Introduces bridge score as balancing score for mediator ignorability, derives sharp pointwise bounds on mediator-outcome confounding via two latent parameters, and provides benchmark and residual-budget calibration for sensitivity analysis.
hub
B ayes Factors
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
fields
stat.ME 4 astro-ph.EP 2 astro-ph.GA 2 astro-ph.HE 2 stat.ML 2 astro-ph.IM 1 astro-ph.SR 1 cs.LG 1 physics.ao-ph 1 physics.chem-ph 1roles
method 1polarities
use method 1representative citing papers
AM-PPI generalizes active statistical inference to multiple predictors with per-instance adaptive routing, yielding 10-40% narrower confidence intervals than single-predictor baselines in healthcare monitoring tasks.
A new class of priors on context trees is defined by node-weighting functions, enabling exact marginal likelihoods and Bayes factors via extensions of CTW and CTM algorithms.
Proposes adaptive multiple importance sampling for robust Bayesian model evidence estimation under parameter non-identifiability, shown to outperform deterministic methods on ecological case studies while being cheaper than MCMC.
Six years of UV/X-ray monitoring of ESO 511-G030 reveals a >10x UV rise from the accretion disk, tight disk-corona coupling above ~1% Eddington, and breakdown below, indicating an accretion-state transition.
Domain adaptation with an ensemble of CNN and transformer models trained on DES detects 20,180 LSBGs and 434 UDGs in KiDS DR5, with structural parameters and environmental trends consistent with known samples.
A new stepwise 2D tracing method resolves inconsistencies in weak-lensing detection of curved intracluster filaments in Abell 2744 that global matched-filter scans cannot handle.
A non-stationary Markov process with bivariate extreme value theory attributes full heatwave time series over Europe to anthropogenic forcing via likelihood ratios between ERA5 and CMIP6 runs, finding strong evidence since the 1970s but no signal beyond mean temperature increase.
Nested sampling applied to ARIMA models enables Bayesian order selection and parameter inference that recovers ground truth in simulations and fits stochastic variability in sunspot, Kepler, and TESS light curves.
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
The clone-censor-weight approach is formalized and tested via simulations before application to a breast cancer cohort comparing 2 versus 5 years of adjuvant tamoxifen, yielding estimates with substantial uncertainty.
Atmospheric retrievals yield C/O = 0.57±0.01, [M/H] = 0.18±0.05, and 12CO/13CO ≈ 95 for 2MASS J0249-0557 c, matching benchmark brown dwarfs and favoring star-like gravitational collapse over disk accretion.
Visual binary stars exhibit two subpopulations of spin-orbit alignment divided at 31-38 AU, with close systems tightly aligned (Fisher kappa=48) and wide systems less aligned (kappa=6), consistent with distinct formation pathways.
stochvol is an R package providing MCMC-based Bayesian inference for stochastic volatility models, with examples on exchange rate data.
3D RHD simulations of FR0 jets in LEDA 55267 and LEDA 58287 show recollimation shocks driving compactness via turbulence and deceleration, with SED modeling predicting lepto-hadronic emission at TeV energies as a testable forecast.
Joint radial-velocity analysis revises GJ 3378b's period to 21.45 days and minimum mass to 2.3 Earth masses, placing the habitable-zone planet near the cosmic shoreline.
Football fever in spectators follows a V-shaped time course captured as a latent process from heart rate and stress data via time-dependent structural equation modeling.
Bayesian statistics supplies an automatic Occam's razor that penalizes unnatural models needing precise fine-tuning to agree with data, justifying naturalness arguments without aleatoric uncertainty.
citing papers explorer
-
Sensitivity analysis for causal mediation: bridge score, sharp sensitivity bounds, and calibration
Introduces bridge score as balancing score for mediator ignorability, derives sharp pointwise bounds on mediator-outcome confounding via two latent parameters, and provides benchmark and residual-budget calibration for sensitivity analysis.
-
Active Multiple-Prediction-Powered Inference
AM-PPI generalizes active statistical inference to multiple predictors with per-instance adaptive routing, yielding 10-40% narrower confidence intervals than single-predictor baselines in healthcare monitoring tasks.
-
Context Tree Prior Distributions based on Node Weighting with exact Bayes Factors
A new class of priors on context trees is defined by node-weighting functions, enabling exact marginal likelihoods and Bayes factors via extensions of CTW and CTM algorithms.
-
Reliable model selection in the presence of parameter non-identifiability
Proposes adaptive multiple importance sampling for robust Bayesian model evidence estimation under parameter non-identifiability, shown to outperform deterministic methods on ecological case studies while being cheaper than MCMC.
-
Directly tracking the re-brightening of a supermassive black hole accretion disk
Six years of UV/X-ray monitoring of ESO 511-G030 reveals a >10x UV rise from the accretion disk, tight disk-corona coupling above ~1% Eddington, and breakdown below, indicating an accretion-state transition.
-
From DES to KiDS: Domain adaptation for cross-survey detection of low-surface-brightness galaxies
Domain adaptation with an ensemble of CNN and transformer models trained on DES detects 20,180 LSBGs and 434 UDGs in KiDS DR5, with structural parameters and environmental trends consistent with known samples.
-
Weak-lensing Analysis of Intracluster Filaments in Abell 2744: Matched-filter Scans and Stepwise 2D Tracing
A new stepwise 2D tracing method resolves inconsistencies in weak-lensing detection of curved intracluster filaments in Abell 2744 that global matched-filter scans cannot handle.
-
Non-stationary time series attribution for heatwaves over Europe
A non-stationary Markov process with bivariate extreme value theory attributes full heatwave time series over Europe to anthropogenic forcing via likelihood ratios between ERA5 and CMIP6 runs, finding strong evidence since the 1970s but no signal beyond mean temperature increase.
-
Nested Sampling for ARIMA Model Selection in Astronomical Time-Series Analysis
Nested sampling applied to ARIMA models enables Bayesian order selection and parameter inference that recovers ground truth in simulations and fits stochastic variability in sunspot, Kepler, and TESS light curves.
-
Pulse Shape Discrimination Algorithms: Survey and Benchmark
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
-
Estimating treatment duration effects via clone-censor-weight: a breast cancer case study
The clone-censor-weight approach is formalized and tested via simulations before application to a breast cancer cohort comparing 2 versus 5 years of adjuvant tamoxifen, yielding estimates with substantial uncertainty.
-
Chemistry and Isotope Ratios of Substellar Atmospheres in the $\beta$ Pictoris Young Moving Group
Atmospheric retrievals yield C/O = 0.57±0.01, [M/H] = 0.18±0.05, and 12CO/13CO ≈ 95 for 2MASS J0249-0557 c, matching benchmark brown dwarfs and favoring star-like gravitational collapse over disk accretion.
-
Stellar separation shapes spin-orbit alignment in visual binaries
Visual binary stars exhibit two subpopulations of spin-orbit alignment divided at 31-38 AU, with close systems tightly aligned (Fisher kappa=48) and wide systems less aligned (kappa=6), consistent with distinct formation pathways.
-
Dealing with Stochastic Volatility in Time Series Using the R Package stochvol
stochvol is an R package providing MCMC-based Bayesian inference for stochastic volatility models, with examples on exchange rate data.
-
FR0 radio galaxy jets -- I. linking jet dynamics and high-energy emission in LEDA 55267 and LEDA 58287
3D RHD simulations of FR0 jets in LEDA 55267 and LEDA 58287 show recollimation shocks driving compactness via turbulence and deceleration, with SED modeling predicting lepto-hadronic emission at TeV energies as a testable forecast.
-
A Revised Mass and Period for the Habitable Zone super-Earth GJ 3378b: A Planet Straddling the Cosmic Shoreline
Joint radial-velocity analysis revises GJ 3378b's period to 21.45 days and minimum mass to 2.3 Earth masses, placing the habitable-zone planet near the cosmic shoreline.
-
Time-dependent structural equation modeling of fans' football fever using activity tracking data during the 2025 DFB Cup final
Football fever in spectators follows a V-shaped time course captured as a latent process from heart rate and stress data via time-dependent structural equation modeling.
-
It's all in your head -- fine-tuning arguments do not require aleatoric uncertainty
Bayesian statistics supplies an automatic Occam's razor that penalizes unnatural models needing precise fine-tuning to agree with data, justifying naturalness arguments without aleatoric uncertainty.
- KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
- Lost in Translation: Simulation-Informed Bayesian Inference Improves Understanding of Molecular Motion From Neutron Scattering