Bayesian versus Orthodox statistics: which side are you on?
Citations
1,496 citations
Cites background or methods from "Bayesian versus Orthodox statistics..."
...…with orthodox statistics, unless pre-specified as possible by one’s stopping rule (Armitage et al., 1969); by contrast, with Bayes, one can always collect more participants until the data are sensitive enough, that is, B < 1/3 or B > 3; see e.g., Berger and Wolpert (1988), Dienes (2008, 2011)....
[...]
...Further, the advantages of Bayes go well beyond the interpretation of non-significant results (e.g., Dienes, 2011)....
[...]
...It is open to public scrutiny and debate (unlike many of the factors that affect significance testing; see Dienes, 2011)....
[...]
...…and the criticisms of 1-tailed tests in an orthodox sense (criticizing a researcher using a 1-tailed test because he would have rejected the null if the results had been extreme in the other direction, even though they were not) hence do not apply to Bayes factors (cf. Royall, 1997; Dienes, 2011)....
[...]
...For that assertion to be relevant to a given scientific context, the minimal value must be relevant to that scientific context (i.e., it cannot be determined by properties of the data alone nor can it be a generic default)....
[...]
1,214 citations
Cites background or methods from "Bayesian versus Orthodox statistics..."
...Dienes (2008, 2011) provided another analytical solution, with a corresponding online calculator....
[...]
...Nevertheless, the BF can be highly sensitive to the choice of alternative-hypothesis prior distribution (e.g., Dienes, 2008, 2011; Kruschke, 2011a; Liu & Aitkin, 2008; Vanpaemel, 2010), even to such as extent that the BF can change from substantially favoring the null hypothesis to substantially…...
[...]
...Bayesian analysis is also more intuitive than traditional methods of null hypothesis significance testing (e.g., Dienes, 2011)....
[...]
1,192 citations
1,190 citations
1,037 citations
References
6,081 citations
"Bayesian versus Orthodox statistics..." refers background or methods in this paper
...(Note that I will not discuss confidence intervals and credibility intervals, the Bayesian equivalent to a confidence interval, in this article; see Dienes, 2008, and Kruschke 2010b, 2011, for detailed discussion and calculations.)...
[...]
...For this, credibility or likelihood intervals can be used (see Dienes, 2008; Kruschke, 2010b, 2011; Royall, 1997)....
[...]
...…is compared with a default theory (namely, the theory that effects may occur in either direction, scaled to a large standardized effect size); and Kruschke (2010a, 2010b, 2011) for Bayes factors for a set of default hypotheses (much like the default effects in analyses of variance) where…...
[...]
...…all the problems enumerated above for Neyman Pearson inference in general (unlike credibility or likelihood intervals): Because confidence intervals consist of all values nonsignificantly different from the sample mean, they inherit the arbitrariness of significance testing (e.g., Kruschke, 2010a)....
[...]
...Power can be calculated in the Bayesian approach to determine likely numbers of subjects needed to make a point, though this is a practical matter, and power does not figure in the inferential procedure itself, unlike in the Neyman Pearson approach (see Kruschke, 2010 a, 2010b, 2010c; Royall, 1997)....
[...]
4,641 citations
3,392 citations
"Bayesian versus Orthodox statistics..." refers background in this paper
...Mussweiler bases his effect on previous similar social priming explored by Bargh, Chen, and Burrows (1996), who found large effects (Cohen’s d of about one)....
[...]
3,012 citations
"Bayesian versus Orthodox statistics..." refers background or methods in this paper
...For a p value, if the null is true, any value in the interval 0 to 1 is equally likely no matter how much data you collect (Rouder et al., 2009)....
[...]
...One solution is to use a default Bayes factor for all occasions (Rouder et al., 2009; Wetzels et al., 2011), though this amounts to evaluating a default theory for all occasions, regardless of one’s actual theory....
[...]
...Different ways of using Bayes factors For a couple of other ways of using Bayes factors, see Rouder et al. (2009) and Wetzels et al. (2011) for a suggested ‘‘default’’ Bayes factor to be used on any data where the null hypothesis is compared with a default theory (namely, the theory that effects…...
[...]