Literature DB >> 29438579

Consequences of relying on statistical significance: Some illustrations.

Ben Van Calster1,2, Ewout W Steyerberg2, Gary S Collins3, Tim Smits4.   

Abstract

BACKGROUND: Despite regular criticisms of null hypothesis significance testing (NHST), a focus on testing persists, sometimes in the belief to get published and sometimes encouraged by journal reviewers. This paper aims to demonstrate known key limitations of NHST using simple nontechnical illustrations.
DESIGN: The first illustration is based on simulated data of 20 000 studies that compare two groups for an outcome event. The true effect size (difference in event rates) and sample size (20-100 per group) were varied. The second illustration used real data from a meta-analysis on alpha-blockers for the treatment of ureteric stones.
RESULTS: The simulations demonstrated the large between-study variability in P-values (range between <.0001 and 1 for most simulation conditions). A focus on statistically significant effects (P < .05), notably in small to moderate samples, led to strongly overestimated effect sizes (up to 240%) and many false-positive conclusions, that is statistically significant effects that were, in fact, true null effects. Effect sizes also exerted strong between-study variability, but confidence intervals accounted for this: the interval width decreased with larger sample size, and the percentage of intervals that contained the true effect size was accurate across simulation conditions. Reducing alpha level, as recently suggested, reduced false-positive conclusions but strongly increased the overestimation of significant effects (up to 320%).
CONCLUSIONS: Researchers and journals should abandon statistical significance as a pivotal element in most scientific publications. Confidence intervals around effect sizes are more informative, but should not merely be reported to comply with journal requirements.
© 2018 Stichting European Society for Clinical Investigation Journal Foundation.

Entities:  

Keywords:  confidence intervals; effect size; null hypothesis significance testing; reporting; statistical significance; study design

Mesh:

Year:  2018        PMID: 29438579     DOI: 10.1111/eci.12912

Source DB:  PubMed          Journal:  Eur J Clin Invest        ISSN: 0014-2972            Impact factor:   4.686


  7 in total

1.  Toward Value-Based Healthcare through Interactive Process Mining in Emergency Rooms: The Stroke Case.

Authors:  Gema Ibanez-Sanchez; Carlos Fernandez-Llatas; Antonio Martinez-Millana; Angeles Celda; Jesus Mandingorra; Lucia Aparici-Tortajada; Zoe Valero-Ramon; Jorge Munoz-Gama; Marcos Sepúlveda; Eric Rojas; Víctor Gálvez; Daniel Capurro; Vicente Traver
Journal:  Int J Environ Res Public Health       Date:  2019-05-20       Impact factor: 3.390

2.  Sample size and power considerations for ordinary least squares interrupted time series analysis: a simulation study.

Authors:  Samuel Hawley; M Sanni Ali; Klara Berencsi; Andrew Judge; Daniel Prieto-Alhambra
Journal:  Clin Epidemiol       Date:  2019-02-25       Impact factor: 4.790

3.  Cognitive Efficacy of Pharmacologic Treatments in Multiple Sclerosis: A Systematic Review.

Authors:  Michelle H Chen; Yael Goverover; Helen M Genova; John DeLuca
Journal:  CNS Drugs       Date:  2020-06       Impact factor: 5.749

4.  Effect of Plyometric Jump Training on Skeletal Muscle Hypertrophy in Healthy Individuals: A Systematic Review With Multilevel Meta-Analysis.

Authors:  F Arntz; B Mkaouer; A Markov; B J Schoenfeld; J Moran; R Ramirez-Campillo; M Behrens; P Baumert; R M Erskine; L Hauser; H Chaabene
Journal:  Front Physiol       Date:  2022-06-27       Impact factor: 4.755

5.  Misinterpretations of P-values and statistical tests persists among researchers and professionals working with statistics and epidemiology.

Authors:  Per Lytsy; Mikael Hartman; Ronnie Pingel
Journal:  Ups J Med Sci       Date:  2022-08-04       Impact factor: 2.646

6.  A teaching tool about the fickle p value and other statistical principles based on real-life data.

Authors:  Salem Alawbathani; Mehreen Batool; Jan Fleckhaus; Sarkawt Hamad; Floyd Hassenrück; Yanhong Hou; Xia Li; Jon Salmanton-García; Sami Ullah; Frederique Wieters; Martin C Michel
Journal:  Naunyn Schmiedebergs Arch Pharmacol       Date:  2021-01-14       Impact factor: 3.000

7.  Inflammation of the Sacroiliac Joints and Spine and Structural Changes on Magnetic Resonance Imaging in Axial Spondyloarthritis: Five-Year Data From the DESIR Cohort.

Authors:  Alexandre Sepriano; Sofia Ramiro; Robert Landewé; Anna Moltó; Pascal Claudepierre; Daniel Wendling; Maxime Dougados; Désirée van der Heijde
Journal:  Arthritis Care Res (Hoboken)       Date:  2021-12-28       Impact factor: 5.178

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.