Kristoffer Magnusson @rpsychologist.com · 03/10/2026A meme thread on how I feel every time I use ZIB/ZOIB models. Feel free to add your own 1190
Kristoffer Magnusson @rpsychologist.com · 25/06/2026Trying out Svelte for the first time here btw, really like it so far. Not sure why I didn't switch years ago. 0181
Kristoffer Magnusson @rpsychologist.com · 25/06/2026New interactive blog! "Why Adjusted Regression Coefficients Are Less Descriptive Than They Look" rpsychologist.com/descriptive-... 1520769
Kristoffer Magnusson @rpsychologist.com · 16/04/2026No one: Absolutely no one: Billion-dollar publisher in 2026: “We published the wrong version so our only option is to issue a retraction under your name” 190
Kristoffer Magnusson @rpsychologist.com · 10/11/2025Fun fact about LMMs: when you have missing data, power also depends on the correlation between intercepts and slopes. In the clip, I’m varying the amount of random slope variance. 020
Kristoffer Magnusson @rpsychologist.com · 07/11/2025Just added to PowerLMM.js v0.3: Interactive power contour plots! Visualize how statistical power changes across parameter combinations. powerlmmjs.rpsychologist.com?view=contour 2112
Kristoffer Magnusson @rpsychologist.com · 30/10/2025Wasn't that happy with how performance crashed as time points grew, so I dusted off some linear algebra to optimize the calculations. Benchmark showed a ~1Mx speedup using new implementation (with 100 time points) 😅 031
Kristoffer Magnusson @rpsychologist.com · 28/10/2025Calculations have been validated against R. Validation notes: github.com/rpsychologis... 130
Kristoffer Magnusson @rpsychologist.com · 28/10/2025Share your analysis as a URL, or store it as a JSON file. For example: powerlmmjs.rpsychologist.com?n1=13&time_e... 120
Kristoffer Magnusson @rpsychologist.com · 28/10/2025Power analysis summary report, that can be printed or saved as a PDF 130
Kristoffer Magnusson @rpsychologist.com · 28/10/2025Hypothesis region visualization. Interactive display of the chosen null and alternative hypothesis. 141
Kristoffer Magnusson @rpsychologist.com · 28/10/2025New release of PowerLMM.js! Browser-based power analysis for longitudinal models with dropout. Now includes: - Power analysis summary report - Reproducible & shareable configs (URL/JSON) - Calculations validated against R - Hypothesis region visualization powerlmmjs.rpsychologist.com 49343
Kristoffer Magnusson @rpsychologist.com · 26/06/2025Sips is always great, I'm hosting my own sessions 010
Kristoffer Magnusson @rpsychologist.com · 06/06/2025Turns out proportions aren't collapsible after all. Take that, OR haters. "Globally, approximately 3.3% of the population reports using AAS, with prevalence rates of 6.4% among men [2] and 4% among women [3]." 2193
Kristoffer Magnusson @rpsychologist.com · 23/05/2025Not sure where to start with this one. Internet gaming addiction… is a risk factor for internet gaming disorder 48012
Kristoffer Magnusson @rpsychologist.com · 19/05/2025Regarding the expert consensus on smartphone use: let’s not forget that the related “behavioral addiction” gaming disorder, is essentially a copy-paste job. Below is a visual comparison of the ICD-11 criteria for gaming and gambling disorder—essentially a substitution of terms. 140
Kristoffer Magnusson @rpsychologist.com · 06/05/2025I see this a lot in longitudinal analysis—people assume missingness can depend on random effects (like slopes). But those aren’t conditioned on, so that kind of missingness would be non-ignorable (MNAR). 171
Kristoffer Magnusson @rpsychologist.com · 05/05/2025🚨New R package! {easymediation}🚨 The *Simplest* and *Most Correct* Way to Do Causal Mediation Analysis Are you tired of explaining mediation analysis to your colleagues? Just send them this package. github.com/rpsychologis... 69422
Kristoffer Magnusson @rpsychologist.com · 05/05/2025Step 1: Say data are MNAR Step 2: Toss in random values Step 3: Call it conservative I’ll definitely adopt this model-free way of handling MNAR, what could go wrong? 130
Kristoffer Magnusson @rpsychologist.com · 02/05/2025Amazing observation in a paper: people use smartphones while waiting. I’ve also observed that people read magazines they’d never touch anywhere else while waiting. Proposing a new disorder: "Compulsive Magazine Reading". Urgent need for intervention programs 2265
Kristoffer Magnusson @rpsychologist.com · 29/04/2025I take this to mean that none of the included studies evaluated performance with respect to the estimand of interest 000
Kristoffer Magnusson @rpsychologist.com · 20/12/2024Added a variogram to the app! I'm experimenting with showing the non-stationarity of correlations in a random slopes model. 021
Kristoffer Magnusson @rpsychologist.com · 16/12/2024Added a simple illustration of group trends to demonstrate what the effect size represents 170
Kristoffer Magnusson @rpsychologist.com · 13/12/2024Just deployed some small updates: More tooltips! Offloaded the most expensive computations to background threads, and added a cheeky loader for the inevitable scenario where someone tries to inverse huge matrices at 60fps+. 140
Kristoffer Magnusson @rpsychologist.com · 11/12/2024You can also view the implied correlation matrix and how the random slopes impact the implied standard deviations at each time point 130
Kristoffer Magnusson @rpsychologist.com · 11/12/2024To better understand the random effect parameters, you can view a sample of 20 random slopes adjusted to match the exact variance and correlations specified 230
Kristoffer Magnusson @rpsychologist.com · 11/12/2024Dropout can be specified using either a Weibull distribution or manually 120
Kristoffer Magnusson @rpsychologist.com · 11/12/2024Introducing PowerLMM.js! A new tool for power analysis of longitudinal linear mixed-effects models (LMMs) – with support for missing data, plus non-inferiority and equivalence tests. powerlmmjs.rpsychologist.com Would really appreciate your feedback as I refine this app! Details below 🧵👇 11299110
Kristoffer Magnusson @rpsychologist.com · 28/11/2024"There is ongoing speculation about the potential reason." Maybe it's not solely caused by social media and iPhones? 👇 163
Kristoffer Magnusson @rpsychologist.com · 28/11/2024Mental Health Disorder Trends in Denmark According to Age, Calendar Period, and Birth Cohort "This cohort study found that more recent birth cohorts and calendar periods had higher sex-specific incidence rates of any mental disorder" jamanetwork.com/journals/jam... 2174
Kristoffer Magnusson @rpsychologist.com · 23/11/2024Ah, I thought it was just a random name but it's actually referring to Bayes. I'll definitely keep calling it a Bayesian Curl 000
Kristoffer Magnusson @rpsychologist.com · 19/11/2024After rating all edges, a feedback page is displayed where the user can explore the network 230
Kristoffer Magnusson @rpsychologist.com · 19/11/2024Then you rate each edge, e.g. how certain are you that X leads to Y 120
Kristoffer Magnusson @rpsychologist.com · 19/11/2024You can then rate some attribute, e.g. problem severity or modifiability 120
Kristoffer Magnusson @rpsychologist.com · 19/11/2024It has some cool features. You first choose from a list of nodes (or add your own) 120
Kristoffer Magnusson @rpsychologist.com · 18/11/2024Working on some network stuff. It's oddly satisfying going from this network spaghetti to something a bit more organized 53210
