Combining information from independent sources through confidence distributions

Abstract

This paper develops new methodology, together with related theories, for combining information from independent studies through confidence distributions. A formal definition of a confidence distribution and its asymptotic counterpart (i.e., asymptotic confidence distribution) are given and illustrated in the context of combining information. Two general combination methods are developed: the first along the lines of combining p-values, with some notable differences in regard to optimality of Bahadur type efficiency; the second by multiplying and normalizing confidence densities. The latter approach is inspired by the common approach of multiplying likelihood functions for combining parametric information. The paper also develops adaptive combining methods, with supporting asymptotic theory which should be of practical interest. The key point of the adaptive development is that the methods attempt to combine only the correct information, downweighting or excluding studies containing little or wrong information about the true parameter of interest. The combination methodologies are illustrated in simulated and real data examples with a variety of applications.

Published at http://dx.doi.org/10.1214/009053604000001084 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (20)

• Prediction intervals for random-effects meta-analysis: a confidence distribution approach
• Confidence distribution (CD) -- distribution estimator of a parameter
• Statistical Methods and Computing for Big Data
• Distributed Simultaneous Inference in Generalized Linear Models via Confidence Distribution
• Incorporating external information in analyses of clinical trials with binary outcomes
• A Distributed and Integrated Method of Moments for High-Dimensional Correlated Data Analysis
• Coherent frequentism
• Large-scale interval and point estimates from an empirical Bayes extension of confidence posteriors
• Controlling the degree of caution in statistical inference with the Bayesian and frequentist approaches as opposite extremes
• Doubly Distributed Supervised Learning and Inference with High-Dimensional Correlated Outcomes
• A frequentist framework of inductive reasoning
• Bridging Bayesian, frequentist and fiducial (BFF) inferences using confidence distribution
• Discussion of "Is Bayes Posterior just Quick and Dirty Confidence?" by D. A. S. Fraser
• The Transform between the space of observed values and the space of possible values of the parameter
• Nonparametric fusion learning: synthesize inferences from diverse sources using depth confidence distribution
• Discussion of "On the Birnbaum Argument for the Strong Likelihood Principle"
• The Bayesian Effects in Measurement of the Asymmetry of Poisson Flows
• A robust fusion-extraction procedure with summary statistics in the presence of biased sources
• A unified nonparametric fiducial approach to interval-censored data
• A simple recipe for making accurate parametric inference in finite sample