BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Reconsidering population inference from a prevalence perspective -
  Robin Ince\, University of Glasgow
DTSTART:20200615T113000Z
DTEND:20200615T130000Z
UID:TALK135535@talks.cam.ac.uk
CONTACT:Johan Carlin
DESCRIPTION:Within neuroscience\, psychology and neuroimaging\, it is typi
 cal to run an experiment on a sample of participants and then apply statis
 tical tools to quantify and infer an effect of the experimental manipulati
 on in the population from which the sample was drawn. Whereas the current 
 focus is on average effects (i.e. the population mean\, assuming a normal 
 distribution[1])\, it is equally valid to ask the alternative question of 
 how typical is the effect in the population[2]? That is\, we infer an effe
 ct in each individual participant in the sample\, and from that infer the 
 prevalence of the effect in the population[3–6]. We propose a novel Baye
 sian method to estimate such population prevalence\, based on within-parti
 cipant null-hypothesis significance testing (NHST). Applying Bayesian popu
 lation prevalence estimation in studies sufficiently powered for NHST with
 in individual participants could address many of the issues recently raise
 d regarding replicability[7].  Bayesian prevalence provides a population l
 evel inference currently missing for designs with small numbers of partici
 pants\, such as traditional psychophysics or animal electrophysiology[8\,9
 ]. Since Bayesian prevalence delivers a quantitative estimate with associa
 ted uncertainty\, it avoids reducing an entire experiment to a binary infe
 rence on a population mean[10].\n \n\n1.         Holmes\, A. & Friston\, K
 . Generalisability\, random effects and population inference. Neuroimage 7
 \, (1998).\n\n2.         Friston\, K. J.\, Holmes\, A. P. & Worsley\, K. J
 . How Many Subjects Constitute a Study? NeuroImage 10\, 1–5 (1999).\n\n3
 .         Friston\, K. J.\, Holmes\, A. P.\, Price\, C. J.\, Büchel\, C. 
 & Worsley\, K. J. Multisubject fMRI Studies and Conjunction Analyses. Neur
 oImage 10\, 385–396 (1999).\n\n4.         Rosenblatt\, J. D.\, Vink\, M.
  & Benjamini\, Y. Revisiting multi-subject random effects in fMRI: Advocat
 ing prevalence estimation. NeuroImage 84\, 113–121 (2014).\n\n5.        
  Allefeld\, C.\, Görgen\, K. & Haynes\, J.-D. Valid population inference 
 for information-based imaging: From the second-level t-test to prevalence 
 inference. NeuroImage 141\, 378–392 (2016).\n\n6.         Donhauser\, P.
  W.\, Florin\, E. & Baillet\, S. Imaging of neural oscillations with embed
 ded inferential and group prevalence statistics. PLOS Computational Biolog
 y 14\, e1005990 (2018).\n\n7.         Benjamin\, D. J. et al. Redefine sta
 tistical significance. Nature Human Behaviour 2\, 6 (2018).\n\n8.         
 Neuroscience\, S. for. Consideration of Sample Size in Neuroscience Studie
 s. J. Neurosci. 40\, 4076–4077 (2020).\n\n9.         Smith\, P. L. & Lit
 tle\, D. R. Small is beautiful: In defense of the small-N design. Psychon 
 Bull Rev 25\, 2083–2101 (2018).\n\n10.       McShane\, B. B.\, Gal\, D.\
 , Gelman\, A.\, Robert\, C. & Tackett\, J. L. Abandon Statistical Signific
 ance. The American Statistician 73\, 235–245 (2019).
LOCATION:Zoom (contact mri.admin@mrc-cbu.cam.ac.uk for attendance details)
END:VEVENT
END:VCALENDAR