In a previous post, I compared equivalence tests to Bayes factors, and pointed out several benefits of equivalence tests. But a much more logical comparison, and one I did not give enough attention to so far, is the ROPE procedure using Bayesian estimation. I’d like to thank John Kruschke ...

<img src=' [Read more...]

<img src=' [Read more...]

<img src=' [Read more...]

You might have seen the ‘Dance of the p-values’ video by Geoff Cumming (if not, watch it here). Because p-values and the default Bayes factors (Rouder, Speckman, Sun, Morey, & Iverson, 2009) are both calculated directly from t-values and sample sizes, we might expect there is also a Dance of the Bayes ...

You might have seen the ‘Dance of the p-values’ video by Geoff Cumming (if not, watch it here). Because p-values and the default Bayes factors (Rouder, Speckman, Sun, Morey, & Iverson, 2009) are both calculated directly from t-values and sample sizes, we might expect there is also a Dance of the Bayes ...

See the follow up post where I introduce my R package and spreadsheet TOSTER to perform TOST equivalence tests, and link to a practical primer on this topic.  When you find p __ 0.05, you did not observe surprising data, assuming there is no true effect. You can often read in the ...

When you find p __ 0.05, you did not observe surprising data, assuming there is no true effect. You can often read in the literature how p __ 0.05 is interpreted as ‘no effect’ but due to a lack of power the data might not be surprising if there was an effect. In this ...

After my previous post about one-sided tests, some people wondered about two-sided F-tests. And then Dr R recently tweeted: No, there is no such thing as a one-tailed p-value for an F-test. reported F(1,40)=3.72, p=.03; correct p=.06 use t-test for one-tailed. — R-Index (@R__INDEX) April 5, 2016 I thought it would be ...

After my previous post about one-sided tests, some people wondered about two-sided F-tests. And then Dr R recently tweeted: No, there is no such thing as a one-tailed p-value for an F-test. reported F(1,40)=3.72, p=.03; correct p=.06 use t-test for one-tailed.— R-Index (@R__INDEX) April 5, 2016I thought it would be ...

I was reworking a lecture on confidence intervals I’ll be teaching, when I came across a perfect real life example of a common error people make when interpreting confidence intervals. I hope everyone (Harvard Professors, Science editors, my bachelo...

<img src=' [Read more...]

In the reproducibility project, original effect sizes correlated r=0.51 with the effect sizes of replications. Some researchers find this hopeful.Less-popularised findings from the "estimating the reproducibility" paper @Eli_Finkel #SPSP2016 pic.twitte...

In the reproducibility project, original effect sizes correlated r=0.51 with the effect sizes of replications. Some researchers find this hopeful.Less-popularised findings from the "estimating the reproducibility" paper @Eli_Finkel #SPSP2016 pic.twitter.com/8CFJMbRhi8— Jessie Sun (@JessieSunPsych) January 28, 2016I don’t think we should be interpreting this correlation at ...

One important benefit of Bayesian statistics is that you can provide relative support for the null hypothesis. When the null hypothesis is true, p-values will forever randomly wander between 0 and 1, but a Bayes factor has consistency (Rouder, Speckman, Sun, Morey, & Iverson, 2009), which means that as the sample size increases, the ...

One important benefit of Bayesian statistics is that you can provide relative support for the null hypothesis. When the null hypothesis is true, p-values will forever randomly wander between 0 and 1, but a Bayes factor has consistency (Rouder, Speckman, Sun, Morey, & Iverson, 2009), which means that as the sample size increases, the ...

In a 2X2X2 design, there are three main effects, three two-way interactions, and one three-way interaction to test. That’s 7 statistical tests.The probability of making at least one Type 1 error in a single ANOVA is 1-(0.95)^7=30%. There are earlier blog posts on this, but my eyes were not ...

The Royal Society has decided to publish journal citations distributions. This makes sense. The journal impact factor is a single number trying to summarize a distribution, but it’s almost always better to plot your data. Somehave been hopeful that visualizing such distributions will make it clear what a troublesome ...