TressoldiPower replication unreliabilitypower = 0.9 with α = 0.05 given <strong>the</strong> observed r<strong>and</strong>om ESs, wasestimated.Statistical power was calculated using <strong>the</strong> software G ∗ Power(Faul et al., 2007).COMMENTThe results are quite clear: apart from <strong>the</strong> unconscious semanticpriming for semantic categorization, where <strong>the</strong> number of participantsin a typical experiment is sufficient to obtain a statisticalpower above 0.90, for all remaining phenomena, to achieve thislevel of power, it is necessary to increase <strong>the</strong> number of participantsin a typical study, from a minimum of seven participants for<strong>the</strong> unconscious semantic priming for lexical decision <strong>and</strong> namingto around 3400 to investigate NLP using <strong>the</strong> forced-choice withnormal state of consciousness protocol.GENERAL DISCUSSIONThe response to <strong>the</strong> question posed in <strong>the</strong> introduction, as towhe<strong>the</strong>r <strong>the</strong>re are elusive phenomena or an elusive power to detect<strong>the</strong>m, is quite clear. If <strong>the</strong>re are clear estimates of ESs from <strong>the</strong>evidence of <strong>the</strong> phenomenon derived from a sufficient numberof studies analyzed meta-analytically <strong>and</strong> <strong>the</strong>ir values are moderateor low, it is m<strong>and</strong>atory to increase <strong>the</strong> number of participantsto achieve a statistical power of 0.90, with <strong>the</strong> inevitable consequenceof investing more time <strong>and</strong> money into each study beforeinterpreting <strong>the</strong> results as support for reality or unreality of aphenomenon.Are <strong>the</strong>re alternatives to this obligation? Yes, <strong>and</strong> we briefly illustratesome of <strong>the</strong>se, also providing references for those interestedin using <strong>the</strong>m.CONFIDENCE INTERVALSIn line with <strong>the</strong> statistical reform movement (i.e., Cumming, 2012),in <strong>the</strong> APA manual (American Psychological Association, APA,2010), <strong>the</strong>re are <strong>the</strong> following statistical recommendations “Alternatively,(to <strong>the</strong> use of NHST) use calculations based on a chosentarget precision (confidence interval width) to determine samplesizes. Use <strong>the</strong> resulting confidence intervals to justify conclusionsconcerning ESs (e.g., that some effect is negligibly small) p. 30.”EQUIVALENCE TESTINGEquivalence tests are inferential statistics designed to provideevidence for a null hypo<strong>the</strong>sis. Like effect tests, <strong>the</strong> nil–null iseschewed in equivalence <strong>testing</strong>. However unlike st<strong>and</strong>ard NHST,equivalence tests provide evidence that <strong>the</strong>re is little differenceor effect. A significant result in an equivalence test means that<strong>the</strong> hypo<strong>the</strong>sis that <strong>the</strong> effects or differences are substantial can berejected. Hence, equivalence tests are appropriate when researcherswant to show little difference or effect (Levine et al., 2008).EVALUATING INFORMATIVE HYPOTHESESEvaluating specific expectations directly produces more usefulresults than sequentially <strong>testing</strong> traditional null hypo<strong>the</strong>ses againstcatch-all rivals. Researchers are often interested in <strong>the</strong> evaluationof informative hypo<strong>the</strong>ses <strong>and</strong> already know that <strong>the</strong> traditionalnull hypo<strong>the</strong>sis is an unrealistic hypo<strong>the</strong>sis. This presupposes thatprior knowledge is often available; if this is not <strong>the</strong> case, <strong>testing</strong> <strong>the</strong>traditional null hypo<strong>the</strong>sis is appropriate. In most applied studies,however, prior knowledge is indeed available in <strong>the</strong> form ofspecific expectations about <strong>the</strong> ordering of statistical parameters(Kuiper <strong>and</strong> Hoijtink, 2010; Van de Schoot et al., 2011).BAYESIAN APPROACHAno<strong>the</strong>r alternative is to ab<strong>and</strong>on <strong>the</strong> frequentist approach <strong>and</strong>use a Bayesian one (Wagenmakers et al., 2011). With a Bayesianapproach <strong>the</strong> problem of statistical power is substituted with parameterestimation <strong>and</strong>/or model comparison (Kruschke, 2011). In<strong>the</strong> first approach, assessing null values, <strong>the</strong> analyst simply setsup a range of c<strong>and</strong>idate values, including <strong>the</strong> null value, <strong>and</strong> usesBayesian inference to compute <strong>the</strong> relative credibility of all <strong>the</strong>c<strong>and</strong>idate values. In <strong>the</strong> model comparison approach, <strong>the</strong> analystsets up two competing models of what values are possible.One model posits that only <strong>the</strong> null value is possible whereas <strong>the</strong>alternative model posits that a broad range of o<strong>the</strong>r values is alsopossible. Bayesian inference is used to compute which model ismore credible, given <strong>the</strong> <strong>data</strong>.FINAL COMMENTIs <strong>the</strong>re a chance to ab<strong>and</strong>on “The Null Ritual” in <strong>the</strong> near future<strong>and</strong> to think of science as cumulative knowledge? The answer is“yes”if we approach scientific discovery thinking meta-analytically(Cumming, 2012), that is, simply reporting observed (st<strong>and</strong>ardized)ES <strong>and</strong> <strong>the</strong> corresponding confidence intervals, both whenNHST is refuted <strong>and</strong> when it is not refuted (Nickerson, 2000;American Psychological Association, APA, 2010) without drawingdichotomous decisions. The statistical approaches listed above aregood tools to achieve this goal.How many editors <strong>and</strong> reviewers are committed to pursuing it?ACKNOWLEDGMENTSSuggestions <strong>and</strong> comments by <strong>the</strong> reviewers were greatly appreciatedfor improving <strong>the</strong> clarity <strong>and</strong> quality of <strong>the</strong> paper. ProofReading Service revised <strong>the</strong> English.REFERENCESAlcock, J. E. (2003). Give <strong>the</strong> nullhypo<strong>the</strong>sis a chance: reasons toremain doubtful about <strong>the</strong> existenceof PSI. J. Conscious. Stud. 10, 29–50.American Psychological Association.(2010). Publication manual of <strong>the</strong>American Psychological Association,6th Edn, Washington, DC: AmericanPsychological Association.Bezeau, S., <strong>and</strong> Graves, R. (2001). Statisticalpower <strong>and</strong> effect sizes of clinicalneuropsychology research. J. Clin.Exp. Neuropsychol. 23, 399–406.Bouwmeester, D., Pan, J. W., Mattle,K., Eibl, M., Weinfurter, H., <strong>and</strong>Zeilinger, A. (1997). Experimentalquantum teleportation. Nature 390,575–579.Busemeyer, J. R., Pothos, E. M., Franco,R., <strong>and</strong> Trueblood, J. S. (2011). Aquantum <strong>the</strong>oretical explanation forprobability judgment errors. Psychol.Rev. 118, 2, 193–218.Cohen, J. (1992). A power primer. Psychol.Bull. 112, 1,155–1,159.Cohen, J. (1994). The earth isround (p < .085). Am. Psychol.49, 997–1003.Cumming, G. (2012). Underst<strong>and</strong>ing <strong>the</strong>New Statistics: Effect Sizes, ConfidenceIntervals, <strong>and</strong> Meta-Analysis.New York: Routledge.Dijksterhuis, A., Bos, M. W., Nordgren,L. F., <strong>and</strong> Van Baaren, R. B.(2006). On making <strong>the</strong> right choice:<strong>the</strong> deliberation-without attentioneffect. Science 311, 1005–1007.Faul, F., Erdfelder, E., Lang, A.-G., <strong>and</strong>Buchner, A. (2007). G∗Power 3:a flexible statistical power analysisprogram for <strong>the</strong> social, behavioral,<strong>and</strong> biomedical sciences. Behav. Res.Methods 39, 175–191.Genovese, M. (2005). Research on hiddenvariable <strong>the</strong>ories, a review ofrecent progresses. Phys. Rep. 413,319–396.<strong>Frontiers</strong> in Psychology | Quantitative Psychology <strong>and</strong> Measurement July 2012 | Volume 3 | Article 218 | 57
TressoldiPower replication unreliabilityGenovese, M. (2010). Interpretationsof quantum mechanics <strong>and</strong> measurementproblem. Adv. Sci. Lett. 3,249–258.Gigerenzer, G., Krauss, S., <strong>and</strong> Vitouch,O. (2004). “The null ritual whatyou always wanted to know aboutsignificance <strong>testing</strong> but were afraidto ask,” in The Sage H<strong>and</strong>bookof Quantitative Methodology for<strong>the</strong> Social Sciences, ed. D. Kaplan(Thous<strong>and</strong> Oaks, CA: Sage),391–408.Gutiérrez, R., Caetano, R.,Woiczikowski, P. B., Kubar, T.,Elstner, M., <strong>and</strong> Cuniberti, G.(2010). Structural fluctuations<strong>and</strong> quantum transport throughDNA molecular wires, a combinedmolecular dynamics <strong>and</strong> modelHamiltonian approach. New J. Phys.12, 023022.Kennedy, J. E. (2001). Why is PSY so elusive?A review <strong>and</strong> proposed model.J. Parapsychol. 65, 219–246.Khrennikov, A. Y. (2010). UbiquitousQuantum Structure from Psychologyto Finance. Berlin: Springer-Verlag.Kline, R. B. (2004). Beyond SignificanceTesting. Reforming Data AnalysisMethods in Behavioral Research.Washington, DC: APA.Kruschke, J. (2011). Bayesian assessmentof null values via parameterestimation <strong>and</strong> model comparison.Perspect. Psychol. Sci. 6, 299–312.Kuiper, R. M., <strong>and</strong> Hoijtink, H.(2010). Comparisons of meansusing exploratory <strong>and</strong> confirmatoryapproaches. Psychol. Methods 15,69–86.Levine, T. R., Weber, R., Sun Park, H.,<strong>and</strong> Hullett, C. R. (2008). A communicationresearchers’ guide to nullhypo<strong>the</strong>sis significance <strong>testing</strong> <strong>and</strong>alternatives. Hum. Commun. Res. 34,188–209.Maxwell, S. E. (2004). The persistence ofunderpowered studies in psychologicalresearch: causes, consequences,<strong>and</strong> remedies. Psychol. Methods 9,147–163.Milton, J. (1997). Meta-analysis of freeresponseESP studies without alteredstates of consciousness. J. Parapsychol.61, 279–319.Nickerson, R. S. (2000). Null hypo<strong>the</strong>sissignificance <strong>testing</strong>: a review ofan old <strong>and</strong> continuing controversy.Psychol. Methods 5, 241–301.Pratte, M. S., <strong>and</strong> Rouder, J. N. (2009). Atask-difficulty artifact in subliminalpriming. Atten. Percept. Psychophys.71,1276–1283.Richard, F. D., Bond, C. F., <strong>and</strong> Stokes-Zoota, J. J. (2003). One hundredyears of social psychology quantitativelydescribed. Rev. Gen. Psychol. 7,331–363.Schmidt, S. (2009). Shall we reallydo it again? The powerful conceptof replication is neglected in <strong>the</strong>social sciences. Rev. Gen. Psychol. 13,90–100.Sedlmeier, P., <strong>and</strong> Gigerenzer, G. (1989).Do studies of statistical power havean effect on <strong>the</strong> power of studies?Psychol. Bull. 105, 309–316.Sio, U. N., <strong>and</strong> Ormerod, T. C. (2009).<strong>Does</strong> incubation enhance problemsolving? A meta-analytic review. Psychol.Bull. 135, 94–120.Storm, L., Tressoldi, P. E., <strong>and</strong> Di Risio,L. (2010). Meta-analysis of freeresponsestudies, 1992–2008: assessing<strong>the</strong> noise reduction model inparapsychology. Psychol. Bull. 136,471–485.Storm, L., Tressoldi, P. E., <strong>and</strong> Di Risio,L. (in press). Meta-analysis of ESPstudies, 1987–2010, assessing <strong>the</strong>success of <strong>the</strong> forced-choice designin parapsychology.Strick, M., Dijksterhuis, A., Bos, M. W.,Sjoerdsma, A., van Baaren, R. B.,<strong>and</strong> Nordgren, L. F. (2011). A metaanalysison unconscious thoughteffects. Soc. Cogn. 29, 738–762.Valentine, J. C., Pigott, T. D., <strong>and</strong> Rothstein,H. R. (2009). How manystudies to you need? A primeron statistical power for metaanalysis.J. Educ. Behav. Stat. 35,215–247.Van de Schoot, R., Hoijtink, H.,<strong>and</strong> Jan-Willem, R. (2011). Movingbeyond traditional null hypo<strong>the</strong>sis<strong>testing</strong>: evaluating expectationsdirectly. Front. Psychol. 2:24.doi:10.3389/fpsyg.2011.00024Van den Bussche, E., den Noortgate,W., <strong>and</strong> Reynvoet, B. (2009). Mechanismsof masked priming: a metaanalysis.Psychol. Bull. 135, 452–477.von Lucadou, W., Römer, H., <strong>and</strong>WAlach, H. (2007). Synchronisticphenomena as entanglement correlationsin generalized quantum<strong>the</strong>ory. J. Conscious. Stud. 14, 4,50–74.Wagenmakers, E. J., Wetzels, R., Borsboom,D., <strong>and</strong> Van der Maas, H.(2011). Why psychologists mustchange <strong>the</strong> way <strong>the</strong>y analyze <strong>the</strong>ir<strong>data</strong>: <strong>the</strong> case of psi. J. Pers. Soc.Psychol. 100, 426–432.Walach, H., <strong>and</strong> von Stillfried, N.(2011). Generalised quantum <strong>the</strong>ory.Basic idea <strong>and</strong> general intuition:a background story <strong>and</strong> overview.Axioma<strong>the</strong>s 21, 185–209.Waroquier, L., Marchiori, D., Klein, O.,<strong>and</strong> Cleeremans, A. (2009). Methodologicalpitfalls of <strong>the</strong> unconsciousthought paradigm. Judgm. Decis.Mak. 4, 601–610.Conflict of Interest Statement: Theauthor declares that <strong>the</strong> research wasconducted in <strong>the</strong> absence of any commercialor financial relationships thatcould be construed as a potential conflictof interest.Received: 13 April 2012; accepted: 12 June2012; published online: 04 July 2012.Citation: Tressoldi PE (2012) Replicationunreliability in psychology: elusivephenomena or “elusive” statisticalpower? Front. Psychology 3:218. doi:10.3389/fpsyg.2012.00218This article was submitted to <strong>Frontiers</strong>in Quantitative Psychology <strong>and</strong> Measurement,a specialty of <strong>Frontiers</strong> in Psychology.Copyright © 2012 Tressoldi. This is anopen-access article distributed under <strong>the</strong>terms of <strong>the</strong> Creative Commons AttributionLicense, which permits use, distribution<strong>and</strong> reproduction in o<strong>the</strong>r forums,provided <strong>the</strong> original authors <strong>and</strong> sourceare credited <strong>and</strong> subject to any copyrightnotices concerning any third-partygraphics etc.www.frontiersin.org July 2012 | Volume 3 | Article 218 | 58