Covariate balance in simple, stratified and clustered comparative studies

DOI10.1214/08-STS254zbMATH Open1327.62019arXiv0808.3857OpenAlexW2949401922MaRDI QIDQ900461FDOQ900461

Jake Bowers, Ben B. Hansen

Publication date: 22 December 2015

Published in: Statistical Science (Search for Journal in Brave)

Abstract: In randomized experiments, treatment and control groups should be roughly the same--balanced--in their distributions of pretreatment variables. But how nearly so? Can descriptive comparisons meaningfully be paired with significance tests? If so, should there be several such tests, one for each pretreatment variable, or should there be a single, omnibus test? Could such a test be engineered to give easily computed $p$-values that are reliable in samples of moderate size, or would simulation be needed for reliable calibration? What new concerns are introduced by random assignment of clusters? Which tests of balance would be optimal? To address these questions, Fisher's randomization inference is applied to the question of balance. Its application suggests the reversal of published conclusions about two studies, one clinical and the other a field experiment in political participation.

Full work available at URL: https://arxiv.org/abs/0808.3857

Recommendations

• The role of covariate balance in observational studies
• New multivariate tests for assessing covariate balance in matched observational studies
• Comparison of covariate balance weighting methods in estimating treatment effects
• Balancing tests in stratified randomized controlled trials: a cautionary note
• The Effect of Pooling Across Strata in Perfectly Balanced Studies
• Estimation of treatment effects in matched-pair cluster randomized trials by calibrating covariate imbalance between clusters
• Between- and Within-Cluster Covariate Effects in the Analysis of Clustered Data
• Covariates distributions balancing for continuous treatment

zbMATH Keywords

clusterrandomization inferencesubclassificationcontiguitycommunity interventiongroup randomization

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Applied Asymptotics
• Title not available (Why is that?)
• Title not available (Why is that?)
• Probability Inequalities for Sums of Bounded Random Variables
• Title not available (Why is that?)
• Regression modeling strategies. With applications to linear models, logistic regression and survival analysis
• Title not available (Why is that?)
• Statistical Models
• On Simpson's Paradox and the Sure-Thing Principle
• Title not available (Why is that?)
• The Generalization of Student's Ratio
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (22)

• No star is good news: a unified look at rerandomization based on \(p\)-values from covariate balance tests
• Comment: Matching methods for observational studies derived from large administrative databases
• Response transformation and profit decomposition for revenue uplift modeling
• Rerandomization and optimal matching
• The Effect of Pooling Across Strata in Perfectly Balanced Studies
• Randomization Inference With Natural Experiments
• The Perils of Balance Testing in Experimental Design: Messy Analyses of Clean Data
• The classification permutation test: a flexible approach to testing for covariate imbalance in observational studies
• Analyzing propensity matched zero-inflated count outcomes in observational studies
• Complexity and Approximation Results for the Balance Optimization Subset Selection Model for Causal Inference in Observational Studies
• Using the Exterior Match to Compare Two Entwined Matched Control Groups
• Evaluating and improving a matched comparison of antidepressants and bone density
• Comparison of covariate balance weighting methods in estimating treatment effects
• New multivariate tests for assessing covariate balance in matched observational studies
• Using Standard Tools From Finite Population Sampling to Improve Causal Inference for Complex Experiments
• Rerandomization in \(2^K\) factorial experiments
• Early effects of 2014 U.S. Medicaid expansions on mortality: design-based inference for impacts on small subgroups despite small-cell suppression
• Rerandomization to improve covariate balance in experiments
• Balancing tests in stratified randomized controlled trials: a cautionary note
• Randomization Inference in a Group–Randomized Trial of Treatments for Depression
• The sensitivity of linear regression coefficients' confidence limits to the omission of a confounder
• A weighting analogue to pair matching in propensity score analysis

Uses Software

• rms
• RItools

This page was built for publication: Covariate balance in simple, stratified and clustered comparative studies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q900461)