@article{TrafimowAmrheinAreshenkoffetal.2018,
  author    = {Trafimow, David and Amrhein, Valentin and Areshenkoff, Corson N. and Barrera-Causil, Carlos J. and Beh, Eric J. and Bilgi{\c{c}}, Yusuf K. and Bono, Roser and Bradley, Michael T. and Briggs, William M. and Cepeda-Freyre, H{\´e}ctor A. and Chaigneau, Sergio E. and Ciocca, Daniel R. and Correa, Juan C. and Cousineau, Denis and de Boer, Michiel R. and Dhar, Subhra S. and Dolgov, Igor and G{\´o}mez-Benito, Juana and Grendar, Marian and Grice, James W. and Guerrero-Gimenez, Martin E. and Guti{\´e}rrez, Andr{\´e}s and Huedo-Medina, Tania B. and Jaffe, Klaus and Janyan, Armina and Karimnezhad, Ali and Korner-Nievergelt, Fr{\"a}nzi and Kosugi, Koji and Lachmair, Martin and Ledesma, Rub{\´e}n D. and Limongi, Roberto and Liuzza, Marco T. and Lombardo, Rosaria and Marks, Michael J. and Meinlschmidt, Gunther and Nalborczyk, Ladislas and Nguyen, Hung T. and Ospina, Raydonal and Perezgonzalez, Jose D. and Pfister, Roland and Rahona, Juan J. and Rodr{\´i}guez-Medina, David A. and Rom{\~a}o, Xavier and Ruiz-Fern{\´a}ndez, Susana and Suarez, Isabel and Tegethoff, Marion and Tejo, Mauricio and van de Schoot, Rens and Vankov, Ivan I. and Velasco-Forero, Santiago and Wang, Tonghui and Yamada, Yuki and Zoppino, Felipe C. M. and Marmolejo-Ramos, Fernando},
  title     = {Manipulating the Alpha Level Cannot Cure Significance Testing},
  series = {Frontiers in Psychology},
  volume    = {9},
  journal   = {Frontiers in Psychology},
  number    = {699},
  issn      = {1664-1078},
  doi       = {10.3389/fpsyg.2018.00699},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-189973},
  year      = {2018},
  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.},
  language  = {en}
}