If I collect some data for a new treatment, but don't collect a control group, can I use the data from an older study that has the control condition? If so, how would I integrate this into my analysis? and what is the name for this? historical control?

#statstodon #stats #research #bayesian

If I were to say that the primary benefit of randomization (and possibly blinding) is that it makes simple statistical models match the true data generating process quite well, would that be a provocative statement? Or would that be obvious? Is there a good reference for this line of reasoning?

#stats #statstodon #phil #philosophy #philsci #philscidon

#r and #statstodon people: do you have any resources for running sensitivity power analyses for mixed effects models? (e.g. for fixed samples to determine what is the smallest reliable detectable effect at a specific power level)

#power #stats #NHST

Great guide to thinking about the age-period-cohort problem by Julia Rohrer: https://osf.io/preprints/psyarxiv/8zmuv

#stats #statstodon

In the latest installment of "Statistical Ideas that Changed the World", son Ryan interviews father Rob Tibshirani, humor included.
https://www.youtube.com/watch?v=3rvl4KV41JE&list=PLt_pNkbycxqahVksaNnjz3M6759xHIZ-r&index=15
#RStats #statstodon #machineLearning

🚨 New Substack Post - A secret third way: Likelihoodist statistics

I provide a quick tutorial on conducting research using the Likelihoodist approach. It's step-by-step + #R code

https://open.substack.com/pub/mzloteanu/p/a-secret-third-way-likelihoodist?r=3b457w&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#substack #statistics #education #guide #science #research #statstodon #stats #tutorial

@vbuendiar I used Statistics for the Life Sciences by Myra Samuels when I was at uni and I've consulted it occasionally since. One of these open access intros to statistics may suit you:
https://openstax.org/details/books/introductory-statistics
https://open.umn.edu/opentextbooks/textbooks/459
https://openintro-ims.netlify.app
https://directory.doabooks.org/handle/20.500.12854/34734
#Statistics #StatisticsBasics #StatsEducation #StatsTeaching #Statstodon

#statstab #42 Bayes Factors in #brms

Thoughts: Bayes Factors are just the ratio of the height difference of two points on two lines, don't @ me! (seriously, that's how most packages commute it)

#rstats #jasp #bayesian #bayesfactors #SavageDickey #ResearchMethods #psychology #statstodon

https://mvuorre.github.io/posts/2017-03-21-bayes-factors-with-brms/

#statstab #39 Permutation test for "sharp" vs "weak" null hyp

Thoughts: Perm/Rand tests have a different (often inappropriate) Null Hypothesis. The similarity in estimates to asymptomatic tests is misleading wrt their inference.

#permutation #nhst #statistics #statstodon #experiments

https://stats.stackexchange.com/questions/315891/permutation-tests-for-sharp-vs-weak-null-hypothesis

#statstab #35 Is R2 useless?

Thoughts: Yesterday I showed how to plot R2, now I post about why you might not want to. The points are valid (imo), but not unknown. Metrics are only useful if you accept their assumptions.

#R2 #rstats #research #stats #statstodon #statistics #psychology #regression

https://library.virginia.edu/data/articles/is-r-squared-useless

#statstab #26 Divergence vs decision p-values

Thoughts: A lot of confusion about p-values can be resolved by realising that Fisherian p-values are different from NHST p-values. Useful paper.

#stats #pvalues #NHST #DataScience
#statistics #statstodon

https://onlinelibrary.wiley.com/doi/10.1111/sjos.12625

#statstab #19 Model Estimation Options, Problems, and Troubleshooting

Thoughts: A nice guide on model convergence issues, REML vs FIML, and model comparison (frequentist s)

#mixedeffects #rstats #stats #statstodon

https://www.learn-mlms.com/07-module-7.html

#statstab #17 {emmeans} for unpacking interactions

Thoughts: Neither SPSS, JASP, or Jamovi can give you all the stats to unpack/report a 3x3 mixed ANOVA. But it's super easy with emmeans. Also learned "joint = TRUE" for simple effects.

#stats #rstats #statstodon #emmeans #anova

https://cran.r-project.org/web/packages/emmeans/vignettes/interactions.html

#statstab #15 Bland-Altman plots

Thoughts: When I learned what these are, I was surprised how rarely (ever?) I see them in papers on "revised questionnaire X". This seems like exactly what readers want to see.
#rstats #pyschometrics #measure #stats #statstodon #statistics

https://thestatsgeek.com/2020/12/03/what-does-correlation-in-a-bland-altman-plot-mean/

#statstab #14 Regression Discontinuity - does it make sense?

Thoughts: Not something I use, and I only learned of it from blogs like this one that critique the practice. I wonder what people think 🤔
#regression #stats #statstodon #statistics
https://statmodeling.stat.columbia.edu/2021/11/21/sausage-notice/

#statstab #12 WebPlotDigitizer - extract data from plots

Thoughts: Cool piece of software for data sleuths, and meta-analyses looking at old (or poorly reported) papers.

#stats #plots #dataviz #forensic #statstodon

https://automeris.io/WebPlotDigitizer/

#statstab #11 A Critical Perspective on Effect Sizes

Thoughts: A nice blog post reminding us to be critical of reported ES and their meaning. First time I considered effects being "too large" in pubs.

#effectsize #stats #statstodon #statistics

https://quentinandre.net/post/a-critical-perspective-on-effect-sizes/

Ran into another "in the wild" instance of a failed rejection of a null hypothesis being interpreted by medical researchers as evidence of no effect.

Absence of evidence is not evidence of absence.

#statstodon #stats

#statstab #10 A calculator for single-case effect size indices

Thoughts: R2 said my N=1 analysis was "the effect of Bob" and was meaningless. Later, I came across Single Case Experimental Design research (SCED). 1 case can have value, just different!

https://jepusto.github.io/SingleCaseES/

#rstats #stats #statstodon #nof1 #sced

I often see researchers confuse the effects they can measure in experiments vs observational studies. This fig from https://doi.org/10.1177/00031224211004187 is my go-to when explaining this:

#stats #causaleffect #statstodon #experiments #DAGs #research