#statstab
🔍 New website for my #statstab posts! mz555.github.io/statstab/

There are now hundreds (!) of these posts, covering everything from stats quirks and causal inference and data vis.

The site brings it all together in one place and lets you search by title, topic, year, or hashtag.
#statstab — a searchable stats tab archive
A searchable multi-source archive of Mircea Zloteanu's #statstab posts.
mz555.github.io
October 31, 2026 at 2:37 PM
#statstab #679 Trending Agreement: Bland–Altman Is All You Need

Thoughts: Even something like showing agreement can be quite difficult.

#agreement #concordance #blandaltman #bias #methods #tutorial #polarplot #analysis
#trend

www.ovid.com/10.1213/ANE....
October 29, 2026 at 7:49 PM
#statstab #678 How Many Participants Do I Need to Test an Interaction?

Thoughts: The shape of your interaction can require a huge sample (unlike what G*Power says)

#samplesize #power #interaction #experiment #tutorial #guide

doi.org/10.1177/2515...
October 28, 2026 at 6:14 PM
#statstab #680 Advanced DiD: Violations of Parallel Trends

Thoughts: A strong assumption to make and test.

#DiD #observational #causalinference #assumptions #tutorial #guide

github.com/Mixtape-Sess...
Advanced-DID/Slides/03-violations.pdf at main · Mixtape-Sessions/Advanced-DID
Advanced Differnce-in-Differences Mixtape Track taught by Jonathan Roth - Mixtape-Sessions/Advanced-DID
github.com
October 30, 2026 at 7:15 PM
#statstab #677* Reference for the claim that you need 16 times as much data to estimate interactions as to estimate main effects

Thoughts: Nice discussion of an older paper/problem.

*fixed the numbering!

#interaction #debate #discussion #samplesize

statmodeling.stat.columbia.edu/2020/10/16/r...
Reference for the claim that you need 16 times as much data to estimate interactions as to estimate main effects | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
October 26, 2026 at 6:23 PM
#statstab #645 Accuracy in parameter estimation and simulation approaches for sample-size planning accounting for item effects

Thoughts: For "studies that may not have a specific hypothesis test"

#poweranalysis #simulation #aipe #estimation #power #tutorial

doi.org/10.3758/s134...
Client Challenge
doi.org
October 23, 2026 at 7:16 PM
#statstab #644 The Causal Mediation Formula – A Guide to the
Assessment of Pathways and Mechanisms

Thoughts: I have no opinions to share on this.

#mediation #causalinference #totaleffect #indirecteffect #moderation #modelling

ftp.cs.ucla.edu/pub/stat_ser...
ftp.cs.ucla.edu
October 22, 2026 at 6:13 PM
#statstab #643 Use change scores or control for pre-treatment outcomes? Depends on the true data generating process

Thoughts: Holds for unobserved stable confounding

#ancova #changescore #baseline #covariates #confounding #DiD #observational #experiment

declaredesign.org/blog/posts/u...
Use change scores or control for pre-treatment outcomes? Depends on the true data generating process – DeclareDesign
declaredesign.org
October 21, 2026 at 4:48 PM
#statstab #642 PublicationBiasBenchmark

Thoughts: R package for benchmarking publication bias correction methods through simulation studies.

#publicationbias #rstats #r #methods #bias #simulation #petpeese #rmse #robma #3psm #pcurve

fbartos.github.io/PublicationB...
Benchmark for Publication Bias Correction Methods
Implements a unified interface for benchmarking meta-analytic publication bias correction methods through simulation studies (see Bartoš et al., 2025, <doi:10.48550/arXiv.2510.19489>). It provides 1) ...
fbartos.github.io
October 20, 2026 at 4:31 PM
#statstab #641 On the defense of "change from baseline" even in randomized trials - can anyone question points in this article?

Thoughts: Sometimes a discussion is better for learning.

#ancova #prepost #rct #covariates #baseline #changescore #statistics

stats.stackexchange.com/questions/57...
On the defense of "change from baseline" even in randomized trials - can anyone question points in this article?
Many times I read a strong criticism on the change-from-baseline (adjusted for baseline or not) in both randomized and non-randomized. Several people advised “don't even think of reporting the change
stats.stackexchange.com
October 19, 2026 at 4:38 PM
#statstab #640 Prediction, Estimation, and Attribution

Thoughts: Useful if you do big data stuff.

#llm #bigdata #prediction #estimation #hypothesistesting #attribution #inference

med.stanford.edu/content/dam/...
med.stanford.edu
October 16, 2026 at 3:17 PM
#statstab #637 Evaluate What Is Claimed to Be Confirmed: Initial Version of a Falsification Assessment Form (FAF)

Thoughts: This seems like a faf🙃

#falsification #nhst #hypothesis #hypothesistesting #assumptions #causalinference
#OpenScience #auxiliary

meth.psychopen.eu/index.php/me...
Evaluate What Is Claimed to Be Confirmed: Initial Version of a Falsification Assessment Form (FAF)| Methodology
meth.psychopen.eu
October 14, 2026 at 10:59 AM
#statstab #638 How is a negative binomial regression model different from OLS with a logged outcome variable?

Thoughts: Some (questionable) potential pros of OLS.

#ols #negativebinomial #logit #transformation #regression #inference #discussion

stats.stackexchange.com/questions/23...
How is a negative binomial regression model different from OLS with a logged outcome variable?
I often deal with distributions of outcome variables that are highly skewed (power-law-like), and I typically want to predict these outcomes. I am wondering when it is appropriate to take a log of...
stats.stackexchange.com
October 14, 2026 at 3:57 PM
#statstab #636 Establishing Psychological Phenomena: An Alternative Methodological Perspective On Scientific Practice

Thoughts: Is psych science a data-phenomenon-theory framework?

#theory #psychology #inference #falsification #effects #science #popper

osf.io/preprints/ps...
OSF
osf.io
October 12, 2026 at 5:48 PM
#statstab #635 Standardization and other approaches to meta-analyze differences in means

Thoughts: A good resource for selecting the standardiser in your SMD & comments for the {metafor} pkg.

#metaanalysis #smd #effectsize #cohend #bias #heterogeneity

onlinelibrary.wiley.com/doi/10.1002/...
Standardization and other approaches to meta‐analyze differences in means
Meta-analysts often use standardized mean differences (SMD) to combine mean effects from studies in which the dependent variable has been measured with different instruments or scales. In this tutori...
onlinelibrary.wiley.com
October 9, 2026 at 4:32 PM
#statstab #634 Standardized Regression Coefficients: A Further Critique and Review of Some Alternatives

Thoughts: Devastating critique of SMDs (e.g. Cohen's d or Pearson's r).

#smd #cohend #effectsize #estimand #standardization #covariates #ancova #SD

www.ovid.com/jnls/epidem/...
Standardized Regression Coefficients : Epidemiology
Abstract was not provided for this article.
www.ovid.com
October 8, 2026 at 7:15 PM
#statstab #633 The Well-Adjusted Statistician: Analysis of Covariance Explained

Thoughts: Randomization +ANCOVA. Inc prognostic covariates improves precision
#ancova #randomization #confidenceintervals #experiment #inference #precision #covariates
www.appliedclinicaltrialsonline.com/view/well-ad...
The Well-Adjusted Statistician: Analysis of Covariance Explained | Applied Clinical Trials Online
How to account and adjust for covariates in clinical trial randomization-and be confident about uncertainty.
www.appliedclinicaltrialsonline.com
October 7, 2026 at 3:03 PM
#statstab #632 Decline effects, statistical artifacts, and a meta-analytic paradox

Thoughts: Plz don't flip/reverse your effects without thinking about the scale!

#metaanalysis #bias #error #effectsize #effects #critique #artifact

raw.githubusercontent.com/richarddmore...
raw.githubusercontent.com
October 6, 2026 at 3:54 PM
#statstab #631 Prior Information in Frequentist Research Designs: The Case of Neyman’s Sampling Theory

Thoughts: Model-based v design-based problem. This should be discussed more.

#modelbased #designbased #sampling #priors #neyman #frequentist #bayesian

link.springer.com/article/10.1...
Prior Information in Frequentist Research Designs: The Case of Neyman’s Sampling Theory - Journal for General Philosophy of Science
We analyse the issue of using prior information in frequentist statistical inference. For that purpose, we scrutinise different kinds of sampling designs in Jerzy Neyman’s theory to reveal a variety o...
link.springer.com
October 5, 2026 at 8:16 PM
#statstab #630 A Tutorial on Distribution-Free Uncertainty Quantification Using Conformal Prediction

Thoughts: Conformal predictions are getting more popular.

#conformalprediction #frequentist #uncertainty #assumptions #distributions #tutorial

doi.org/10.1177/2515...
A Tutorial on Distribution-Free Uncertainty Quantification Using Conformal Prediction - Tim Kaiser, Philipp Herzog, 2025
Statistical prediction models are ubiquitous in psychological research and practice. Increasingly, machine-learning models are used. Quantifying the uncertainty...
doi.org
October 2, 2026 at 5:56 PM
#statstab #629 Extreme-Value Signal Detection Theory For Recognition Memory: The Parametric Road Not Taken

Thoughts: Let's get ready to Gumbel!

#sdt #theory #modelling #gumbel #methods #statistics #tutorial #memory #discrimination

osf.io/preprints/ps...
Extreme-Value Signal Detection Theory for Recognition Memory: The Parametric Road Not Taken
Signal Detection Theory has long served as a cornerstone of psychological research, particularly in recognition memory. Yet its conventional application hinges almost exclusively on the Gaussian assum...
osf.io
October 1, 2026 at 6:30 PM
#statstab #628 Meta-analysis models relaxing the random-effects normality assumption: methodological systematic review and simulation study

Thoughts: Looks interesting, the little I get.

#metaanalysis #methods #statistics #assumptions
#randomeffects

link.springer.com/article/10.1...
Meta-analysis models relaxing the random-effects normality assumption: methodological systematic review and simulation study - BMC Medical Research Methodology
Background Random-effects meta-analysis is widely used for synthesizing the studies of a systematic review assuming a normal distribution for the study-specific effects. However, this assumption might...
link.springer.com
September 30, 2026 at 7:07 PM
#statstab #626 Goal-Driven Flexible Bayesian Design

Thoughts: Bayes allows you to design informative studies and anticipate issues.

#bayesian #bayes #design #simulation #rct #tutorial #inference #mcid #equivalence #efficacy #estimation #noninferiority

hbiostat.org/bayes/design
Bayesian Design
hbiostat.org
September 28, 2026 at 6:05 PM