EJ
About
- Username
- EJ
- Joined
- Visits
- 2,585
- Last Active
- Roles
- Member, Administrator, Moderator
Comments
-
Hi Duplex, The Bayesian analysis produces a posterior distribution for the log odds ratio. This distribution is induced by the posteriors for the model parameters. You are comparing the result to the outcome of a classical analysis (the classical a…
-
Hi Lotje, It seems to me that the second factor explains variance that would otherwise go into your error term. Suppose you study the effect of weight loss for three different diets (the first factor), and the second factor is whether or not partic…
-
Hi M, In JASP you can compare models to assess whether inclusion of beta for X2 helps or hurts. However, in case of regression and ANOVA, JASP does not (yet!) return the parameter estimates. Cheers, E.J.
-
Hi Lori, About the 2.1 being evidence against the interaction: the table indicated that the two-main effects model didn't do so well against the null model. But adding the interaction didn't help. In fact, it made things even worse: the model with …
-
Hi M, The first point is that individual betas only have meaning in the context of a specific model. You can pick the full model, but that's just one (arbitrary?) choice. With respect to your specific question, one easy way would be to plot the pos…
-
Hi Lori, First, let's assume that looking at the interaction term is a good idea. Then yes, the BF is 2.1 against including the interaction (over and above the two main effects model). You can get the same result more easily if you use the model sp…
-
Hi M, This is on our to-do list. A recent paper on the topic is here: http://sci-hub.cc/10.1016/j.jmp.2015.08.001 I'm not sure whether there is R code, but I expect there is. Cheers, E.J.
-
Hi Juliane, You have to be careful with covariates. Suppose you have different groups and you suspect your DV is influenced by IQ. You have measured IQ and the distribution of IQ is approximately the same in the different groups. In that situation …
-
Hi Spacediver, You mention: "But to me, this seems to indicate a ratio of the probability of an effect size 0 given the prior, relative to the probability of an effect size 0 given the posterior." You are exactly right! But by mathematical…
-
Not sure about this. What I would do is create a Bayesian hierarchical model, use vague priors, and inspect the posterior distribution for the group-level mean effect size. The one-sided p-value should be very similar to the area of the posterior di…
-
My bad! Yes, you are right, g informs the prior (see also http://www.ejwagenmakers.com/2012/WetzelsEtAl2012AmStat.pdf) Cheers, E.J.
-
Hi Julie, The code should specify some "r" scale value that you can change...yes, see here: http://www.ejwagenmakers.com/2012/BFcorrelationsLargeN.R Cheers, E.J.
-
Hi Julie, There's nothing wrong with the WW2012 approach, but if you want to do this in JASP then you can selection "Bayesian correlation pairs" and explore different prior widths. The JASP version of the correlation test comes from Jeffr…
-
Dear researcher, JASP does compute Spearman but not yet in a Bayesian framework. We have completed a Bayesian version of Kendall's tau (paper accepted pending minor revision) and hope to add this to JASP soon. Spearman might follow suit. Nonparamet…
-
Hi JR, This is largely a matter of taste I think. The first idea we had was to incorporate only the Bayesian analyses, but then we figured people might like to have the classical analyses as well. Anyway, one problem with combining the two is that …
-
Yes there are plans :-) But it can't hurt to learn R! E.J.
-
I believe that there's a R package by Raftery that could be helpful (forgot the name though). Cheers, E.J.
-
Hi Alasdair, This is not implemented yet! It is on the list though. Cheers, E.J.
-
Hi Kristel, Sebastiaan, As I was about to answer your post, I realized a similar issue can up earlier in the forum. Here's my previous answer, slightly edited: "As far as I am concerned, t-test as usually what researchers want to know if they…
-
Hi Leah, These nonparametric tests are currently undergoing development. Johnny van Doorn, a PhD student in the JASP group, has submitted one paper (on Bayesian Kendall's tau) and is working on another. I'll see whether we can put the paper on ArXi…
-
Yes, this is weird. The export function has gone. This is unintentional, and we'll add it back in asap. Thanks for attending us to this. Cheers, E.J.
-
Hi Guha, We only have JASP working for Ubuntu Linux. If you look on the GitHub issues list you can see our previous (failed) attempts to get it to work on another Linux version (I forgot the name). Right now we've decided to focus our efforts on ad…
-
Yes, data-editing is one of the major jobs on the JASP to-do list. E.J.
-
OK, after talking to Richard it is now clear to me. Consider a situation with factors A and B. BTW, a specific example is always appreciated -- note that you can upload annotated .jasp files to the OSF and everybody can view the output. Anyway, con…
-
Hi R_A, thanks for that question. It has me scratching my head. Perhaps Richard knows more. Let me look into this and get back to you. Cheers. E.J.
-
Hi Lotje, This is not yet possible, but I will add it to the to-do list (we have been asked about this before) Cheers, E.J.
-
Hi Matti, About contingency tables: the interpretation of the prior concentration is the main suggestion for improvement in the review process (it has gotten "minor revision" at BRM). So we'll work on that. You can think of "a" …
-
Hi Pieter, Entering prior odds is something you can do easily yourself; multiplying them with the Bayes factor gives the posterior odds. If you want H0 to be a distribution, then you'll have to look at some of Richard's work on interval Bayes facto…
-
Hi Pieter, 1. For the parameter under test (such as effect size), H0 specifies a point (e.g., delta=0), not a distribution. So under H0 we have a spike at 0, both as a prior and as a posterior. 2. Therefore, the prior and the posterior you see in th…
-
Here we go: 1. "H0: score =< 6.4 H1: score > 6.4" This is the classical test. I have always considered it illogical, for the following reason. We have the two-sided test that compares H0: score = 6.4 against H1: score \neq 6.4. Now w…