical inference of threat conditioning procedures is commonly based on p-values and Null Hypothesis Signiﬁcance Testing (NHST). Nowadays, however, there is a growing concern about this statistical approach, as many scientists point to the various limitations of p-values and NHST. As an alternative, the use of Bayes factors and Bayesian hypothesis testing has been suggested. In this article, we apply this statistical approach to threat conditioning data. In order to enable the easy computation of Bayes factors for threat conditioning data we present a new R package named condir, which can be used either via the R console or via a Shiny application. This article provides both a non-technical introduction to Bayesian analysis for researchers using the threat conditioning paradigm, and the necessary tools for computing Bayes factors easily.

show abstract

The New Statistics

Cited by 2,724 publications

References 59 publications

Is the intention–behaviour gap greater amongst the more deprived? A meta‐analysis of five studies on physical activity, diet, and medication adherence in smoking cessation

Is the intention–behaviour gap greater amongst the more deprived? A meta‐analysis of five studies on physical activity, diet, and medication adherence in smoking cessation

The fickle P value generates irreproducible results

Bayesian hypothesis testing for human threat conditioning research: an introduction and the condir R package

Contact Info

Product

Resources

About