#### Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

# MSB

MSB
Joined
Visits
225
Last Active
Roles
Member

• The differences between the BFs for "salience" might be explains as stemming from the fact the other models that also include "salience" are much better than the models that do not include "salience" (which is the defin…
Comment by MSB December 2019
• Thanks. I've since reached out to Jeff Rouder - I will update here if I hear from him. Thanks again and happy holidays!
Comment by MSB December 2019
• Generally, BFs are suppose to converge to the "truth" as N increases. So I depends what "truth" your betas are closer to, I guess. For determining N, you might also be interested in https://github.com/nicebread/BFDA
Comment by MSB December 2019
• You can use as.vector(): library(BayesFactor) data(puzzles) result <- anovaBF(RT ~ shape*color + ID, data = puzzles,          whichRandom = "ID", progress = FALSE) result #> Bayes factor analysis #> -------------- #> [1] sha…
Comment by MSB December 2019
• Hi @EJ, any news on this?
Comment by MSB December 2019
• I don't think this should matter. But, upon further reflection, the lme4 formula should be: percent_looking ~ Book * Condition +           (1 + Book | Trial:Subject) +          (1 + Book + ... | Subject) to account for the fact the trials are nest…
Comment by MSB October 2019
• Hmmm... Given your data and design, probably the most correct analysis would be a multinomial logistic regression... But let's stick to an ANOVA-like design. It seems %A and %B are dependent (negatively). You can deal with this dependance in two way…
Comment by MSB October 2019
• How dependent are A and B? If they are completely dependent (say 100% gaze = GazeA + GazeB), than no need to put both measurements into the model - the intercept will give an indication for both, the main effect for condition (X/Y) will actually be …
Comment by MSB October 2019
• Hi Gabriel, Until the JASP R package is available 😅, you can use bayestestR::bayesfactor_inclusion()(gives the same results as JASP). Mattan
Comment by MSB October 2019
• Everything seems like it should work... Sorry I couldn't be of more help...
Comment by MSB September 2019
• And the JASP data format is in the wide format? Very weird indeed...
Comment by MSB September 2019
• JASP uses BayesFactor under the hood, so they should produce the same results... The only thing I can think of is if the data is a repeated measures design, and the ID random intercept is miss-specified somewhere..
Comment by MSB September 2019
• Hi Lior, Bayes factors are the ratio of P(Data|M) (the likelihood), not P(M|Data) (the posterior probability of the model). Hope that helps!
Comment by MSB September 2019
• Hi Flaihai, If you are interested in accounting for knowledge gained in the first study, you can use a replication Bayes factor (for a simple application you can read DOI:10.3758/s13428-018-1092-x), assuming this is a direct / exact replication. Goo…
Comment by MSB September 2019
• It would see that the matrix is organized with row as the numerator and column as the denominator (@EJ this does seem counter-intuitive...), so 31735.222 represents how much more likely H1 is compared to H2. You can also see that the PMP (Posterior…
Comment by MSB August 2019
• What you want is to order-restrict your H1 model. This can be done in one of the following: Newest version of JASP has a BAIN module seems to do just this (but is in BETA) with "model constrains". More info here >> Write some custom …
Comment by MSB August 2019
• But maybe replace order of magnitude on base 10, with order of magnitude on base-e (which is basically the classical cut-offs for BFs)..
Comment by MSB August 2019
• > but still human I resent your assumptions, sir! But yes, you are right - it would affected my interpretation somewhat 😞 (But that is a change of X4, what you described was a change of <X2, no?)
Comment by MSB August 2019
• As you mention these fluctuations are minor (I would say that a change less than an order of magnitude is not substantial for a BF that is a ratio, after all). What to do? Tread lightly - I think it is reasonable to explain in ms that due to instabi…
Comment by MSB July 2019
• Hi Chris, JASP uses the afex package for (rm)AN(C)OVA. Among other things, afex (1) makes sure factors have effect coding, and (2) used type III errors (whereas summary.aov uses type II), both of which affect estimates and significances in unbalance…
Comment by MSB July 2019
• The reason you have and exclusion BF is that you have - under Bayes Factor - marked BF01. If you want the inclusion BF mark BF10. Note that these are reciprocal - BF01 = 1/BF10, and BF_inc = 1/BF_exc.
Comment by MSB June 2019
• Generally, yes - but I'm not sure you want to use whichModels = "bottop" - it is advised to stick with the defaults here (whichModels = "withmain") (see here). Also you can't really get a BF for an F test - as BF are always compa…
Comment by MSB June 2019
• These look really good! It is okay if I use them for class? Just one note: on the left panel, the gray points aren't exactly the point-null, they represent the likelihood of the null value on the alternative prior and posterior distributions. You ca…
Comment by MSB June 2019
• The posterior distribution(s) does not equal what you wrote, but the posterior odds do. Note sure what you mean by: That's because the approach doesn't permit defining the alternative hypothesis as, specifically, the degree of second-order uncertain…
Comment by MSB June 2019
• But the Bayes factor does not support updating with respect to H and I. Instead, it involves updating with respect to H and J, where J is not the same hypothesis as I The BF is based on model I completely - it simply incorporated information regardi…
Comment by MSB June 2019
• Okay, never mind - I got it now - reading the original post more closely ^_^
Comment by MSB June 2019
• Looking at the code, I understand that models with interactions are compared only to models with all the main effects. But why is this?
Comment by MSB June 2019
• Hi Richard, I think you might have mixed the prior distribution with the prior odds. Say you want to test if there is or isn't a difference between two groups. For this you would construct two models: Model A, in which the difference is non-zero. Mo…
Comment by MSB June 2019
• Your conclusions seem correct. One option would be to report these results. Another option might be to fit and test your specified model (one main effect and the interaction) in R: library(BayesFactor) data(puzzles) # example of 2*2 data # This i…
Comment by MSB May 2019
• Thanks Richard! This is very helpful!
Comment by MSB May 2019