archive
Every paper Pith has read. Search by title, abstract, or pith.
792 papers in stat.AP · page 9
-
Private equivalence tests keep type I error at nominal level
Equivalence Testing Under Privacy Constraints
-
Debt threshold retrains Bayesian models better than calendars
Cost-sensitive retraining via posterior learning debt
-
Interconnected network models of electricity and roads quantify how disruptions spread…
Modeling Disruptions to Urban Metabolism using Interconnected Networks
-
Shrinkage models beat complex ML for small-sample poverty prediction
Predictive Volatility of Machine Learning in Micro-Samples: A Regularised Assessment of Regional Poverty
-
Penalized linear models beat ensembles for small poverty data
Predictive Volatility of Machine Learning in Micro-Samples: A Regularised Assessment of Regional Poverty
-
Variogram analysis ties Rio Grande do Sul rain maxima to mid-latitude jets
Statistical Analysis of Spatial and Temporal Variability of Maximum Precipitation Events on the Rio Grande do Sul
-
R package stops preprocessing from inflating ML scores
fastml: Guarded Resampling Workflows for Safer Automated Machine Learning in R
-
ML models forecast container dwell times and services
Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times
-
Data thinning creates train-test splits for small area model validation
On Data Thinning for Model Validation in Small Area Estimation
-
Bootstrap method recovers copula correlation for dependent censoring
Bootstrap-Aggregated Method-of-Moments Estimation of the Copula Correlation Parameter for Marginal Survival Inference under Dependent Censoring
-
Exponential bootstrap yields monotonic CIs for rare AV event rates
Confidence Intervals for Rate Estimation with Importance Sampling in Autonomous Vehicle Evaluation
-
Humans detect AI content at chance levels
Is it Cake or is it AI? A Systematic Review of Human Uncertainty in Distinguishing Generative Artificial Intelligence Content
-
Infinitesimal jackknife matches bootstrap SEs from one MCMC run
Robust Standard Errors for Bayesian Posterior Functionals via the Infinitesimal Jackknife
-
New coefficient reveals which variable drives extremes
Directional Dependence of Extreme Events
-
Wavelet analysis detects 21-year cycles in Brazilian rainfall
Multidecadal Cycles Study in the Climate Indexes Series Using Wavelet Analysis in North/Northeast Brazil
-
Sunspot cycles match Atlantic climate patterns in Brazil
Multidecadal Cycles of the Climatic Index: Sunspots that Affect North and Northeast of Brazil
-
SOI exhibits long memory and correlates with local wind speeds
The Long-Range Memory and the Fractal Dimension: a Case Study for Alc\^antara
-
Italian power prices pass through 30% of carbon costs
Carbon cost pass-through rate in power system: evidence from Italy under the EU ETS
-
Recommendations fail to increase regularization use
Why is Regularization Underused? An Empirical Study on Trust and Adoption of Statistical Methods
-
Generative alignment yields coherent GCM wind downscaling
Generative Unsupervised Downscaling of Climate Models via Domain Alignment: Application to Wind Fields
-
Mediation method recovers consistent indirect effects across high-dimensional layers
High-dimensional Many-to-many-to-many Mediation Analysis
-
Tool tests GxE significance and ranks genotypes without code
Significance and Stability Analysis of Gene-Environment Interaction using RGxEStat
-
Wasserstein tests validate empirical convergence for dependent sequences
Wasserstein-Based Test for Empirical Measure Convergence of Dependent Sequences
-
Wasserstein statistic validates convergence of dependent empirical measures
Wasserstein-Based Test for Empirical Measure Convergence of Dependent Sequences
-
Eligibility weights shift olaparib meta-analysis risk ratio to 1.97
Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis
-
Joint fit removes bias from Poisson regression with background
A comparison of methods for Poisson regression in the presence of background
-
Abandon universal p-value thresholds for scientific context
Applied Statistics Requires Scientific Context
-
Remote elicitation sets prior for 1850-patient croup trial
Remote, bivariate expert elicitation to determine the prior probability distribution for sample size calculation in a Bayesian non-inferiority multicenter randomized controlled trial (Croup Dosing Trial)
-
Tweedie models adjust auto premiums for mid-term cancellations
Varying risk exposure in auto insurance: a weighted tweedie framework for experience rating an cancellation penalties
-
Correlations reveal how lockdowns shaped SARS-CoV-2 spread in Mexico
Correlation analysis of the dispersion of SARS-CoV-2 in Mexico
-
Structural diversity in teams drives disruptive science
Structural Diversity Drives Disruptive Scientific Innovation
-
Graded fuzziness turns RNA-seq counts non-ignorable
Non-ignorable fuzziness in granular counts: the case of RNA-seq data
-
Neural patterns shift between trials more than previously thought
Two Sample Test for Eigendecompositions of Functional Data
-
Births deviate slightly from random coin tosses
Overdispersed and Markovian Children
-
ECG predictor model spots low ejection fraction with 88% accuracy
Detecting low left ventricular ejection fraction from ECG using an interpretable and scalable predictor-driven framework
-
Patient identity drives brain tumor AI accuracy more than model choice
Fairboard: a quantitative framework for equity assessment of healthcare models
-
Observed risks explain why decision curves beat treat-all or treat-none
Why decision curves go above or below treat-all and treat-none: a PPV- and calibration-based guide for clinical prediction models
-
Review links network psychometrics to classical models for broader tools
Reconciling Latent Variables and Networks: Exploring and extending the Psychometric-Toolbox
-
Prais-Winsten maintains coverage under higher-order AR where OLS-NW fails
Multiple-group (Controlled) Interrupted Time Series Analysis with Higher-Order Autoregressive Errors: A Simulation Study Comparing Newey-West and Prais-Winsten Methods
-
Compositional ratios boost bankruptcy prediction recall
Adapting Altman's bankruptcy prediction model to the compositional data methodology
-
Compositional regression maps simplex data to cylinder via spheres
Compositional regression using principal nested spheres
-
Logistic tuning cuts GNSS positioning errors by 28 percent
Logistic-aided Huber M-estimator for robust GNSS positioning
-
Unified reprocessed datasets yield stable attack classifiers and high-fidelity synthetic
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation
-
Reconciliation lifts GARCH portfolio variance accuracy
Multivariate GARCH and portfolio variance prediction: A forecast reconciliation perspective
-
Triple-difference design removes bias in time-series policy studies
Improving causal inference in interrupted time series analysis: the triple difference design
-
CausalPFN runs fast but credible intervals miss the true ATE
Prior-Data Fitted Networks for Causal Inference: a Simulation Study with Real-World Scenarios
-
Nested vines fix climate model biases while preserving space-time links
Spatiotemporally Consistent Multivariate Bias Correction for Climate Projections via Nested Vine Copulas
-
Risk calibration adjusts C_pk thresholds for finite-sample uncertainty
Risk-Calibrated Process Capability Approval with Finite Samples
-
Prediction methods boost power in EHR genetic studies
Prediction-based Inference in Electronic Health Record (EHR)-linked Biobanks with Clinically Informative Outcomes
-
Plasmoid model matches FSRQ post-flare skewness shifts
Reconnection-driven State Transitions in Flat Spectrum Radio Quasars