On The Bayesian Bootstrap

By R. Cano. 1992

How researchers see this paper

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

Citations in the corpus

Heterogeneous Treatment Effects in Digital Experimentation (2014, methodology): “Following Rubin (1981), we can obtain a sample from the posterior on γ through a simple Bayesian bootstrap: for b = 1 , . . . , B , • draw ω b ∼ Dir( 1 ) , and set Ω b = diag( ω b ) ; then The same steps can be used to obtain posterior samples for the interaction-adjusted effects, γ (cid:63) , or…”
A Nonparametric Bayesian Analysis of Heterogenous Treatment Effects in Digital Experimentation (2014, methodology): “Following Rubin (1981), we can obtain a sample from the posterior on S through a Bayesian bootstrap.”
Bootstrapped Thompson Sampling and Deep Exploration (2015, methodology): “In fact, with a small modiﬁcation, Algorithm 1 becomes Algorithm 2, the so-called Bayesian bootstrap, for which the distribution produced can be interpreted as a posterior based on the data and a degenerate Dirichlet prior [5].”
Nonparametric Applications of Bayesian Inference (2003, methodology): “In this article we presented two applications of a less parametric Bayes approach that are due to Ferguson (1973, 1974) and Rubin (1981).”
A Review of Hot Deck Imputation for Survey Non‐response (2010, methodology): “One such procedure is the Bayesian Bootstrap (BB) (Rubin, 1981).”
Bootstrapping data arrays of arbitrary order (2011, methodology): “There are two main ways to bootstrap: resampling (Efron, 1979) and reweighting (Rubin, 1981), with the distinction being that the former uses a multinomial distribution on the data while the latter applies independent random weights to the observations.”
Generalized bootstrap for estimators of minimizers of convex functions (2003, methodology): “…a measurable way satisfying QnB(anB) = min a QnB(a): (1.8) The above scheme includes suitable generalizations of diHerent known resampling techniques like the classical bootstrap of Efron (1979), the Bayesian bootstrap of Rubin (1981), the k out of n bootstrap and the diHerent delete-d jackknives.”
Inference for Nonprobability Samples (2017, methodology): “…assumption of ignorable sampling (X is independent of the sampling indicator I conditional on Z) by making draws of p(Xp,Zp) from a Bayesian bootstrap (Rubin, 1981) and draws from p(Xns,Zns |Xp, Zp) via a finite population Bayesian bootstrap (FPBB) procedure that accounts for probabilities of…”
Tests of general relativity with the binary black hole signals from the LIGO-Virgo catalog GWTC-1 (2019, methodology): “[6], we quantify this uncertainty using Bayesian bootstrapping [124].”
Bayesian inference in a class of partially identified models (2016, background): “See for example Tamer (2003), Berry and Tamer (2006), or Kline (2015a, 2015b) for further details of various models of this general form, each of which imply a certain form for f (·).”
A survey of Bayesian predictive methods for model assessment, selection and comparison (2012, methodology): “|D) cannot be described well with a Gaussian distribution, Vehtari and Lampinen (2002) proposed to use a non-parametric Bayesian bootstrap (BB) (Rubin, 1981) approach based on the Dirichlet distribution.”
Using CART to generate partially synthetic public use microdata (2005, methodology): “A Bayesian bootstrap (Rubin 1981) is employed in each leaf as part of the imputation process.”
Bayesian quantile regression methods (2010, methodology): “4 Comparison with the Bayesian Bootstrap The Bayesian bootstrap of Rubin (1981) takes the data to be iid multinomial with probabilities {pi}.”
Variance estimation in high dimensional regression models (2000, background): “The idea of bootstrapping with random weights probably appeared first in Rubin (1981).”