using the debug.csv dataset and creating a new variable (contNormal scaled), ordering the if item dropped plot fails when choosing KLD to order:

Sería interesante que puedan incluir en la seccion de información de jasp , el contenido y los procedimientos de la confiabilidad bayesiana, así sería mas facil usarlo y poder recomendarlo.

needs new Bayesrel version (0.7.0.6) because there are no priors saved for only two items

Recently I calculated Cohen's kappa with SPSS and with JASP. Unfortunately, JASP sometimes produces strange results that do not correspond at all to the results of SPSS. E.g.: a test with N=59. Cohen's kappa in SPSS is 0.873, and kappa in JASP is -0.031.
For comparison, I also calculated the percentage agreement: 93.3%. Higher than Cohen's kappa from SPSS, but that is what you expect.
So it seems that de kappa from SPSS is right, but what happens with the kappa from JASP? There were 14 missings, can this be the reason for the result in JASP?

For the Bayesian part of the module it makes sense to also have the ESS as an indication of autocorrelation. How should this be calculated? If we have 3 chains with 1000 iterations each, the ESS is computed for each chain anyways, but how should we report the results:

• three ESS values with a maximum of 1000 each
• one ESS value with a maximum of 3000
• a percentage of all three ESSs values together, for example, 2500/3000 = 83%?

How do other programs do that, if at all... Do you have any input @vandenman?

Jasp file:

https://github.com/jasp-stats/jasp-verification-project/blob/main/Datasets/Reliability.jasp

Note

• the upper bound of McDonald's omega used to be 0.771 now it's 0.777
• It looks like the McDonald's omega result in 0.13.1 are now Cronbach alpha's result

While making the verified unit test I see that that the "mean" results from the new module differ from the previous results.

In particular, the verified results show a mean of

https://jasp-stats.github.io/jasp-verification-project/reliability-module.html

whereas the new mean is 17.55. Julius, is this related to the mean of the sum scores (17.55) vs mean of the (column)means? See also the remark

JASP calculates the overall mean and SD across all questions, whereas other software calculates the overall mean and SD across subjects.

options <- analysisOptions("reliabilityUniDimFrequentist")
options$omegaScale <- TRUE
options$alphaScale <- TRUE
options$lambda2Scale <- TRUE
options$lambda6Scale <- TRUE
options$meanScale <- TRUE
options$omegaItem <- TRUE
options$alphaItem <- TRUE
options$lambda2Item <- TRUE
options$lambda6Item <- TRUE
options$itemRestCor <- TRUE
options$itemMean <- TRUE
options$itemSd <- TRUE
options$omegaAnalytic <- TRUE

options$variables <- c(paste("Question", c(1, 4:8), sep="_0"), paste("Question", 10, sep="_"))
set.seed(1)
results <- jaspTools::runAnalysis("reliabilityUniDimFrequentist", 
                                  paste0(packagePath, "/tests/testthat/Reliability.csv"), options)