A tutorial on Bayes Factor Design Analysis using an informed prior

Stefan, Angelika; Gronau, Quentin Frederik; Schönbrodt, Felix D.; Wagenmakers, Eric‐Jan

doi:10.3758/s13428-018-01189-8

Cited by 189 publications

(203 citation statements)

References 48 publications

Supporting

Mentioning

186

Contrasting

Order By: Relevance

“…Thirdly, Bayes Factors for the critical contrast (0.1 by-participants and 0.14 by-items) showed moderate to strong evidence in support of the null hypothesis, where less than 0.3 is considered moderate and less than 0.1 as strong evidence (Stefan et al, 2019). While this level of evidence might not be considered definitive, due to the slow rate of evidence accumulation for a true null as sample size increases (and particularly for default priors; Stefan, Gronau, Schönbrodt, & Wagenmakers, 2019) much larger sample sizes are necessary for stronger evidence (Brysbaert, 2019).…”

Section: Discussionmentioning

confidence: 91%

Semantic interpretability does not influence masked priming effects

Tseng

Lindsay

Davis

2020

Quarterly Journal of Experimental Psychology

View full text Add to dashboard Cite

Much of the recent masked nonword priming literature demonstrates no difference in priming between affixed and non-affixed nonword primes (e.g., maskity-MASK vs. maskond-MASK). A possible explanation for the absence of a difference is that studies have used affixed primes which were semantically uninterpretable. Therefore, this explanation indicates semantic interpretability plays a fundamental role in masked priming. To test this account, we conducted an experiment using the masked priming paradigm in the lexical decision task. We compared responses with targets which were preceded by one of four primes types: (1) interpretable affixed nonwords (e.g., maskless-MASK), (2) uninterpretable affixed nonwords (e.g., maskity-MASK), (3) non-affixed nonwords (e.g., maskond-MASK), and (4) unrelated words (e.g., tubeful-MASK). Our results follow the trend of finding no difference between affixed and non-affixed primes. Critically, however, we observed no difference in priming between uninterpretable and interpretable affixed primes. Thus, our results suggest that semantic interpretability does not influence masked priming.

show abstract

Section: Discussionmentioning

confidence: 91%

Semantic interpretability does not influence masked priming effects

Tseng

Lindsay

Davis

2020

Quarterly Journal of Experimental Psychology

View full text Add to dashboard Cite

show abstract

“…The third and main drawback of this procedure is that the construction of the calibration set costs data. For example, a study initially thought to have sufficient power (or sufficiently high probability of finding compelling evidence, see Stefan et al 2019), may become underpowered in light of a split-half cross-validation technique in which 50% of the data have to be sacrificed to construct the calibration set.…”

Section: Methods 1: Masking a Subsetmentioning

confidence: 99%

Flexible yet fair: blinding analyses in experimental psychology

2019

Self Cite

View full text Add to dashboard Cite

The replicability of findings in experimental psychology can be improved by distinguishing sharply between hypothesis-generating research and hypothesis-testing research. This distinction can be achieved by preregistration, a method that has recently attracted widespread attention. Although preregistration is fair in the sense that it inoculates researchers against hindsight bias and confirmation bias, preregistration does not allow researchers to analyze the data flexibly without the analysis being demoted to exploratory. To alleviate this concern we discuss how researchers may conduct blinded analyses (MacCoun and Perlmutter in Nature 526:187-189, 2015). As with preregistration, blinded analyses break the feedback loop between the analysis plan and analysis outcome, thereby preventing cherry-picking and significance seeking. However, blinded analyses retain the flexibility to account for unexpected peculiarities in the data. We discuss different methods of blinding, offer recommendations for blinding of popular experimental designs, and introduce the design for an online blinding protocol.

show abstract

“…The third and main drawback of this procedure is that the construction of the calibration set costs data. For example, a study initially thought to have sufficient power (or sufficiently high probability of finding compelling evidence, see Stefan, Gronau, Schönbrodt, & Wagenmakers, 2019), may become underpowered in light of a split-half cross-validation technique in which 50% of the data have to be sacrificed to construct the calibration set.…”

Section: Methods Of Analysis Blindingmentioning

confidence: 99%

Flexible Yet Fair: Blinding Analyses in Experimental Psychology

Dutilh¹,

Sarafoglou²,

Wagenmakers³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

The replicability of findings in experimental psychology can be improved by distinguishing sharply between hypothesis-generating research and hypothesis-testing research. This distinction can be achieved by preregistration, a method that has recently attracted widespread attention. Although preregistration is fair in the sense that it inoculates researchers against hindsight bias and confirmation bias, preregistration does not allow researchers to analyze the data flexibly without the analysis being demoted to exploratory. To alleviate this concern we discuss how researchers may conduct blinded analyses (MacCoun & Perlmutter, 2015). As with preregistration, blinded analyses break the feedback loop between the analysis plan and analysis outcome, thereby preventing cherry-picking and significance seeking. However, blinded analyses retain the flexibility to account for unexpected peculiarities in the data. We discuss different methods of blinding, offer recommendations for blinding of popular experimental designs, and introduce the design for an online blinding protocol.

show abstract

A tutorial on Bayes Factor Design Analysis using an informed prior

Cited by 189 publications

References 48 publications

Semantic interpretability does not influence masked priming effects

Semantic interpretability does not influence masked priming effects

Flexible yet fair: blinding analyses in experimental psychology

Flexible Yet Fair: Blinding Analyses in Experimental Psychology

Contact Info

Product

Resources

About