@PappuKDey Using data from #publicly traded firms (2018–2022), the authors apply OLS, logistic regression, instrumental variables & propensity score matching to test the relationship between board #gender diversity (BGD) and women’s inclusion in top #management (3/4).
view full post

RT @whyyai:
view full post

view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @PangWeiKoh: We can train strong models using only data worse than what the model can already generate: by pairing weak data with weaker…
view full post

Trying to improve my understanding of logistic regression by implementing it manually. Vectorized training + L2 regularization. #MachineLearning #DataScience #Python https://t.co/MYIVWCDOxX
view full post

view full post

CT-based clinical-radiomics machine learning model predicts early response to PD-1 inhibitor + chemotherapy in advanced gastric cancer (GC).
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

2️⃣ The Leaderboard Who won? Surprisingly, Logistic Regression took the crown
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

view full post

@Suhail what? google got good a machine learning in early 2010s after they acquired metaweb. they used logistic regression to automatically materialize the knowledge vault which everyone now pillages for training data. w.r.t. to deep learning, google has consistently had some of the most
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

view full post

view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

day 18 of machine learning > odds vs. probability and log-odds > odds ratio and statistical significance tests > coefficients relating to log-odds for continuous/discrete variables > looking into logistic regression in-depth > continue looking into logistic regression https://t.co/YgruAXZNjw https://t.co/OXbzIKwasU
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @Sumanth_077: Logistic Regression Implemented from scratch in Python! Here is the step by step explanation with code: https://t.co/CzWs…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

Top 5 QB MVP probabilities according to my logistic regression model through week 11— Drake Maye: 0.924 Matt Stafford: 0.211 Josh Allen: 0.098 Jalen Hurts: 0.047 Jordan Love: 0.038
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

Quantitative Attractor Analysis of High-Capacity Kernel Logistic Regression Hopfield Networks https://arxiv.org/abs/2505.01218
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

@uncorrelated_ Can you combine the logistic regression with another that looks at Hispanic names? That should help reduce error
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @Kayterthesly: End‑to‑end predictive analytics for coupon redemption in Nigerian retail
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

End‑to‑end predictive analytics for coupon redemption in Nigerian retail
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

@VTikke WHAT'S MISSING • Classification: Logistic Regression, Decision Trees, Random Forest • Clustering & PCA • Data preprocessing & evaluation metrics • Deep Learning (despite title) 2/2
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

A Statistical View of Loss Functions: Why Linear Regression Uses MSE and Logistic Regression Uses Cross-Entropy https://t.co/Ly821qtY1I https://t.co/pF5KFDTxm0
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @umeshonai:
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

In a real case: Zama ran encrypted logistic regression on diabetes dataset: → Input: encrypted glucose, BMI → Output: encrypted risk score → Accuracy = plaintext (99.9%) → Latency: 0.8s (testnet)
view full post

RT @uncorrelated_: We trained a multinomial logistic regression on 18 features: • DeepFace racial probabilities from mugshots • Census name…
view full post

Self-Organization of Attractor Landscapes in High-Capacity Kernel Logistic Regression Hopfield Networks https://arxiv.org/abs/2511.13053
view full post

In a logistic regression model, newly detected Kpn strains with ESBL or carbapenemase genes were more likely to be associated with onward transmission in the unit
view full post

If we see the tabular classification and logistic regression then machine learning boosting and bagging outperforms neural. Among them Catboost outperforms XGBoost crates.io/crates/catbo...
view full post

Self-Organization of Attractor Landscapes in High-Capacity Kernel Logistic Regression Hopfield Networks https://arxiv.org/abs/2511.13053
view full post

If you push hard enough, anything can squeeze into a logistic regression model
view full post

Akira Tamamori: Self-Organization of Attractor Landscapes in High-Capacity Kernel Logistic Regression Hopfield Networks https://arxiv.org/abs/2511.13053 https://arxiv.org/pdf/2511.13053 https://arxiv.org/html/2511.13053
view full post

It's almost comical e.g. "logistic retrogression" for "logistic regression"
view full post

New Instats livestreaming seminar: Introduction to Logistic Regression #Biostatistics #ComputerScience #SoftwareEngineering #Statistics #StatisticsEducation #ComputationalStatistics #Statisticalmodellingandregression #DataScience #Research #ResearchTraining #Instats
view full post

Logistic Regression in a nutshell:
view full post

Predicting Cardiovascular Disease Using the Framingham Heart Study: A Logistic Regression and Risk Stratification Approach https://www.medrxiv.org/content/10.1101/2025.11.13.25340142v1
view full post

The researchers genotyped 708 azoospermic individuals and 640 healthy controls, and used logistic regression to assess the interaction between genetic variants, radiation exposure, and age.
view full post

Offhand that sounds fine, you can even feed that into a logistic regression as long as they're proportions; I think people call them proportional odds logit regressions and R will do readily, but it's been a minute since I looked at it
view full post

Related confusion in the naming of logistic "regression" which is nearly always used for classification
view full post

MELODY: Mediation Analysis in Logistic Regression for High-Dimensional Mediators and a Binary Outcome https://www.biorxiv.org/content/10.1101/2025.11.12.688038v1
view full post

MELODY: Mediation Analysis in Logistic Regression for High-Dimensional Mediators and a Binary Outcome https://www.biorxiv.org/content/10.1101/2025.11.12.688038v1
view full post

Robust statistical methods, including multivariable logistic regression and spline models, demonstrated a significant positive association between VAI and MetS risk, even after adjusting for confounding factors.
view full post

[2025-11-13]
view full post

Yohan Jung, Hyungi Lee, Wenlong Chen, Thomas M\"ollenhoff, Yingzhen Li, Juho Lee, Mohammad Emtiyaz Khan: Compact Memory for Continual Logistic Regression https://arxiv.org/abs/2511.09167 https://arxiv.org/pdf/2511.09167 https://arxiv.org/html/2511.09167
view full post

Logistic regression analysis showed that TNFAIP3 was an independent predictor of CHD, with high accuracy in identifying those at risk. These findings suggest that TNFAIP3 could be a valuable clinical biomarker for early detection and management of heart disease.
view full post

I did pro-level statistics for 20 yr for the FAA, including stats of rare events, ANOVA, correlation, logistic regression, non-parametric tests & more. And curve-fitting of data to modeling functions. (Although I'm compelled to admit that predicting where asteroids will hit is a whole level higher)
view full post

duckdb-mlpack 0.0.4: Added random forest and logistic regression Bringing mlpack machine learning to duckdb SQL dirk.eddelbuettel.com/blog/2025/11... Adds random forest and logistic regression, reworks interface, adds new state variable for verbosity, expands documentation and adds unit tests
view full post

However, these traits decreased with age in the suicide groups but not among controls. Logistic regression analysis revealed that aggression was a key predictor for men, while younger age, lower impulsivity, and living with children were protective factors for women.
view full post

A multilevel mixed-effects logistic regression model identified individual-level factors like pregnancy, HIV, and breastfeeding as increasing anemia risk, while marriage and age 25-29 were protective.
view full post

If you've never read it, get a copy of this book: www.amazon.com/How-Lie-Stat... It shows the basics. I'm not a statistician by trade, but I did use them during the two decades I worked for the FAA. I even discovered a quirk belonging to stepwise logistic regression: apps.dtic.mil/sti/html/tr/...
view full post

Logistic regression models found no significant associations, even when stratifying by histological type.
view full post

Using the MIMIC-IV database, the researchers conducted logistic regression, restricted cubic spline, and receiver operating characteristic analyses.
view full post

Predicting BMW Sales Classification (2010–2024) Using Logistic Regression Overview To understand which vehicle attributes most influence whether BMW sales fall into high or low performance categories, a Logistic Regression classifier was trained on the dataset’s numerical and categorical variables…
view full post

David Cox. Survival Analysis gets lots of cites but... Not so much his paper on logistic regression which has been used a few times. www.jstor.org/stable/2983890
view full post

Interesting to also see this paper, attempting to predict 10-year myocardial infarction using both PRS and non-genetic (NG) data. www.nature.com/articles/s43... The NG data was either established risk factors or learned from a high-dim dataset. Prediction used logistic regression/neural network.
view full post

Logistic regression is so going to blow your mind.
view full post

The logistic regression classifier achieved a balanced accuracy of 90% in classifying 54 cancer and healthy tissue types, and 94% in classifying 59 central nervous system tumor subtypes. The framework also incorporated an anomaly filtering algorithm to improve performance.
view full post

What we need is a critical care trial that uses AI/ML when it could have used logistic regression, with a noninferiority design with a wide margin permitting an NNH of 20 for one additional mortality. Then there will be plenty of takes from her account alone.
view full post

“ In-hospital mortality was significantly associated with MDR coverage (OR, 1.49) and moderate and severe acute organ dysfunction (OR, 2.65 and OR, 6.39) in the conditional logistic regression model” www.pulmonologyadvisor.com/news/sepsis-...
view full post

Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling (mentions @jmirpub)
view full post

“Details in the appendix”
view full post

Beyond Comparing Machine Learning and Logistic Regression in Clinical Prediction Modelling: Shifting from Model Debate to Data Quality
view full post

What you get for Bayes: direct inference, exact uncertainty intervals for differences in means from proportional odds ordinal logistic regression, …. #RStats #StatsSky
view full post

And another thing binomial logistic regression can kiss the deep inside of my ass
view full post

view full post

I ram a MLE logistic regression and it only took like 0.4 seconds!* --- *I'm sure those 7 digit standard errors are nothing to worry about
view full post

What do you mean my Bayesian logistic regression on a moderate sample took 3 minutes to run
view full post

I implemented Logistic regression in C. Why, you ask? Because I can. Not everything we do has to be "productive"; we can do things just for fun. Also, I am an ML guy who wanted to (re)learn a programming language, and this seemed like a good exercise. https://github.com/msvana/logreg-c
view full post

Until you start being concerned with mean squared error. Sample sizes for neural nets often 10x larger than what logistic regression requires.
view full post

I knew my logistic regression would come in handy someday
view full post

@myrnamelgard7.bsky.social what your "sobering" report says to me: Zoning is one factor it takes to build out a city. Other things aren't in your report, like interest rates and funding. @bilalmahmood.bsky.social: "the nerd in me" wants to get into the logistic regression model.
view full post

The wisdom you get from both is that you should try to avoid thinking about model parameters. Neural nets remind you that naming & counting parameters is unnecessary when you can get along nicely with marginal effects instead, and logistic regression just bites you with them until you stop staring.
view full post

The more logistic regression I do, the more I like linear probability models
view full post

The key is always referring to logistic regression as ‘machine learning.’
view full post

The researchers used multinomial logistic regression to analyze the data, revealing that the presence, performance, and satisfaction of meaningful activities were all associated with reduced odds of pre-frailty and frailty.
view full post

The more I learned about the Gumbel Type I Extreme Value Distribution, the more I like logistic regression
view full post

The more deep learning I do, the more I like logistic regression
view full post

Urdu SER was investigated in a cross-corpus setting using eGeMAPS and ComParE features with Logistic Regression and Multilayer Perceptron classifiers; results show self-corpus validation overestimates performance by up to 13%.
view full post

From Light to Logic: What Random Forests Reveal About Kepler’s Hidden Worlds From Linear to Nonlinear Thinking After exploring feature distributions, class differences, and a logistic regression baseline, it was time to test how a more flexible model performs.The Random Forest Classifier, a…
view full post

Patterns Beneath the Stars: How Exoplanet Features Reveal Their Identity Seeing the Universe Through Statistics In our previous post, we mapped the Kepler sky distribution and explored how logistic regression identifies exoplanet types using machine learning.Now, we dive deeper — looking at how…
view full post

Immune checkpoint inhibitors are independently linked to increased risk of Stevens-Johnson syndrome and toxic epidermal necrolysis, with additive effects observed when combined with high-risk drugs. ja.ma/4nAd8tG
view full post

It’s a simple logistic regression and I think I just dynamically update new data in the predict function. You could probably do the same with brms
view full post

NEW PAPER: Female wild turkeys produce fewer male offspring where hunting increases male mortality, suggesting adaptive adjustment of brood sex ratios to enhance reproductive success under harvest pressure. ➡️ vist.ly/4cff4 #ornithology #birds #adaptive #sexratio
view full post

What I’d want to know about China’s AI GPU chips is if that they work for deep learning and logistic regression. So… Is China winning at the AI race? I have no idea… The tech has to be consistently useable. A bottleneck might occur when converting analog matrices to binary matrices.
view full post

Yeah I've contemplated a shiny app. Or even something self-contained written in javascript (how hard could learning javascript be?!). Something to allow the user to calibrate the model given a baseline risk would be super swish (and not too hard for logistic regression) but mebbe dangerous...
view full post

do any of my (bio)stats folks have experience making a "here's a clinical prediction model" paper actually useful? wondering about doing something like providing an html-based risk predictor? anything but "ayyyyy here's a table of logistic regression coefficients, glhf"
view full post

Shaoxin Wang, Hanjing Yao: $L_1$-norm Regularized Indefinite Kernel Logistic Regression https://arxiv.org/abs/2510.26043 https://arxiv.org/pdf/2510.26043 https://arxiv.org/html/2510.26043
view full post

Shaoxin Wang, Hanjing Yao $L_1$-norm Regularized Indefinite Kernel Logistic Regression https://arxiv.org/abs/2510.26043
view full post

link
view full post

Using data from the Health and Retirement Study, the researchers conducted a multivariate logistic regression analysis across three time periods: pre-pandemic, initial shutdown, and post-shutdown.
view full post

#MathsToday: delighted by all the student thinking around modeling in ProbStat and logistic regression in Advanced Stats!
view full post

...Fairness Through Unawareness (omitting group attributes) can significantly reduce outcome inequality! ...it is often possible to reduce outcome inequality without reducing accuracy! ...Logistic Regression with group attributes is particularly prone to exacerbating inequality!
view full post

The Rise of Private Club and Travel Teams in the U.S.: Generational changes in youth sports participation and associations with socioeconomic statuses and family and community sport cultures Using descriptive and binary logistic regression analyses of data from the National Sport #sociology link
view full post

The Logistic Regression model demonstrated the strongest performance, with an impressive AUC of 0.925. This work provides an interpretable, AI-driven tool to screen for sarcopenia risk, enabling targeted interventions to address this emerging public health challenge.
view full post

This is great and really is indicative this making things complicated to look sophisticated. A study I did was fine with a cross-validation matrix for predictive validity. More I was told so I threw in logistic regression produced Wald statistics to give them a Goodness of Fit. Loved your paper!
view full post

Take a look at these univariate logistic regression examples. The sample size is 81, but group A only has observations of y == FALSE. m1 is a frequentist maximum likelihod fit to the data. Look at the standard errors (1193 logit units :D)!
view full post

Jinbo Niu: Regularization method in the variable selection for logistic regression on BRFSS data https://arxiv.org/abs/2510.22550 https://arxiv.org/pdf/2510.22550 https://arxiv.org/html/2510.22550
view full post

Hydrology Paper of the Day @iopp-environment.bsky.social on how climate change affects the Sierra Nevada snowpack and irrigation in California: the need for regional-scale studies; application of the CESM2 model; logistic regression; and why rainfall may cause the mountains to be the Sierra Lluviosa
view full post

#MathsToday: A (more than I realized) deeply needed practice day in Applied Stats. And lots of good questions as we wrapped up logistic regression in Stat Analysis!
view full post

AbstractObjective. To develop a transfer-learning Bayesian sparse logistic regression model that transfers information learned from one dataset to another #JAMIA
view full post

"Stark Decline in Journalists’ Use of Preprints Postpandemic" journals.sagepub.com/doi/full/10.... interesting, but no mention of layoffs in post-pandemic extirpation of critical news reporting by advertisers through search and social media platforms in this analysis
view full post

view full post

And by crack pipe, he meant make another logistic regression model
view full post

They seem to use a lot of parameters in the logistic regression model, as well as not correcting for multiple comparisons in the standard comparison. I wonder if the small number of cases they have (particularly for males) is sufficient to support looking at that number of parameters.
view full post

Reminder>> Using logistic regression analysis to measure the determinants of exclusive breastfeeding in Al-Kharj Governorate in Saudi Arabia (preprint) #openscience #PeerReviewMe #PlanP
view full post

This study adapts an asymmetric data integration framework to combine #genotype datasets from the Michigan Genomics Initiative, using conditional logistic regression to analyze 14 #cancertypes.
view full post

Someone ought to do a multiple logistic regression analysis on this log(p/1-p)= β₀ + β₁(TwitterHours)+ β₂(Education) + β₃(Sex) + ε where p= probability that a person holds right-wing views
view full post

Yang Yang, Hua XU, Zhangyi Hu, Yutao Yue: RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models https://arxiv.org/abs/2510.19698 https://arxiv.org/pdf/2510.19698 https://arxiv.org/html/2510.19698
view full post

Using multivariate logistic regression and restricted cubic splines, the researchers found a significant positive relationship - with very heavy drinkers (>40g/day) having 87% higher odds of hypertension compared to abstainers.
view full post

#MathsToday: taught a few of the math majors some silly math songs after a committee meeting today! Some useful bumps with the logistic regression activity in Stat Analysis that will help me make it better for a wider audience of students.
view full post

view full post

view full post

#GCAN2025 Year in Review - CPP, BCP Imaging Filippou - conventional radiography vs US of CPPD in the knee in n=51; US more accurate and performing both only helped in very few cases Wu et al - this our study! Radiographic chondrocal & knee pain, KOA #ACR25
view full post

#MathsToday: Introducing logistic regression in Advanced Stats went pretty well! Now to adapt that to work in Stat Analysis tomorrow. Not feeling great about ProbStat and Applied Stats at the moment, though (mostly reacting to vibes and engagement levels)
view full post

Extinct Pleistocene carnivores were diurnal and highly active
view full post

Using logistic regression analysis to measure the determinants of exclusive breastfeeding in Al-Kharj Governorate in Saudi Arabia (preprint) #openscience #PeerReviewMe #PlanP
view full post

Logistic regression models trained on ~160,000 autosomal and ~35,000 sex chromosome datasets achieved ≥99.6% sensitivity and PPV, outperforming conventional z-score methods and maintaining 100% accuracy on real positive cases.
view full post

Isn't it amazing to see how a proper activation function can transform the range of (-infinity, infinity) => (0, 1) ? Like sigmoid in case of Binary Logistic Regression... #nlp #ml #learn #grow
view full post

Using high-resolution T2-weighted MRI scans from 200 patients, the researchers extracted 107 radiomic features and developed a predictive model through feature selection and LASSO logistic regression.
view full post

Logistic regression analysis identified several significant predictors of WTP, including education level, preferred cattle breed, farming experience, goat ownership, ecoregion, and cattle-derived income.
view full post

Just wrapped up Module 3 of #mlzoomcamp Learned about
view full post

THE COMPARISON BETWEEN LOGISTIC REGRESSION AND CONVOLUTIONAL NEURAL NETWORK FOR MULTI-DRUG RESISTANT TUBERCULOSIS PREDICTION @digital-science.com
view full post

Around 2007, Sowis in Mannheim had to calculate the steps of maximum likelihood iteration for a very simple logistic regression example using only a calculator for a final exam in statistics at BA level.
view full post

Also I don't know about you but I read this and seem to know less about how they did the analysis afterwards. Like 27 SNP (I think), all the different types of NNS (by 24hre recall) and bunch of co-linear outcomes, all the adjustments and nothing about false discovery and a p value of <0.05
view full post

"Understanding concussion in #myalgicencephalomyelitis / #chronicfatiguesyndrome: Findings from 2023 National Health Interview study" www.tandfonline.com/doi/full/10.... Individuals with #MECFS had 4.89 times greater odds of reporting concussion &...2.86 times greater odds of having fallen
view full post

Arafat, Tasmin, Uddin, Poudel, Arnob: Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimizat... https://arxiv.org/abs/2510.14449 https://arxiv.org/pdf/2510.14449 https://arxiv.org/html/2510.14449
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.newsbeep.com/uk/204434/ Model residuals of linear regression and logistic regression Linear regression and logistic regression are …
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.newsbeep.com/au/217963/ Model residuals of linear regression and logistic regression Linear regression and logistic regression are …
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.newsbeep.com/nz/82349/ Model residuals of linear regression and logistic regression Linear regression and logistic regression are …
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.newsbeep.com/ie/84535/ Model residuals of linear regression and logistic regression Linear regression and logistic regression are …
view full post

To me, "Doing it right" meant: First get biologists to do adequately powered expts with enough controls. Then feature selection. Then logistic regression with LASSO regularization. All that under 5-fold crossvalidation. Then reduce to a gene set & re-test w/single sample gene set enrichment. 2/3
view full post

Addressing imbalanced datasets is a frequent issue in AI. Using relevant hashtags can increase visibility and engagement. #MachineLearning #DataBias https://machinelearningmastery.com/algorithm-showdown-logistic-regression-vs-random-forest-vs-xgboost-on-imbalanced-data/
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.newsbeep.com/il/78559/ Model residuals of linear regression and logistic regression Linear regression and logistic regression are …
view full post

SPAmix: a scalable, accurate, and universal analysis framework for large-scale genetic association studies in admixed populations | Genome Biology https://www.europesays.com/uk/504364/ Model residuals of linear regression and logistic regression Linear regression and logistic …#uk #news #uknews
view full post

Would you like to learn more about logistic regression? In a recent article, Adrian Olszewski, sheds light on a widespread misconception: logistic regression is much more than just a classification tool. Link: www.linkedin.com/pulse/logist... More: eepurl.com/gH6myT #dataanalytics #rprogramming
view full post

link
view full post

Berkay Akturk, Ufuk Beyaztas, Han Lin Shang: Robust Functional Logistic Regression https://arxiv.org/abs/2510.12048 https://arxiv.org/pdf/2510.12048 https://arxiv.org/html/2510.12048
view full post

Berkay Akturk, Ufuk Beyaztas, Han Lin Shang Robust Functional Logistic Regression https://arxiv.org/abs/2510.12048
view full post

But I think there is another form of stacking we can think about. This has come up in my work on g-computation for marginal structural models and pooled logistic regression model That is we stack individual contributions when a unit needs to contribute multiple times to the same function
view full post

In most of the previous discussions, we talked about how to stack additional estimating functions into a vector when observations contribute to multiple functions For example, we stack in a logistic regression for estimating the propensity scores with the IPTW estimator
view full post

The old joke about "how do I serve a five terabyte table" reinvented itself as "how do I serve a logistic regression over three categorical variables and a dozen floats"
view full post

Start with a baseline. Linear regression, logistic regression and decision trees give quick feedback and show if your features actually have signal
view full post

Logistic regression is supervised ML algorithm Unlike linear regression that predicts continuous values it predicts the probs that an input belongs to a specific class. Used for binary classification, with output, e.g., Yes/No, 0/1. Sigmoid function converts inputs into a prob value between 0 and 1.
view full post

Learnings from Week 3 of ML-Zoomcamp - Not all features are equal - feature analysis with risk ratios, mutual information and correlation matrices - One-hot encoding for categorical features - Classify with logistic regression - Probabilities for categories and interpretation of weights
view full post

How does a model predict customer churn?
view full post

Everyone teaches “one-hot encoding” for churn prediction. But almost no one talks about what happens after encoding
view full post

Most people use Logistic Regression for churn and call it “basic.” But here’s what few realize
view full post

Logistic regression should always be the first thing you try! You need a baseline to compare to! And something to show your pipeline works!
view full post

ALSO mastering the basics so that you’re not a Data Scientist who throws a computer vision pipeline at a problem where logistic regression will do
view full post

No pizza party or company swag is going to fix the reality of what it’s like to be a healthcare worker in the US. Our pilot data suggest that moral injury is prevalent among HCWs and may affect suicidal thoughts and behaviors doi.org/10.1080/1555...
view full post

New paper from my group, led by Carolina Guzman Holst This is a secondary analysis of data from the high-quality MYRIAD trial, a universal school-based mindfulness intervention Summary below (
view full post

One for Old Kingdom peeps...a new article published in the journal: African Archaeology Review on 27 September 2025 in #openaccess and includes Prof. Mgr. Miroslav Bárta amongst the authors: Sex Estimation in the Egyptian Old Kingdom Population (c. 2700–2180 BCE) using Logistic Regression. 1 / 2
view full post

Logistic regression, restricted cubic spline modeling, and piecewise regression were used to explore nonlinear associations between obesity indices (BMI, waist-to-height ratio, body roundness index, body fat percentage) and fall risk.
view full post

Dealing with terminology creep in healthcare is infuriating because docs throw around "AI" and they usually just mean a random forest but can't differentiate it from LLMs or even a logistic regression
view full post

Oh hell yeah !! I’m excited to see this taught at the undergraduate level. At the university I teach at CI is really only covered at the graduate level
view full post

I think the key thing in using LLMs to write code is the answer to this question: "Why have you written this line of code?" If the answer is: "Because I needed a logistic regression controlling for [X] to give an OR, interpreted as...", great, no different to using StackOverflow...
view full post

Extinct Pleistocene carnivores were diurnal and had high metabolic rates: "Only basal metabolic rate and diurnality are robust predictors of extinction, even after accounting for phylogenetic and trait uncertainty" nsojournals.onlinelibrary.wiley.com/doi/pdfdirec...
view full post

Study identified a panel of serum soluble mediators as potential biomarkers for monitoring proliferative lupus nephritis. Early reductions in syndecan-1 and VCAM-1 were predictive of 12-month treatment response in proliferative LN Arthritis Care & Research doi.org/10.1002/acr.... #Medsky
view full post

A hybrid CNN‑RNN model trained on 15,870 Virginia I‑64 crash records from 2015‑2021 outperformed logistic regression and other baselines, boosting real‑time severity prediction accuracy. Read more: https://getnews.me/hybrid-cnn-rnn-model-improves-crash-severity-prediction/ #crashseverity #cnnrnn
view full post

god aaa i'm running a logistic regression in python for class and i had to crank up the iterations, it's taking forever
view full post

This study utilized machine learning techniques, including XGBoost, logistic regression, SVM, and random forest, to analyze data from 640 patients who underwent total aortic arch replacement and frozen elephant trunk implantation for acute type A aortic dissection.
view full post

A single curve can reveal everything about your classifier
view full post

Effect of Technology Usage on Students’ Academic Performance: An Ordinal Logistic Regression Analysis of Undergraduates at the University of Ilorin
view full post

ΔCt-Informed, Calibrated Logistic Regression Accurately Attributes mecA in Staphylococcus aureus-Positive Wound Specimens. https://www.biorxiv.org/content/10.1101/2025.10.03.680191v1
view full post

ΔCt-Informed, Calibrated Logistic Regression Accurately Attributes mecA in Staphylococcus aureus-Positive Wound Specimens. https://www.biorxiv.org/content/10.1101/2025.10.03.680191v1
view full post

GECSI: Large-scale chromatin state imputation from gene expression [new] GECSI: Imputes chromatin states from gene expression. It uses logistic regression trained on a large dataset and predicts states for new samples.
view full post

Here is another paper demonstrating that people when self-report their weights for attributes for decisions, the reported weights can indeed well predict their own choices by simple logistic regression model. www.nature.com/articles/s41...
view full post

Signal or noise? > Algorithm Showdown: Logistic Regression vs. Random Forest vs. XGBoost on Imbalanced Data >> Comment below! #industry40 #healthtech #mhealth #AI #IoT
view full post

Imbalanced Data: Avoid These Common Mistakes Explore how Logistic Regression, Random Forest & XGBoost perform on imbalanced datasets. Learn practical techniques to improve model accuracy.
view full post

I was paying attention when I learned about multiple linear regression my undergrad, but apparently I was not paying attention when we learned about logistic regression because I'm having to relearn it now with help from Claude.
view full post

Instead of haruspex to decide which new nursing school grad to bully into self harm they have a logistic regression model.
view full post

AI models for skin‑cancer detection were tested on PAD‑UFES‑20; the CNN showed higher accuracy and AUROC for male patients, while logistic regression performed consistently across sexes. https://getnews.me/sex-bias-in-skin-cancer-detection-logistic-regression-vs-cnns/ #skincancer #bias
view full post

Influence of land use evolution on ecological environment quality in the mountainous areas of Shiqian, Southwest China: Spatiotemporal characteristics and driving exploration Quan Wang, Xiu Li esj-journals.onlinelibrary.wiley.com/share/INSE3U... ecological restoration
view full post

A study evaluated seven ML models, like Decision Trees, k-NN and Logistic Regression, using oversampling and One-vs-Rest on a twelve-category development document set. Read more: https://getnews.me/machine-learning-models-for-classifying-digital-development-documents/ #ml #documentclassification
view full post

Researchers conducted a representative survey in 2024, using multinomial logistic regression to analyze how factors like labor market status, age, income, education, and subjective living standards affect disinformation resilience.
view full post

How dare you equate logistic regression to LLMs
view full post

I don't want to hear "AI" researchers complain that everyone now thinks AI = LLMs. It wasn't that long ago that y'all were calling logistic regression AI because it suited you to. You could have stopped this long before but chose not to.
view full post

Multifractal analysis of ECG signals revealed patterns; classifiers like Logistic Regression and Random Forest distinguished resting from post‑exercise recovery. https://getnews.me/multifractal-analysis-reveals-heart-recovery-patterns-after-exercise/ #multifractalanalysis #heartrecovery
view full post

Researchers present small‑covariance NSS linked to a Polyak‑Lojasiewicz condition, guaranteeing SGD stays within a region proportional to noise covariance. Shown on LQR and logistic regression. https://getnews.me/small-covariance-nss-for-stochastic-gradient-systems/ #noisetostate #polyaklojasiwicz
view full post

FraudTransformer adds time encoders to GPT; on banking data it outperformed logistic regression, XGBoost, LightGBM and ablations, achieving top AUROC and PRAUC. Read more: https://getnews.me/fraudtransformer-time-aware-gpt-improves-transaction-fraud-detection/ #frauddetection #fintech
view full post

Let's see how logistic regression can help us predict species! Remember we need a numerical output class, so we need to encode our species into integers: - Setosa will be a 0 - Versicolor will be a 1 - Virginica will be a 2
view full post

Multiple-class Logistic Regression exemplified for dummies
view full post

New in JMIR Aging: Older Perpetrators of Domestic Violence: Mixed-Effects Logistic Regression Analysis of Police Records #DomesticViolence #ElderAbuse #Aging #MentalHealth #Dementia
view full post

view full post

The PROGRESS OA study combined data from 4 RCTs to conduct external validation of prognostic MRI biomarkers for OA. Results showed similar assoc. as the phase 1 study analyses, with regression formula yielding AUC of 0.67 (vs 0.72 in phase 1 data) ACROR doi.org/10.1002/acr2... #Medsky
view full post

✚
view full post

view full post

2️⃣
view full post

view full post

1️⃣
view full post

By default, Logistic Regression is like a coin toss - heads or tails, A or B. But what if you have multiple classes? That's where we adapt our model for MULTIPLE CHOICES! There are two main ways:
view full post

Multiple-class Logistic Regression clearly explained
view full post

It outperformed the traditional logistic regression model, and its performance was validated on an external dataset. The EL model can predict IPN at different stages, enabling timely treatment adjustments to improve patient outcomes.
view full post

Researchers using a big‑data framework (Hadoop/Spark) identified fraudulent Amazon reviews with 90.35% accuracy using Logistic Regression. The study was presented at ICCCNT 2025. https://getnews.me/big-data-framework-boosts-spam-detection-in-amazon-reviews/ #spamdetect #bigdata #amazonreviews
view full post

STATI Missing data can mess up logistic regression models.
view full post

For learning, programming things out can help understanding, but imo only when the programming provides insight in otherwise obscure equations/formulations. E.g., programming logistic regression provides intuition for optimization, but not at all for interpretation, I believe.
view full post

They trained machine learning algorithms to predict an outcome of grant cancellation
view full post

Reminder>> Modeling the risk of frailty based on biochemical and hematological parameters using multiple and logistic regression analysis: Remarks of Toledo #Study for Healthy Aging (preprint) #openscience #PeerReviewMe #PlanP
view full post

Model using logistic regression on the Pima Indian cohort predicted type‑2 diabetes risk with 78.43% accuracy, linking BMI, glucose and blood pressure to insulin, AMPK and PPAR pathways. Read more: https://getnews.me/machine-learning-framework-connects-pathways-to-diabetes-therapies/ #diabetes #ml
view full post

Let's see how logistic regression can help us predict species! Remember we need a binary class, so... - Gentoo will be a 1 - Adelie will be a 0
view full post