Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Deletion/substitution/addition algorithm in learning with applications in genomics.

Sandra E Sinisi1, Mark J van der Laan

  • 1Division of Biostatistics, School of Public Health, University of California, Berkeley, USA. ssin-isi@stat.berkeley.edu

Statistical Applications in Genetics and Molecular Biology
|May 2, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An approach to nonparametric inference on the causal dose-response function.

Journal of causal inference·2026
Same author

Sequential invitations to FOBT screening and colorectal cancer incidence.

Scientific reports·2026
Same author

Powering RCTs for Marginal Effects With GLMs Using Prognostic Score Adjustment.

Statistics in medicine·2026
Same author

Machine learning to optimize precision in the analysis of randomized trials: A journey in pre-specified, yet data-adaptive learning.

Clinical trials (London, England)·2026
Same author

Assessing Treatment Effects in Observational Data With Missing Confounders: A Comparative Study of Practical Doubly-Robust and Traditional Missing Data Methods.

Statistics in medicine·2026
Same author

Epistatic contributions to human traits via transcription factor mechanisms.

medRxiv : the preprint server for health sciences·2025
Same journal

Balanced mediated pathway detection in genomic data.

Statistical applications in genetics and molecular biology·2026
Same journal

Annealed variational mixtures for disease subtyping and biomarker discovery.

Statistical applications in genetics and molecular biology·2026
Same journal

Performance of the permutation test approach with base calling errors for detecting changes in variant allele frequencies in ctDNA for a single patient.

Statistical applications in genetics and molecular biology·2026
Same journal

BLOG: Bayesian longitudinal omics with group constraints.

Statistical applications in genetics and molecular biology·2026
Same journal

AI-driven risk prediction and categorization in cystic fibrosis leveraging AttentiveLSTM and Fox Wolf Optimizer.

Statistical applications in genetics and molecular biology·2026
Same journal

Perfect collinearity not created equal: measuring and visualizing the severity of multi-collinearity of modern omics data.

Statistical applications in genetics and molecular biology·2026
See all related articles

This study introduces a general deletion/substitution/addition algorithm to minimize empirical risk for estimators. This method enhances prediction accuracy for various outcomes, including survival data.

Area of Science:

  • Statistical Learning
  • Computational Biology
  • Bioinformatics

Background:

  • The van der Laan and Dudoit (2003) framework defines parameters of interest as risk minimizers for loss functions.
  • Candidate estimators are derived using loss functions, forming the basis for risk assessment.

Purpose of the Study:

  • To propose a general deletion/substitution/addition algorithm for minimizing empirical risk over variable subsets.
  • To introduce a new class of loss-based cross-validated algorithms for prediction and estimation tasks.
  • To extend these methods to handle complex data types like multivariate and censored outcomes.

Main Methods:

  • A general deletion/substitution/addition algorithm is proposed to minimize empirical risk for subset-specific estimators.
  • The algorithm is applied to subsets of variables, such as basis functions.

Related Experiment Videos

  • Loss-based cross-validation is employed for algorithm development.

    • Main Results:

    • The algorithm yields a novel class of loss-based cross-validated algorithms.
    • The method demonstrates applicability in predicting univariate outcomes and can be extended to multivariate, conditional density, hazard, and censored outcomes.
    • Simulations using polynomial basis functions in regression contexts are performed.

    Conclusions:

    • The deletion/substitution/addition algorithm offers a flexible approach for statistical estimation and prediction.
    • The method shows promise for applications in biological data analysis, such as identifying transcription factor binding sites.
    • The proposed algorithms are adaptable to various statistical modeling scenarios.