Helpful cat also likes the vertical mouse.

Yes, the handwaving is problematic, especially for single-item analysis (of any ordinal scale). And when you find a scale (DERS) with these response distributions, it raises a lot of questions. My initial example post was also from this scale.

Another example of how useful {geomtextpath} can be, imho. This is from the item category probability plot in my {easyRasch2} package. Most psychometric papers within the factor analytic tradition seem to disregard evaluating how the response scale works, which I find difficult to understand.

To make it more accessible to use up-to-date psychometric methods, I have made a module for www.jamovi.org, which has a nice point-and-click user interface. 'easyRasch2jmv' can be installed from within jamovi. The updated module added helpful text output together with the analysis output.

We really need a collective effort to leave rule-of-thumb cutoffs and incorrect methods behind us. I think a key aspect is to treat older psychometric validations with skepticism, both in paper intros and method sections. "Inaugural" papers are particularly important to scrutinize.

New Jamovi module functionality to determine appropriate model fit cutoffs for confirmatory factor analysis now available in easyRasch2jmv v0.4.0. Install/update from Jamovi Library within the app. #rstats #psychometrics #stats #openscience

New family member today.

You can also get traceplots for item category probabilities and targeting (person-item Wright map), and conditional item characteristic curves.

I've made an R package for Bayesian Rasch #psychometrics with brms models, easyRaschBayes (on CRAN), implementing simple functions to create figures and tables with model fit metrics, etc. Attaching figures from conditional item infit, item-restscore with GK gamma, and the log-likelihood criterion.

I like them, but in this format (from smped.github.io/SimpleUpset/... )

geomtextpath can really help make a plot easier to interpret. Nice to avoid using a legend. #rstats #dataviz

More tinkering with relative measurement uncertainty proposed by @bignardi.bsky.social et al, using plausible values to estimate conditional reliability (inspired by @dmcneish.bsky.social) for Rasch models with WL estimation of latent scores. Code here: github.com/pgmj/easyRas...

I've done some more work on the relative measurement uncertainty, comparing `brms` posterior draws to "plausible values" in Rasch models, and some other reliability metrics. Estimating RMU from draws adds some variation, as shown in the figure. pgmj.github.io/reliability.... #rstats #psychometrics

The RelRep.R function "just works" with a dataframe with items as columns and produces pretty neat output for alpha or omega. Point estimate and CI for alpha is almost identical to RMU for my example with `eRm::raschdat1[,1:20]` data. github.com/melissagwolf...

For instance, yesterday I read a paper with a table describing participants' sickness absence days with a mean of 71 and SD = 88. Generating a random (gaussian) sample using these values produces ~20% participants with less than zero sick days.

Grateful to have this view a few minutes walk from home.

Inspired by a paper (linked) that added a response category to the PHQ-2 and GAD-2 screener questionnaires we did the same in Swedish with good results in a sample of 15-18 year olds. The uppermost categories performed worse, though (q25-26=GAD,27-28=PHQ). #psychometrics osf.io/preprints/ps...

Reading the preface to "Thinking through statistics" and this section already made me like the book.

Might be the perfect guitar string gauge? Seems ridiculous, but .005 inches thinner than the .011 I've used forever on my solid body seems really nice.

...since it needs revising (ongoing) to incorporate correct information about critical values for GOF metrics: osf.io/preprints/os... We basically use the 4 criteria as presented by Kreiner (2007), who refers to Rosenbaum (1989).

Really looking forward to this. It's been six years since his last book.

Great to see conditional reliability and the "targeting" of test/sample discussed. I've incorporated a similar approach in a TIF curve figure in the `easyRasch` R package. Note that IRT/Rasch also provides information about the reliability of the test/questionnaire itself, independent of the sample.

Such style and grace. Have one of those too

Made with a Makina 67 a few years ago. Rollei Retro 400S overexposed a step and developed in Adox Silvermax 1+19. #filmphotography #blackandwhite #believeinfilm

Sunset at 13.30 has some benefits.

Stunning clouds, which my old phone struggles to reproduce.