Please use this identifier to cite or link to this item:
Title: Manipulating the alpha level cannot cure significance testing
Author: Trafimow, David
Amrhein, Valentin
Areshenkoff, Corson N.
Barrera-Causil, Carlos J.
Beh, Eric J.
Bilgiç, Yusuf K.
Bono Cabré, Roser
Bradley, Michael T.
Briggs, William M.
Cepeda-Freyre, Héctor A.
Chaigneau, Sergio E.
Ciocca, Daniel R.
Correa, Juan Carlos
Cousineau, Denis
de Boer, Michiel R.
Dhar, Subhra Sankar
Dolgov, Igor
Gómez Benito, Juana
Grendar, Marian
Grice, James W.
Guerrero Giménez, Martín E.
Gutiérrez, Andrés
Huedo-Medina, Tania B.
Jaffe, Klaus
Janyan, Armina
Karimnezhad, Ali
Korner-Nievergelt, Fränzi
Kosugi, Koji
Lachmair, Martin
Ledesma, Rubén D.
Limongi, Roberto
Liuzza, Marco Tullio
Lombardo, Rosaria
Marks, Michael J.
Meinlschmidt, Gunther
Nalborczyk, Ladislas
Nguyen, Hung T.
Ospina, Raydonal
Pérez-González, José D.
Keywords: Presa de decisions (Estadística)
Tests d'hipòtesi (Estadística)
Statistical decision
Statistical hypothesis testing
Issue Date: 15-May-2018
Publisher: Frontiers Media
Abstract: We argue that making accept/reject decisions on scientific hypotheses, including a recent call for changing the canonical alpha level from p = 0.05 to p = 0.005, is deleterious for the finding of new discoveries and the progress of science. Given that blanket and variable alpha levels both are problematic, it is sensible to dispense with significance testing altogether. There are alternatives that address study design and sample size much more directly than significance testing does; but none of the statistical tools should be taken as the new magic method giving clear-cut mechanical answers. Inference should not be based on single studies at all, but on cumulative evidence from multiple independent studies. When evaluating the strength of the evidence, we should consider, for example, auxiliary assumptions, the strength of the experimental design, and implications for applications. To boil all this down to a binary decision based on a p-value threshold of 0.05, 0.01, 0.005, or anything else, is not acceptable.
Note: Reproducció del document publicat a:
It is part of: Frontiers in Psychology, 2018, vol. 9, p. 699
Related resource:
ISSN: 1664-1078
Appears in Collections:Articles publicats en revistes (Psicologia Social i Psicologia Quantitativa)

Files in This Item:
File Description SizeFormat 
680950.pdf384.94 kBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons