Pitfalls of hypothesis tests and model selection on bootstrap samples: causes and consequences in biometrical applications

DOI10.1002/BIMJ.201400246zbMATH Open1386.62053OpenAlexW2123482240WikidataQ40537500 ScholiaQ40537500MaRDI QIDQ2806831FDOQ2806831

Authors: Silke Janitza, Harald Binder, Anne-Laure Boulesteix 

Publication date: 19 May 2016

Published in: Biometrical Journal (Search for Journal in Brave)

Full work available at URL: https://epub.ub.uni-muenchen.de/21038/

Recommendations

• Three methods to apply the bootstrap correctly to hypothesis testing
• Bootstrap Model Selection
• Introduction to the bootstrap world
• Subsampling versus bootstrapping in resampling-based model selection for multivariable regression
• A general bootstrap algorithm for hypothesis testing

zbMATH Keywords

bootstrapbootstrapped \(p\)-valuesbootstrapped information criteriabootstrapped test statistictests on bootstrap samples

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Nonparametric statistical resampling methods (62G09)

Cites Work

• Model-based boosting 2.0
• Greedy function approximation: A gradient boosting machine.
• Title not available (Why is that?)
• Bootstrap methods: another look at the jackknife
• Adapting prediction error estimates for biased complexity selection in high-dimensional bootstrap samples
• Jackknife, bootstrap and other resampling methods in regression analysis
• A general theory for jackknife variance estimation
• Bootstrap Methods
• Model Selection: An Integral Part of Inference
• Model Selection and Multimodel Inference
• Large sample confidence regions based on subsamples under minimal assumptions
• Recent developments in bootstrap methodology
• Title not available (Why is that?)
• Naïve Nonparametric Bootstrap Model Weights Are Biased
• Subsampling versus bootstrapping in resampling-based model selection for multivariable regression
• Categorical variables with many categories are preferentially selected in bootstrap-based model selection procedures for multivariable regression models

Cited In (9)

• An update on statistical boosting in biomedicine
• Analyzing large datasets with bootstrap penalization
• On stability issues in deriving multivariable regression models
• Stability of clinical prediction models developed using statistical or machine learning methods
• Selection of variables for multivariable models: opportunities and limitations in quantifying model stability by resampling
• The use of components' weights improves the diagnostic accuracy of a health-related index
• Categorical variables with many categories are preferentially selected in bootstrap-based model selection procedures for multivariable regression models
• Subsampling versus bootstrapping in resampling-based model selection for multivariable regression
• Random forest for ordinal responses: prediction and variable selection

This page was built for publication: Pitfalls of hypothesis tests and model selection on bootstrap samples: causes and consequences in biometrical applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2806831)