#PowerAnalysis
LightNews LightNews
psychscience.bsky.social
Advanced stats like SEM & MLM are great, but how often do we estimate power for complex hypotheses? David Cole & @abitantegeorge.bsky.social share tips on using & interpreting power analyses. #PowerAnalysis #Statistics #ResearchMethods #DataScience #AdvancedStats
Tips for Estimating Power in Complex Statistical Models
David Cole and George Abitante present recommendations for using and interpreting power analyses.
www.psychologicalscience.org
March 17, 2025 at 4:09 PM
mzloteanu.bsky.social
#statstab #417 {pwrss} Practical Power Analysis in R

Thoughts: Some useful vignettes for conducting power analyses for various designs, constraints, and data types.

#poweranalysis #samplesize #r #power #guide #tutorial #sesoi #equivalence #tost #rstats

cran.r-project.org/web/packages...
Practical Power Analysis in R
cran.r-project.org
September 16, 2025 at 7:44 PM
mzloteanu.bsky.social
#statstab #230 Power and Sample Size Determination

Thoughts: Frequentist power is a complicated and non-intuitive thing, so it's good to read various tutorials/papers until you find one that sticks.

#stats #poweranalysis #power #NHST #effectsize

sphweb.bumc.bu.edu/otlt/mph-mod...
Power and Sample Size Determination
sphweb.bumc.bu.edu
November 22, 2024 at 6:52 PM
mzloteanu.bsky.social
#statstab #524 {simglm}: Tidy simulation and power analyses

Thoughts: As your design becomes more complex, simulation is the only way to go.

#simulation #r #rstats #tidy #tidyverse #poweranalysis #design #tutorial

simglm.brandonlebeau.org
Simulate Models Based on the Generalized Linear Model
Simulates regression models, including both simple regression and generalized linear mixed models with up to three level of nesting. Power simulations that are flexible allowing the specification of m...
simglm.brandonlebeau.org
May 1, 2026 at 6:31 PM
mzloteanu.bsky.social
🚨New blog post 📝: Your Study Is Too Small (If You Care About Practically Significant Effects)

#effectsize #precision #poweranalysis #research #Psychology #MCID

open.substack.com/pub/mzlotean...
Your Study Is Too Small (If You Care About Practically Significant Effects)
Power ≠ Precision, the misguided comfort of 80% power
open.substack.com
June 1, 2025 at 12:41 PM
mzloteanu.bsky.social
#statstab #464 Should a pilot study change your study design decisions?

Thoughts: You shouldn't use the ES, but you can use the SD (see also #192) for planning.

#pilot #experiments #poweranalysis #standarderror #simulation #methodology #SD #TypeM

declaredesign.org/blog/posts/p...
Should a pilot study change your study design decisions? – DeclareDesign
declaredesign.org
January 15, 2026 at 7:13 PM
mzloteanu.bsky.social
#statstab #535 The Benefits Of Reporting Critical Effect Size Values

Thoughts: You ran a study w/o a power analysis? Report the lowest value your test could have detected at 80% power and 5% alpha.

#poweranalysis #effectsize #samplesize #posthoc

osf.io/preprints/ps...
OSF
osf.io
May 20, 2026 at 6:02 PM
pelagic.bsky.social
Coming soon! Statistics and Data Handling for Biologists by Neil Millar 📖

Learn more and preorder your copy ➡️ https://tinyurl.com/mrxx6vbw

#biology #statistics #statisticssoftware #excel #jamovi #effectsize #poweranalysis
August 21, 2025 at 9:21 AM
mzloteanu.bsky.social
#statstab #592 ANOVA: Mixed-Effects (F-Test) {pwrss}

Thoughts: A slightly more comprehensive view of interaction testing in ANOVA.

#poweranalysis #samplesize #rstats #r #package #guide #effectsize #interaction

cran.r-project.org/web/packages...
Practical Power Analysis in R
cran.r-project.org
August 11, 2026 at 4:54 PM
mzloteanu.bsky.social
#statstab #609 When power analyses based on pilot data are biased: Inaccurate effect size estimators and follow-up bias

Thoughts: Don't judge effects by impressive pilot data.

#poweranalysis #bias #samplesize #error #eta2 #omega #epsilon #effectsize

www.sciencedirect.com/science/arti...
When power analyses based on pilot data are biased: Inaccurate effect size estimators and follow-up bias
When designing a study, the planned sample size is often based on power analyses. One way to choose an effect size for power analyses is by relying on…
www.sciencedirect.com
September 3, 2026 at 5:25 PM
mzloteanu.bsky.social
#statstab #453 {Bayes Power}
A General Application of Power and Sample Size Calculation for the Bayes Factors

Thoughts: Blending frequentist notions of power with bayes hypothesis testing.

#poweranalysis #bayesian #bayesfactor #errorrate #rstats #nhbt

doi.org/10.31234/osf...
OSF
doi.org
November 5, 2025 at 7:08 PM
mzloteanu.bsky.social
#statstab #479 Uncertainty limits the use of power analysis

Thoughts: Frequentists avoiding uncertainty is never good.

#poweranalysis #error #uncertainty #simulation #cohend #effectsize

www.researchgate.net/publication/...
(PDF) Uncertainty Limits the Use of Power Analysis
PDF | The calculation of statistical power has been taken up as a simple yet informative tool to assist in designing an experiment, particularly in... | Find, read and cite all the research you need o...
www.researchgate.net
December 11, 2025 at 3:55 PM
thetraceparadigm.substack.com
"Putin's dictatorship." The dominant frame in Western media and Russian opposition alike. It contradicts 62 years of structural evidence. Since 1964, the ruling class has never handed supreme power to one person. Putin is not the exception. He is the pattern.
#Russia #geopolitics #poweranalysis
May 26, 2026 at 11:13 AM
mzloteanu.bsky.social
#statstab #595 Required Sample Size to Detect the Mediated Effect

Thoughts: Do with this information what you will.

#mediation #samplesize #poweranalysis #power #error #type2 #causalinference

journals.sagepub.com/doi/full/10....
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
journals.sagepub.com
August 14, 2026 at 5:26 PM
mzloteanu.bsky.social
#statstab #477 Simulating data for Dirichlet regression with varying estimates

Thoughts: Interesting thread about an underused model.

#Dirichlet #brms #poweranalysis #rstats #proportions #stan #forum

discourse.mc-stan.org/t/simulating...
Simulating data for Dirichlet regression with varying estimates
Hello everyone, The shortest formulation of my problem is the following: I’m trying to design a power analysis by simulation for a Dirichlet regression model using brms. How could we calculate the s...
discourse.mc-stan.org
December 9, 2025 at 8:27 PM
mzloteanu.bsky.social
#statstab #603 A More Complete Post on Decision Theory and EVSI in A/B Testing

Thoughts: Interesting to consider, mostly for replications imo.

#samplesize #poweranalysis #bayesian #evsi #loss #utility #ABtesting #decisiontheory

dpananos.github.io/posts/2026-0...
A More Complete Post on Decision Theory and EVSI in A/B Testing – Demetri Pananos Ph.D
dpananos.github.io
August 26, 2026 at 5:52 PM
mzloteanu.bsky.social
#statstab #444 {popower}: Power and Sample Size for Ordinal Response

Thoughts: Not the most intuitive but useful if you know the DGP will use ordinal data.

#ordinal #poweranalysis #power #effectsize #rstats #stats

rdrr.io/cran/Hmisc/m...
popower: Power and Sample Size for Ordinal Response in Hmisc: Harrell Miscellaneous
rdrr.io
October 23, 2025 at 7:34 PM
mzloteanu.bsky.social
#statstab #371 Safeguard Power as a Protection Against Imprecise Power Estimates

Thoughts: tl;dr - when replicating a study, use the lower end of the CI of the original study as your effect in a power analysis.

#poweranalysis #samplesize #replication

journals.sagepub.com/doi/10.1177/...
Safeguard Power as a Protection Against Imprecise Power Estimates - Marco Perugini, Marcello Gallucci, Giulio Costantini, 2014
An essential first step in planning a confirmatory or a replication study is to determine the sample size necessary to draw statistically reliable inferences us...
journals.sagepub.com
June 23, 2025 at 8:11 PM
mzloteanu.bsky.social
#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 #clm

library.virginia.edu/data/article...
August 9, 2024 at 6:06 PM
mzloteanu.bsky.social
#statstab #440 Computing Statistical Power for the Difference in Differences Design

Thoughts: DiD studies are all the rage in Obs research. But how does the concept of power apply to them?

#poweranalysis #DiD #causalinference #samplesize #observational

journals.sagepub.com/doi/10.1177/...
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
journals.sagepub.com
October 17, 2025 at 7:20 PM
joachimschork.bsky.social
Today, I released a new module in the Statistics Globe Hub that explains how to perform sample size calculation using power analysis.

More info about the Statistics Globe Hub: statisticsglobe.com/hub

#rstats #datascience #statistics #poweranalysis #samplesize #studyplanning #statisticsglobehub
March 16, 2026 at 12:53 PM
mzloteanu.bsky.social
Finishing my migration to #substack here is:

What NOT to do with NON-“null” results Part III: Underpowered study, but significant results open.substack.com/pub/mzlotean...

#rstats #statistics #poweranalysis #typeM #falsediscoveryrate #NHST
open.substack.com
February 9, 2024 at 12:08 PM
digitalscorpyun.bsky.social
White America, not the DSA, held the power to secure Harris. That’s where the abandonment happened. Everything else is deflection. #USPolitics #PowerAnalysis

Brookings: DSA ≈ 78,000 people in a nation of 168M voters.

Meaning: Even full unity inside the DSA cannot move a presidential outcome.
November 26, 2025 at 11:39 PM
goringennady.bsky.social
How many samples should you sequence?
Collect too few, and the experiment is inconclusive. Collect too many, and the costs add up very quickly.
Check out our bioRxiv preprint and calculator at poweranalysis-fb.streamlit.app! 1/
March 5, 2026 at 8:27 PM
mzloteanu.bsky.social
#statstab #371 Safeguard Power as a Protection Against Imprecise Power Estimates

Thoughts: tl;dr - when replicating a study, use the lower end of the CI of the original study as your effect in a power analysis.

#poweranalysis #samplesize #replication

journals.sagepub.com/doi/10.1177/...
June 23, 2025 at 8:11 PM