Lmst

#statstab #282 Plotting ordinal logistic predicted effects on latent scale of ordinal outcome {ggeffects}

Thoughts: An interesting discussion on plotting ordinal data on the latent scale or probability scale.

#dataviz #ggeffects #ordinal #latent #likert

https://github.com/strengejacke/ggeffects/issues/507

#statstab #262 One-way Repeated Ordinal Regression with CLMM

Thoughts: You've heard that ANOVA isn't appropriate for ordinal data. Here's a nice tutorial on an alternative, with effect size reporting and plotting.

#ordinal #clmm #clm #ANOVA #r

https://rcompanion.org/handbook/G_08.html

#statstab #258 What's wrong with rating scales?

Thoughts: A scathing review of "scales" in Psychology. But, can be a useful paper for students to get a sense of experiment and survey design, and #psychometrics.

#measurement #psychology #scales #ordinal #likert #validity #language #personality #replication

https://compass.onlinelibrary.wiley.com/doi/10.1111/spc3.12740

#statstab #257 Permutation tests are robust and powerful at 0.5% and 5% significance levels

Thoughts: Permutation tests are cool and useful to learn, although they come with some quirks.

#permutation #randomization #ttest #ordinal #metricdata

https://link.springer.com/article/10.3758/s13428-021-01595-5

#statstab #210 Effect Sizes for ANOVAs {effectsize}

Thoughts: ANOVAs are rarely what ppl want to report, but if it is then report an effect size! Just mind the % for the CIs 😉

#ANOVA #effectsize #APA #reporting #nonparametric #eta2 #ordinal

https://easystats.github.io/effectsize/articles/anovaES.html

#statstab #198 Bayesian mixed effects (aka multi-level) ordinal regression models with {brms}

Thoughts: Useful tutorial also for frequentists, as it covers checking multiple links at once in {ordinal}.

#ordinal #brms #clmm #probit #cloglog #r #cauchit

https://kevinstadler.github.io/notes/bayesian-ordinal-regression-with-random-effects-using-brms/

@philosophy
#infinite #math

nice take in 2 1/2 open acccess pages,

wrt #philosophers were well advised to not limiting the scope of their attention to #cardinal #numbers when referring to the #math #infinite. equally important [besides #ordering #structures and especially #ordinal #numbers] are e.g. #measures on #infinite #Booelan #lattices [#probability only a special case of these]

https://link.springer.com/article/10.1007/s10670-022-00643-6

#statstab #173 Comparison of binary, ordinal and metric answer formats

Thoughts: "[same] interpretations & reliability; differ in speed [...] equally simple, pleasant, and useful"
I rate this result 3/5.

#binary #likert #ordinal #metric #ratings #survey

https://core.ac.uk/download/pdf/36990394.pdf

#statstab #164 Ordinal regression models to analyze Likert scale data

Thoughts: One of the clearest tutorial for ordinal, cumulative (probit), models I've seen. Reports probabilities and expected mean ratinga, w/ plots!

#ordinal #brms #likert #probit #r

https://dibsmethodsmeetings.github.io/ordinal-regression/

#statstab #161 Ridit scores for analysis and interpretation of ordinal (pain) data

Thoughts: A less well-known ordinal analysis. Ridits are scale and integer invariant, and provide effect magnitude comparisons.

#ordinal #ridits #statistics #probability

https://www.sciencedirect.com/science/article/abs/pii/S1090380198900180

#statstab #160 Is the difference between two ordinal variables ordinal?

Thoughts: Yes. No. Maybe. Can you repeat the question? Some big names in stats are in the thread providing insightful replies. I'm undecided.

#ordinal #statistics #measurement #data

https://stats.stackexchange.com/questions/585799/is-the-difference-between-two-ordinal-variables-ordinal

#statstab #155 Power & Sample Size calculations for ordinal data {Hmisc}

Thoughts: An appropriate sample size is just as important as an appropriate (ordinal) analysis. Nice guide for a 2-group design with a Likert-type DV.

#ordinal #NHST #poweranalysis

https://library.virginia.edu/data/articles/power-and-sample-size-calculations-ordered-categorical-data

code example for computing sample size with ordinal data

#statstab #143 {likert} package: Analysis and Visualization of Likert Based Items

Thoughts: As the battle for best way to visualise ordinal data continue, here is a package that does some straightforward plots.

#R #likert #ordinal #dataviz #survey

https://jbryer.github.io/likert/

#statstab #81 Visualisation of ordinal models

Thoughts: I run a lot of ordinal models, but still haven't found a way to plot the models to be both "accurate" and interpretabile.

#ordinal #dataviz #brms #likert

https://towardsdatascience.com/testing-an-alternative-visualisation-of-ordinal-data-and-regression-in-r-1dc838fcaa2d

#statstab #66 Ordinal Regression in #R

Thoughts: Nice tutorial. I liked the visualisation of the potential priors. It's good to think of how ordinal data might be distributed.

#rstats #brms #priors #ordinal #bayesian

https://tdunn.ca/posts/2020-03-17-ordinal-regression-in-r-part-2/

Can you see why Drake is so opinionated about how this "X out of 5 Stars" rating scale is being used?

Scales, they're everywhere, and everywhere abused!

#Nominal #Ordinal #Interval #Ratio

https://open.substack.com/pub/capnsblog/p/types-of-scales?r=9z45&utm_campaign=post&utm_medium=web&showWelcome=true

Drake meme. Shunning 4.6 out of 5 stars. Pointing approvingly at bar chart with each star rating shown

The first issue of the new Transactions on #Graph #Data and #Knowledge (#TGDK) was published yesterday --- a new Diamond #Open #Access journal. Included is our vision article on the future role and prospective methods of #Ordinal Data Science.

'Insights into Ordinal Embedding Algorithms: A Systematic Evaluation', by Leena Chennuru Vankadara, Michael Lohaus, Siavash Haghiri, Faiz Ul Wahab, Ulrike von Luxburg.

http://jmlr.org/papers/v24/21-1170.html

#embeddings #embedding #ordinal