arXiv subjects

David Azriel

Publications and source records attributed to David Azriel.

At least 19 recordsLinked to original sources

arXiv2026

Optimal Designs with Robust Inference for Binary Treatment Effects

We study randomized experiments with binary outcomes under Neyman's nonparametric model, where covariate measurements are fixed but potential outcomes are random. In this setting we derive the exact variance of the difference-in-means estimator and characterize designs that minimize it. We show that any balanced design satisfying a covariate-balance condition is asymptotically optimal, and we prove that a broad class of blocking designs satisfies this condition under mild smoothness assumptions. Because the variance depends on unknown success probabilities, unbiased variance estimation is impossible. We therefore develop two conservative estimators: a generalization of the Cochran-Mantel-Haenszel (CMH) statistic applicable to any balanced design, and an extension of Robins' variance estimator for blocking designs. We establish conditions under which the CMH-based estimator is asymptotically tight under local alternatives, thereby yielding asymptotically valid confidence intervals. Our theoretical and simulations results show that blocking and other designs that achieve covariate balance and sufficient degree of randomness, perform well when they are equipped with the CMH-based inference. Thus, we provide an experimental design and inference framework for incidence outcomes that is simultaneously variance-optimal, conservative in finite samples and asymptotically tight.

stat.ME↗

arXiv2026

Principal Components Decomposition of Fraction of Variance Explained in High Dimensional Linear Models with Strong Correlation

The fraction of variance explained (FVE) in a linear model quantifies the extent to which predictors account for outcome variability. In high-dimensional settings, where traditional FVE estimators do not apply, modern FVE estimators such as GWASH or linear mix-effect model estimated through the restricted maximum likelihood (LMM-REML) struggle with strong correlation among predictors, often found, for example, in brain imaging data. We propose a decomposition framework that partitions the FVE into two components: a low-dimensional component capturing the strong correlation, estimable by low dimensional methods, and a high-dimensional component with remaining weak correlation, estimable by high dimensional methods. Simulations demonstrate that decomposing dominant principal components (PCs) and estimating the high-dimensional FVE using GWASH or LMM-REML leads to improved bias reduction compared to directly applying standard approaches such as GWASH and LMM-REML. Our method shows consistent performance asymptotically as both the number of predictors and the number of samples increase. We illustrate the method in an analysis of the Adolescent Brain Cognitive Development (ABCD) brain imaging dataset, capturing nuanced heritability signals in the FVE of cognitive measures predicted by high-resolution brain imaging data.

stat.ME↗

arXiv2025

Block Designs that Provide Optimal Power in the Cochran-Mantel-Haenszel Test

We consider the asymptotic power performance under local alternatives of the Cochran-Mantel-Haenszel test. Our setting is non-traditional: we investigate randomized experiments that assign subjects via Fisher's blocking design. We show that blocking designs that satisfy a certain balance condition are asymptotically optimal. When the potential outcomes can be ordered, the balance condition is met for all blocking designs with number of blocks going to infinity. More generally, we prove that the pairwise matching design of Greevy et al. (2004) satisfies the balance condition under mild assumptions. In smaller sample sizes, we show a second order effect becomes operational thereby making blocking designs with a smaller number optimal. In practical settings with many covariates, we recommend pairwise matching for its ability to approximate the balance condition.

stat.ME↗

arXiv2025

Consistency of heritability estimation from summary statistics in high-dimensional linear models

In Genome-Wide Association Studies (GWAS), heritability is defined as the fraction of variance of an outcome explained by a large number of genetic predictors in a high-dimensional polygenic linear model. This work studies the asymptotic properties of the most common estimator of heritability from summary statistics called linkage disequilibrium score (LDSC) regression, together with a simpler and closely related estimator called GWAS heritability (GWASH). These estimators are analyzed in their basic versions and under various modifications used in practice including weighting and standardization. We show that, with some variations, two conditions which we call weak dependence (WD) and bounded-kurtosis effects (BKE) are sufficient for consistency of both the basic LDSC with fixed intercept and GWASH estimators, for both Gaussian and non-Gaussian predictors. For Gaussian predictors it is shown that these conditions are also necessary for consistency of GWASH (with truncation) and simulations suggest that necessity holds too when the predictors are non-Gaussian. We also show that, with properly truncated weights, weighting does not change the consistency results, but standardization of the predictors and outcome, as done in practice, introduces bias in both LDSC and GWASH if the two essential conditions are violated. Finally, we show that, when population stratification is present, all the estimators considered are biased, and the bias is not remedied by using the LDSC regression estimator with free intercept, as originally suggested by the authors of that estimator.

math.ST↗

arXiv2024

Surgery duration prediction using multi-task feature selection

Efficient optimization of operating room (OR) activity poses a significant challenge for hospital managers due to the complex and risky nature of the environment. The traditional "one size fits all" approach to OR scheduling is no longer practical, and personalized medicine is required to meet the diverse needs of patients, care providers, medical procedures, and system constraints within limited resources. This paper aims to introduce a scientific and practical tool for predicting surgery durations and improving OR performance for maximum benefit to patients and the hospital. Previous works used machine-learning models for surgery duration prediction based on preoperative data. The models consider covariates known to the medical staff at the time of scheduling the surgery. Given a large number of covariates, model selection becomes crucial, and the number of covariates used for prediction depends on the available sample size. Our proposed approach utilizes multi-task regression to select a common subset of predicting covariates for all tasks with the same sample size while allowing the model's coefficients to vary between them. A regression task can refer to a single surgeon or operation type or the interaction between them. By considering these diverse factors, our method provides an overall more accurate estimation of the surgery durations, and the selected covariates that enter the model may help to identify the resources required for a specific surgery. We found that when the regression tasks were surgeon-based or based on the pair of operation type and surgeon, our suggested approach outperformed the compared baseline suggested in a previous study. However, our approach failed to reach the baseline for an operation-type-based task.

stat.AP↗

arXiv2024

The Pairwise Matching Design is Optimal under Extreme Noise and Assignments

We consider the general performance of the difference-in-means estimator in an equally-allocated two-arm randomized experiment under common experimental endpoints such as continuous (regression), incidence, proportion, count and uncensored survival. We consider two sources of randomness: the subject-specific assignments and the contribution of unobserved subject-specific measurements. We then examine mean squared error (MSE) performance under a new, more realistic "simultaneous tail criterion". We prove that the pairwise matching design of Greevy et al. (2004) performs best asymptotically under this criterion when compared to other blocking designs. We also prove that the optimal design must be less random than complete randomization and more random than any deterministic, optimized allocation. Theoretical results are supported by simulations in all five response types.

stat.ME↗

arXiv2023

Optimal confidence interval for the difference of proportions

Estimating the probability of the binomial distribution is a basic problem, which appears in almost all introductory statistics courses and is performed frequently in various studies. In some cases, the parameter of interest is a difference between two probabilities, and the current work studies the construction of confidence intervals for this parameter when the sample size is small. Our goal is to find the shortest confidence intervals under the constraint of coverage probability being at least as large as a predetermined level. For the two-sample case, there is no known algorithm that achieves this goal, but different heuristics procedures have been suggested, and the present work aims at finding optimal confidence intervals. In the one-sample case, there is a known algorithm that finds optimal confidence intervals presented by Blyth and Still (1983). It is based on solving small and local optimization problems and then using an inversion step to find the global optimum solution. We show that this approach fails in the two-sample case and therefore, in order to find optimal confidence intervals, one needs to solve a global optimization problem, rather than small and local ones, which is computationally much harder. We present and discuss the suitable global optimization problem. Using the Gurobi package we find near-optimal solutions when the sample sizes are smaller than 15, and we compare these solutions to some existing methods, both approximate and exact. We find that the improvement in terms of lengths with respect to the best competitor varies between 1.5\% and 5\% for different parameters of the problem. Therefore, we recommend the use of the new confidence intervals when both sample sizes are smaller than 15. Tables of the confidence intervals are given in the Excel file in this link.

stat.CO↗

arXiv2022

The Optimality of Blocking Designs in Equally and Unequally Allocated Randomized Experiments with General Response

We consider the performance of the difference-in-means estimator in a two-arm randomized experiment under common experimental endpoints such as continuous (regression), incidence, proportion and survival. We examine performance under both equal and unequal allocation to treatment groups and we consider both the Neyman randomization model and the population model. We show that in the Neyman model, where the only source of randomness is the treatment manipulation, there is no free lunch: complete randomization is minimax for the estimator's mean squared error. In the population model, where each subject experiences response noise with zero mean, the optimal design is the deterministic perfect-balance allocation. However, this allocation is generally NP-hard to compute and moreover, depends on unknown response parameters. When considering the tail criterion of Kapelner et al. (2021), we show the optimal design is less random than complete randomization and more random than the deterministic perfect-balance allocation. We prove that Fisher's blocking design provides the asymptotically optimal degree of experimental randomness. Theoretical results are supported by simulations in all considered experimental settings.

math.ST↗

arXiv2022

The Role of Pairwise Matching in Experimental Design for an Incidence Outcome

We consider the problem of evaluating designs for a two-arm randomized experiment with an incidence (binary) outcome under a nonparametric general response model. Our two main results are that the priori pair matching design of Greevy et al. (2004) is (1) the optimal design as measured by mean squared error among all block designs which includes complete randomization. And (2), this pair-matching design is minimax, i.e. it provides the lowest mean squared error under an adversarial response model. Theoretical results are supported by simulations and clinical trial data.

stat.ME↗

arXiv2022

Empirical Bayes approach to Truth Discovery problems

When aggregating information from conflicting sources, one's goal is to find the truth. Most real-value \emph{truth discovery} (TD) algorithms try to achieve this goal by estimating the competence of each source and then aggregating the conflicting information by weighing each source's answer proportionally to her competence. However, each of those algorithms requires more than a single source for such estimation and usually does not consider different estimation methods other than a weighted mean. Therefore, in this work we formulate, prove, and empirically test the conditions for an Empirical Bayes Estimator (EBE) to dominate the weighted mean aggregation. Our main result demonstrates that EBE, under mild conditions, can be used as a second step of any TD algorithm in order to reduce the expected error.

cs.LG↗

arXiv2022

A zero-estimator approach for estimating the signal level in a high-dimensional model-free setting

We study a high-dimensional regression setting under the assumption of known covariate distribution. We aim at estimating the amount of explained variation in the response by the best linear function of the covariates (the signal level). In our setting, neither sparsity of the coefficient vector, nor normality of the covariates or linearity of the conditional expectation are assumed. We present an unbiased and consistent estimator and then improve it by using a zero-estimator approach, where a zero-estimator is a statistic whose expected value is zero. More generally, we present an algorithm based on the zero estimator approach that in principle can improve any given estimator. We study some asymptotic properties of the proposed estimators and demonstrate their finite sample performance in a simulation study.

math.ST↗

arXiv2021

Optimal minimax random designs for weighted least squares estimators

This work studies an experimental design problem where {the values of a predictor variable, denoted by $x$}, are to be determined with the goal of estimating a function $m(x)$, which is observed with noise. A linear model is fitted to $m(x)$ but it is not assumed that the model is correctly specified. It follows that the quantity of interest is the best linear approximation of $m(x)$, which is denoted by $\ell(x)$. It is shown that in this framework the ordinary least squares estimator typically leads to an inconsistent estimation of $\ell(x)$, and rather weighted least squares should be considered. An asymptotic minimax criterion is formulated for this estimator, and a design that minimizes the criterion is constructed. An important feature of this problem is that the $x$'s should be random, rather than fixed. Otherwise, the minimax risk is infinite. It is shown that the optimal random minimax design is different from its deterministic counterpart, which was studied previously, and a simulation study indicates that it generally performs better when $m(x)$ is a quadratic or a cubic function. Another finding is that when the variance of the noise goes to infinity, the random and deterministic minimax designs coincide. The results are illustrated for polynomial regression models and the general case is also discussed.

math.ST↗

arXiv2021

Optimal designs for the development of personalized treatment rules

We study the design of multi-armed parallel group clinical trials to estimate personalized treatment rules that identify the best treatment for a given patient with given covariates. Assuming that the outcomes in each treatment arm are given by a homoscedastic linear model, with possibly different variances between treatment arms, and that the trial subjects form a random sample from an unselected overall population, we optimize the (possibly randomized) treatment allocation allowing the allocation rates to depend on the covariates. We find that, for the case of two treatments, the approximately optimal allocation rule does not depend on the value of the covariates but only on the variances of the responses. In contrast, for the case of three treatments or more, the optimal treatment allocation does depend on the values of the covariates as well as the true regression coefficients. The methods are illustrated with a recently published dietary clinical trial.

math.ST↗

arXiv2021

Improved Estimators for Semi-supervised High-dimensional Regression Model

We study a linear high-dimensional regression model in a semi-supervised setting, where for many observations only the vector of covariates $X$ is given with no response $Y$. We do not make any sparsity assumptions on the vector of coefficients, and aim at estimating $\mathrm{Var}(Y|X)$. We propose an estimator, which is unbiased, consistent, and asymptotically normal. This estimator can be improved by adding zero-estimators arising from the unlabelled data. Adding zero-estimators does not affect the bias and potentially can reduce variance. In order to achieve optimal improvement, many zero-estimators should be used, but this raises the problem of estimating many parameters. Therefore, we introduce covariate selection algorithms that identify which zero-estimators should be used in order to improve the above estimator. We further illustrate our approach for other estimators, and present an algorithm that improves estimation for any given variance estimator. Our theoretical results are demonstrated in a simulation study.

math.ST↗

arXiv2020

Optimal selection of sample-size dependent common subsets of covariates for multi-task regression prediction

An analyst is given a training set consisting of regression datasets $D_j$ of different sizes, which are distributed according to some $G_j$, $j=1,\ldots,\cal J$, where the distributions $G_j$ are assumed to form a random sample generated by some common source. In particular, the $D_j$'s have a common set of covariates and they are all labeled. The training set is used by the analyst for selection of subsets of covariates denoted by ${P}^*(n)$, whose role is described next. The multi-task problem we consider is as follows: given a number of random labeled datasets (which may be in the training set or not) $D_{J_k}$ of size $n_k$, $k=1,\ldots,K$, estimate separately for each dataset the regression coefficients on the subset of covariates ${P}^*(n_k)$ and then predict future dependent variables given their covariates. Naturally, a large sample size $n_k$ of $D_{J_k}$ allows a larger subset of covariates, and the dependence of the size of the selected covariate subsets on $n_k$ is needed in order to achieve good prediction and avoid overfitting. Subset selection is notoriously difficult and computationally demanding, and requires large samples; using all the regression datasets in the training set together amounts to borrowing strength toward better selection under suitable assumptions. Furthermore, using common subsets for all regressions having a given sample size standardizes and simplifies the data collection and avoids having to select and use a different subset for each prediction task. Our approach is efficient when the relevant covariates for prediction are common to the different regressions, while the models' coefficients may vary between different regressions.

math.ST↗

arXiv2020

Better Experimental Design by Hybridizing Binary Matching with Imbalance Optimization

We present a new experimental design procedure that divides a set of experimental units into two groups in order to minimize error in estimating an additive treatment effect. One concern is minimizing error at the experimental design stage is large covariate imbalance between the two groups. Another concern is robustness of design to misspecification in response models. We address both concerns in our proposed design: we first place subjects into pairs using optimal nonbipartite matching, making our estimator robust to complicated non-linear response models. Our innovation is to keep the matched pairs extant, take differences of the covariate values within each matched pair and then we use the greedy switching heuristic of Krieger et al. (2019) or rerandomization on these differences. This latter step greatly reduce covariate imbalance to the rate $O_p(n^{-4})$ in the case of one covariate that are uniformly distributed. This rate benefits from the greedy switching heuristic which is $O_p(n^{-3})$ and the rate of matching which is $O_p(n^{-1})$. Further, our resultant designs are shown to be as random as matching which is robust to unobserved covariates. When compared to previous designs, our approach exhibits significant improvement in the mean squared error of the treatment effect estimator when the response model is nonlinear and performs at least as well when it the response model is linear. Our design procedure is found as a method in the open source R package available on CRAN called GreedyExperimentalDesign.

stat.ME↗

arXiv2020

Improving the Power of the Randomization Test

We consider the problem of evaluating designs for a two-arm randomized experiment with the criterion being the power of the randomization test for the one-sided null hypothesis. Our evaluation assumes a response that is linear in one observed covariate, an unobserved component and an additive treatment effect where the only randomness comes from the treatment allocations. It is well-known that the power depends on the allocations' imbalance in the observed covariate and this is the reason for the classic restricted designs such as rerandomization. We show that power is also affected by two other design choices: the number of allocations in the design and the degree of linear dependence among the allocations. We prove that the more allocations, the higher the power and the lower the variability in the power. Designs that feature greater independence of allocations are also shown to have higher performance. Our theoretical findings and extensive simulation studies imply that the designs with the highest power provide thousands of highly independent allocations that each provide nominal imbalance in the observed covariates. These high powered designs exhibit less randomization than complete randomization and more randomization than recently proposed designs based on numerical optimization. Model choices for a practicing experimenter are rerandomization and greedy pair switching, where both outperform complete randomization and numerical optimization. The tradeoff we find also provides a means to specify the imbalance threshold parameter when rerandomizing.

stat.ME↗

arXiv2019

Optimal Rerandomization via a Criterion that Provides Insurance Against Failed Experiments

We present an optimized rerandomization design procedure for a non-sequential treatment-control experiment. Randomized experiments are the gold standard for finding causal effects in nature. But sometimes random assignments result in unequal partitions of the treatment and control group visibly seen as imbalance in observed covariates. There can additionally be imbalance on unobserved covariates. Imbalance in either observed or unobserved covariates increases treatment effect estimator error inflating the width of confidence regions and reducing experimental power. "Rerandomization" is a strategy that omits poor imbalance assignments by limiting imbalance in the observed covariates to a prespecified threshold. However, limiting this threshold too much can increase the risk of contracting error from unobserved covariates. We introduce a criterion that combines observed imbalance while factoring in the risk of inadvertently imbalancing unobserved covariates. We then use this criterion to locate the optimal rerandomization threshold based on the practitioner's level of desired insurance against high estimator error. We demonstrate the gains of our designs in simulation and in a dataset from a large randomized experiment in education. We provide an open source R package available on CRAN named OptimalRerandExpDesigns which generates designs according to our algorithm.

stat.ME↗