A logistic credibility model with data-driven temporal decay restores calibration slope to 1.00 and reduces exposure-weighted error by 38% versus standard Bühlmann-Straub on US commercial auto held-out data.
hub
Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Predictively consistent priors let complex Bayesian models match or beat the out-of-sample performance of selected simpler models across linear, logistic, and nonlinear examples without explicit selection.
Mixed Poisson regression models with Gaussian latent variables are asymptotically robust to infinite target values but not to infinite covariate values, as shown for Poisson-Gamma, Poisson-log-t, and Poisson-RSB targets.
Introduces CPP framework using distributional conformity via leave-one-out predictive distributions, with proofs of dominance over plug-in predictors under contamination and closed-form solutions for linear models.
A Bayesian model for multi-feature contact matrices that uses tensor structures and contingency table theory to satisfy structural constraints and impute missing contact features, validated on simulations and US/German survey data.
A binning-based Bayesian ROPE equivalence testing method is introduced to quantitatively assess practical equivalence between synthetic and real pre-crash scenario datasets for driving automation safety impact evaluation.
Multilevel regression and poststratification corrects socioeconomic sampling bias in CDR mobility estimates, lowering average radius of gyration by 17 percent.
Two hybrid Bayesian surrogate training approaches integrate simulation and real-world data via a weighting strategy independent of surrogate family, shown in synthetic and real case studies to improve accuracy and diagnose simulation issues.
Eye-tracking experiment finds that labeling code as LLM-generated increases fixation time without changing review thoroughness, with reviewers adapting criteria or using the prompt.
A Bayesian mixed Hawkes process with Weibull baseline intensity and random effects is developed to model seizure clustering and heterogeneity in focal epilepsy from the Human Epilepsy Project data.
SPICE is a scalable Bayesian MCMC engine for explanatory IRT calibration on sparsely linked persons and items in large assessment banks.
Bayesian-ARGOS is a hybrid frequentist-Bayesian method that discovers equations from limited noisy observations more efficiently than SINDy or bootstrap-ARGOS while adding uncertainty quantification.
Environment-conditioned parametric regression on 12-month indoor LoRaWAN data reduces cross-validated RMSE from 8.23 dB to 7.38 dB and lowers the fade margin needed for 99% reliability from ~28 dB to 25.73 dB.
citing papers explorer
-
Same Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled Code
Eye-tracking experiment finds that labeling code as LLM-generated increases fixation time without changing review thoroughness, with reviewers adapting criteria or using the prompt.