Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians.

By James R. Carpenter, J. Bithell. 2000

1,647 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation (2016, neutral): “The bootstrap method we present is the percentile bootstrap for confidence levels [2].”
High Confidence Off-Policy Evaluation with Models (2016, methodology): “Specifically, the bootstrap method we present is the percentile bootstrap for confidence levels [2].”
Defining an Optimal Cut-Point Value in ROC Analysis: An Alternative Approach (2017, methodology): “) In order to estimate the standard deviation and the confidence interval (CI) for the optimal cut-point, the bootstrap resampling technique is applied [14].”
Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network (2016, methodology): “For each ROC, the area under the curve (AUC) was computed and the 95% confidence interval was plotted according to [41].”
Analysis of Incomplete Data Using Inverse Probability Weighting and Doubly Robust Estimators (2010, methodology): “We used the nonparametric bootstrap (bias corrected and accelerated bootstrap percentile confidence intervals (Carpenter & Bithell, 2000)) for inference with all estimators.”
Semi-parametric and Parametric Inference of Extreme Value Models for Rainfall Data (2010, methodology): “To evaluate the uncertainty of the extreme value index estimators, discussed in this study, the bootstrap technique (Efron 1979; Davison and Hinkley 1997; Carpenter and Bithell 2000) is performed as follows.”
Reporting Recommendations for Tumor Marker Prognostic Studies (REMARK): Explanation and Elaboration (2012, methodology): “For internal validation, the specific validation algorithm used should be described (for example, bootstrapping, 10-fold or leave-one-out cross-validation) [147-149].”