Results 201 to 210 of about 2,509,073 (310)

Combining Bayesian and Evidential Uncertainty Quantification for Improved Bioactivity Modeling. [PDF]

open access: yesJ Chem Inf Model
Khalil B   +4 more
europepmc   +1 more source

Uncertainty Calibration in Molecular Machine Learning: Comparing Evidential and Ensemble Approaches

open access: yesChemistry – A European Journal, EarlyView.
Raw uncertainty estimates from deep evidential regression and deep ensembles are systematically miscalibrated. Post hoc calibration aligns predicted uncertainty with true errors, improving reliability and enabling efficient active learning and reducing computational cost while preserving predictive accuracy.
Bidhan Chandra Garain   +3 more
wiley   +1 more source

Rank‐based estimation of propensity score weights via subclassification

open access: yesCanadian Journal of Statistics, EarlyView.
Abstract Propensity score (PS) weighting estimators are widely used for causal effect estimation and enjoy desirable theoretical properties, such as consistency and potential efficiency under correct model specification. However, their performance can degrade in practice due to sensitivity to PS model misspecification.
Linbo Wang   +3 more
wiley   +1 more source

Predicting cervical cancer DNA methylation from genetic data using multivariate CMMP

open access: yesCanadian Journal of Statistics, EarlyView.
Abstract Epigenetic modifications link the environment to gene expression and play a crucial role in tumour development. DNA methylation, in particular, is gaining attention in cancer research, including cervical cancer, the focus of this study.
Hang Zhang   +5 more
wiley   +1 more source

Partial identification with categorical data and nonignorable missing outcomes

open access: yesCanadian Journal of Statistics, EarlyView.
Abstract Nonignorable missing outcomes are common in real‐world datasets and often require strong parametric assumptions to achieve identification. These assumptions can be implausible or untestable, and so we may wish to forgo them in favour of partially identified models that narrow the set of a priori possible values to an identification region.
Daniel Daly‐Grafstein, Paul Gustafson
wiley   +1 more source

Stagewise crop yield prediction with multisource functional indices

open access: yesCanadian Journal of Statistics, EarlyView.
Abstract Index insurance design involves integrating weather data, soil moisture, phenology information, and satellite imagery, which presents challenges in data fusion. This article addresses the modelling of multisource functional indices of varying lengths by constructing a stagewise ensemble of sequential models.
Jing Zou, Ostap Okhrin
wiley   +1 more source

Home - About - Disclaimer - Privacy