Anqi Zhao

Journal Article Biometrika · December 1, 2024 Covariate adjustment can improve precision in analysing randomized experiments. With fully observed data, regression adjustment and propensity score weighting are asymptotically equivalent in improving efficiency over unadjusted analysis. When some outcome ... Full text Cite

No star is good news: A unified look at rerandomization based on p-values from covariate balance tests

Journal Article Journal of Econometrics · April 1, 2024 Randomized experiments balance all covariates on average and are considered the gold standard for estimating treatment effects. Chance imbalances are nonetheless common in realized treatment allocations. To inform readers of the comparability of treatment ... Full text Cite

A Randomization-Based Theory for Preliminary Testing of Covariate Balance in Controlled Trials

Journal Article Statistics in Biopharmaceutical Research · January 1, 2024 Randomized trials balance all covariates on average and are the gold standard for estimating treatment effects. Chance imbalances nevertheless exist more or less in realized treatment allocations and intrigue an important question: what should we do if the ... Full text Cite

To Adjust or not to Adjust? Estimating the Average Treatment Effect in Randomized Experiments with Missing Covariates

Journal Article Journal of the American Statistical Association · January 1, 2024 Randomized experiments allow for consistent estimation of the average treatment effect based on the difference in mean outcomes without strong modeling assumptions. Appropriate use of pretreatment covariates can further improve the estimation efficiency. M ... Full text Cite

Rerandomization and Covariate Adjustment in Split-Plot Designs

Journal Article Journal of Business and Economic Statistics · January 1, 2024 Split-plot designs are widely used in agricultural, industrial, social, and biomedical experiments to accommodate hard-to-change factors. Given multiple factors of interest and experimental units that are nested within groups, the design assigns a subset o ... Full text Cite

Covariate adjustment in multiarmed, possibly factorial experiments

Journal Article Journal of the Royal Statistical Society Series B Statistical Methodology · February 1, 2023 Randomized experiments are the gold standard for causal inference and enable unbiased estimation of treatment effects. Regression adjustment provides a convenient way to incorporate covariate information for additional efficiency. This article provides a u ... Full text Cite

Regression-based causal inference with factorial experiments: estimands, model specifications and design-based properties

Journal Article Biometrika · September 1, 2022 Factorial designs are widely used because of their ability to accommodate multiple factors simultaneously. Factor-based regression with main effects and some interactions is the dominant strategy for downstream analysis, delivering point estimators and sta ... Full text Cite

EVIDENCE FACTORS FROM MULTIPLE, POSSIBLY INVALID, INSTRUMENTAL VARIABLES

Journal Article Annals of Statistics · June 1, 2022 Valid instrumental variables enable treatment effect inference even when selection into treatment is biased by unobserved confounders. When multiple candidate instruments are available, but some of them are possibly invalid, the previously proposed reinfor ... Full text Cite

RECONCILING DESIGN-BASED AND MODEL-BASED CAUSAL INFERENCES FOR SPLIT-PLOT EXPERIMENTS

Journal Article Annals of Statistics · April 1, 2022 The split-plot design arose from agricultural science with experimental units, also known as the subplots, nested within groups known as the whole plots. It assigns different interventions at the whole-plot and subplot levels, respectively, providing a con ... Full text Cite

Covariate-adjusted Fisher randomization tests for the average treatment effect

Journal Article Journal of Econometrics · December 1, 2021 Fisher's randomization test (FRT) delivers exact p-values under the strong null hypothesis of no treatment effect on any units whatsoever and allows for flexible covariate adjustment to improve the power. Of interest is whether the resulting covariate-adju ... Full text Cite

The effect of user interactions on shaping online trust: Evidence from a large-scale experiment

Conference Proceedings of the 24th Pacific Asia Conference on Information Systems Information Systems is for the Future Pacis 2020 · January 1, 2020 Trust is critical to the healthy function and growth of organizations. In particular, the success of online platforms of resource exchange, which depends on enabling trust between strangers, hinges on understanding factors that contribute to the engineerin ... Cite

Randomization-based causal inference from split-plot designs

Journal Article Annals of Statistics · October 1, 2018 Under the potential outcomes framework, we propose a randomization based estimation procedure for causal inference from split-plot designs, with special emphasis on 22 designs that naturally arise in many social, behavioral and biomedical experi ... Full text Cite

MSIQ: Joint modeling of multiple RNA-SEQ samples for accurate isoform quantification

Journal Article Annals of Applied Statistics · March 1, 2018 Next-generation RNA sequencing (RNA-seq) technology has been widely used to assess full-length RNA isoform abundance in a high-throughput manner. RNA-seq data offer insight into gene expression levels and transcriptome structures, enabling us to better und ... Full text Cite

Neyman-pearson classiffication under high-dimensional settings

Journal Article Journal of Machine Learning Research · December 1, 2016 Most existing binary classiffication methods target on the optimization of the overall classification risk and may fail to serve some real-world applications such as cancer diagnosis, where users are more concerned with the risk of misclassifying one speci ... Cite

A survey on Neyman-Pearson classification and suggestions for future research

Journal Article Wiley Interdisciplinary Reviews Computational Statistics · March 1, 2016 In statistics and machine learning, classification studies how to automatically learn to make good qualitative predictions (i.e., assign class labels) based on past observations. Examples of classification problems include email spam filtering, fraud detec ... Full text Cite