arXiv subjects

Keisuke Hanada

Publications and source records attributed to Keisuke Hanada.

12 recordsLinked to original sources

arXiv2026

Covariate-Adaptive Sample Size Re-estimation for Population-Standardized Historical Control Designs in Single-Arm Trials

Externally controlled single-arm trials are increasingly considered when randomized controls are infeasible, but baseline imbalance between the active-arm trial and historical controls complicates both estimation and sample size planning. We propose a population-standardized design framework in which the target estimand is defined for the actually enrolled active-arm population and historical-control outcomes are standardized to that population through a pre-specified balancing score. Building on this estimand, we develop an outcome-blinded, covariate-adaptive sample size re-estimation (SSR) procedure that updates the required sample size using only accumulating baseline covariates, without using active-arm outcomes during enrollment. The method combines an initial scenario-based design with sequential updates of the enrolled-population score distribution, standardized control parameters, and target sample size under pre-specified stopping rules. We give conditional and unconditional power interpretations and sufficient conditions for approximate type I error control under repeated blinded SSR. In simulation studies with distributional shifts between planned and true active-arm populations, fixed designs based only on planning assumptions lost power, whereas the proposed SSR maintained power near the target level and performed similarly to an oracle design. In an illustrative ADCS-based example, the proposed procedures yielded different final sample sizes across adjustment sets, reflecting evolving enrolled-population covariate profiles. These results support covariate-adaptive, outcome-blinded SSR as a practical design strategy for externally controlled single-arm trials that target population-standardized treatment effects.

stat.ME↗

arXiv2026

Differentially Private One-Shot Federated Inference for Linear Mixed Models via Lossless Likelihood Reconstruction

One-shot federated learning enables multi-site inference with minimal communication. However, sharing summary statistics can still leak sensitive individual-level information when sites have only a small number of patients. In particular, shared cross-product summaries can reveal patient-level covariate patterns under discrete covariates. Motivated by this concern, this study proposes a differentially private one-shot federated inference framework for linear mixed models with a random-intercept working covariance. The method reconstructs the pooled likelihood from site-level summary statistics and applies a Gaussian mechanism to perturb these summaries, ensuring a site-level differential privacy. Cluster-robust variance estimators are developed that are computed directly from the privatized summaries. Robust variance provides valid uncertainty quantification even under covariance mis-specification. Under a multi-site asymptotic regime, the consistency and asymptotic normality of the proposed estimator are established and the leading-order statistical cost of privacy is characterized. Simulation studies show that moderate privacy noise substantially reduces reconstruction risk while maintaining competitive estimation accuracy as the number of sites increases. However, very strong privacy settings can lead to unstable standard errors when the number of sites is limited. An application using multi-site COVID-19 testing data demonstrates that meaningful privacy protection can be achieved with a modest loss of efficiency.

stat.ME↗

arXiv2026

Hybrid Non-informative and Informative Prior Model-assisted Designs for Mid-trial Dose Insertion

In oncology phase I trials, model-assisted designs have been increasingly adopted because they enable adaptive yet operationally simple dose adjustment based on accumulating safety data, leading to a paradigm shift in dose-escalation methodology. In practice, a single mid-trial dose insertion may be considered to examine safer doses and/or to collect more informative efficacy data. In this study, we investigate methods to improve dose assignment and the selection of the maximum tolerated dose (MTD) or the optimal biological dose (OBD) when a new dose level is added during an ongoing trial under a model-assisted framework, by assigning informative prior information to the inserted dose. We propose a hybrid design that uses a non-informative model-assisted design at trial initiation and, upon dose insertion, applies an informative-prior extension only to the newly added dose. In addition, to address potential skeleton misspecification, we propose two adaptive extensions: (i) an online-weighting approach that updates the skeleton over time, and (ii) a Bayesian-mixture approach that robustly combines multiple candidate skeletons. We evaluate the proposed methods through simulation studies.

stat.ME↗

arXiv2025

A Clustering Approach for Basket Trials Based on Treatment Response Trajectories

Heterogeneity in efficacy is sometimes observed across baskets in basket trials. In this study, we propose a model-free clustering framework that groups baskets based on transition probabilities derived from the trajectories of treatment response, rather than relying solely on a single efficacy endpoint such as the objective response rate. The number of clusters is not predetermined but is automatically determined in a data-driven manner based on the similarity structure among baskets. After clustering, baskets within the same cluster are analyzed using a hierarchical Bayesian model. This framework aims to improve the estimation precision of efficacy endpoints and enhance statistical power while maintaining the type~I error rate at the nominal level. The performance of the proposed method was evaluated through simulation studies. The results demonstrated that the proposed method can accurately identify cluster structures in heterogeneous settings and, even under such conditions, maintain the type~I error rate at the nominal level while improving statistical power.

stat.ME↗

arXiv2025

Random-effects meta-analysis via generalized linear mixed models: A Bartlett-corrected approach for few studies

Random-effects models are central to meta-analysis, yet the between-study variance is often underestimated when the number of studies is small. In such settings, confidence intervals become unduly narrow and fail to attain the nominal coverage probability. Although several small-sample corrections, including the Bartlett correction, have been developed under the normal-normal model, corresponding methodology for generalized linear mixed models (GLMMs) remains limited. This study proposes a unified framework for random-effects meta-analysis within the GLMM that relies exclusively on aggregate data and accommodates outcomes that follow any distribution in the exponential family, including the binomial, Poisson, and gamma distributions. To improve interval estimation with few studies, we develop a profile likelihood method with a simplified Bartlett correction (PLSBC), which refines the chi-squared approximation of the profile likelihood ratio statistic without requiring higher-order derivatives. We show theoretically that the proposed estimators preserve the consistency and asymptotic normality of the maximum likelihood estimators. Simulation studies demonstrate that the PLSBC yields nearly unbiased estimates and maintains nominal coverage across a variety of outcome types. Applications to three published meta-analyses with binomial, Poisson, and gamma outcomes indicate that the proposed approach provides robust and interpretable inference with few studies. The PLSBC therefore offers a practical and broadly applicable framework for random-effects meta-analysis when the number of studies is limited.

stat.ME↗

arXiv2025

Sample size re-estimation in blinded hybrid-control design using inverse probability weighting

With the increasing availability of data from historical studies and real-world data sources, hybrid control designs that incorporate external data into the evaluation of current studies are being increasingly adopted. In these designs, it is necessary to pre-specify during the planning phase the extent to which information will be borrowed from historical control data. However, if substantial differences in baseline covariate distributions between the current and historical studies are identified at the final analysis, the amount of effective borrowing may be limited, potentially resulting in lower actual power than originally targeted. In this paper, we propose two sample size re-estimation strategies that can be applied during the course of the blinded current study. Both strategies utilize inverse probability weighting (IPW) based on the probability of assignment to either the current or historical study. When large discrepancies in baseline covariates are detected, the proposed strategies adjust the sample size upward to prevent a loss of statistical power. The performance of the proposed strategies is evaluated through simulation studies, and their practical implementation is demonstrated using a case study based on two actual randomized clinical studies.

stat.ME↗

arXiv2025

Integrate Meta-analysis into Specific Study (InMASS) for Estimating Conditional Average Treatment Effect

Randomized controlled trials are the standard method for estimating causal effects, ensuring sufficient statistical power and confidence through adequate sample sizes. However, achieving such sample sizes is often challenging. This study proposes a novel method for estimating the average treatment effect (ATE) in a target population by integrating and reconstructing information from previous trials using only summary statistics of outcomes and covariates through meta-analysis. The proposed approach combines meta-analysis, transfer learning, and weighted regression. Unlike existing methods that estimate the ATE based on the distribution of source trials, our method directly estimates the ATE for the target population. The proposed method requires only the means and variances of outcomes and covariates from the source trials and is theoretically valid under the covariate shift assumption, regardless of the covariate distribution in the source trials. Simulations and real-data analyses demonstrate that the proposed method yields a consistent estimator and achieves higher statistical power than the estimator derived solely from the target trial.

stat.ME↗

arXiv2024

Moment-based Random-effects Meta-analysis Equipped with Huber's M-Estimation

Meta-analyses are commonly used to provide solid evidence across numerous studies. Traditional moment methods, such as the DerSimonian-Laird method, remain popular in spite of the availability of more accurate alternatives. While moment estimators are simple and intuitive, they are known to underestimate the variance of the overall treatment effect, particularly when the number of studies is small. This underestimation can lead to excessively narrow confidence intervals that do not meet the nominal confidence level, potentially resulting in misleading conclusions. In this study, we improve traditional moment-based meta-analysis methods by incorporating Huber's M-estimation to more accurately capture the distributional characteristics of between-study variance. Our approach enables conservative parameter estimation, even when almost all existing methods lead to underestimation of between-study variance under a small number of studies. Additionally, by deriving the simultaneous distribution of overall treatment effect and between-study variance, we propose facilitating a visual exploration of the relationship between these two quantities. Our method provides more reliable estimators for the overall treatment effect and between-study variance, particularly in situations with few studies. Using simulations and real data analysis, we demonstrate that our approach always yields more conservative results compared to traditional moment methods, and ensures more accurate confidence intervals in meta-analyses.

stat.ME↗

arXiv2024

Bayesian Parametric Methods for Deriving Distribution of Restricted Mean Survival Time

We propose a Bayesian method for deriving the distribution of restricted mean survival time (RMST) using posterior samples, which accounts for covariates and heterogeneity among clusters based on a parametric model for survival time. We derive an explicit RMST equation by devising an integral of the survival function, allowing for the calculation of not only the mean and credible interval but also the mode, median, and probability of exceeding a certain value. Additionally, We propose two methods: one using random effects to account for heterogeneity among clusters and another utilizing frailty. We developed custom Stan code for the exponential, Weibull, log-normal frailty, and log-logistic models, as they cannot be processed using the brm functions in R. We evaluate our proposed methods through computer simulations and analyze real data from the eight Empowered Action Group states in India to confirm consistent results across states after adjusting for cluster differences. In conclusion, we derived explicit RMST formulas for parametric models and their distributions, enabling the calculation of the mean, median, mode, and credible interval. Our simulations confirmed the robustness of the proposed methods, and using the shrinkage effect allowed for more accurate results for each cluster.

stat.ME↗

arXiv2024

Random Effect Restricted Mean Survival Time Model

The restricted mean survival time (RMST) model has been garnering attention as a way to provide a clinically intuitive measure: the mean survival time. RMST models, which use methods based on pseudo time-to-event values and inverse probability censoring weighting, can adjust covariates. However, no approach has yet been introduced that considers random effects for clusters. In this paper, we propose a new random-effect RMST. We present two methods of analysis that consider variable effects by i) using a generalized mixed model with pseudo-values and ii) integrating the estimated results from the inverse probability censoring weighting estimating equations for each cluster. We evaluate our proposed methods through computer simulations. In addition, we analyze the effect of a mother's age at birth on under-five deaths in India using states as clusters.

stat.ME↗

arXiv2023

Adjusting confidence intervals under covariate-adaptive randomization in non-inferiority and equivalence trials

Regulatory authorities guide the use of permutation tests or randomization tests so as not to increase the type-I error rate when applying covariate-adaptive randomization in randomized clinical trials. For non-inferiority and equivalence trials, this paper derives adjusted confidence intervals using permutation and randomization methods, thus controlling the type-I error to be much closer to the pre-specified nominal significance level. We consider three variable types for the outcome of interest, namely normal, binary, and time-to-event variables for the adjusted confidence intervals. For normal variables, we show that the type-I error for the adjusted confidence interval holds the nominal significance level. However, we highlight a unique theoretical challenge for non-inferiority and equivalence trials: binary and time-to-event variables may not hold the nominal significance level when the model parameters are estimated by models that diverge from the data-generating model under the null hypothesis. To clarify these features, we present simulation results and evaluate the performance of the adjusted confidence intervals.

stat.AP↗

arXiv2022

Comparison of Baseline Covariate Adjustment Methods for Restricted Mean Survival Time

The restricted mean survival time is a clinically easy-to-interpret measure that does not require any assumption of proportional hazards. We focus on two ways to directly model the survival time and adjust the covariates. One is to calculate the pseudo-survival time for each subject using leave-one-out, and then perform a model analysis using all pseudo-values to adjust for covariates. The pseudo-survival time is used to reflect information of censored subjects in the model analysis. The other method adjusts for covariates using subjects for whom the time-to-event was observed while adjusting for the censored subjects using the inverse probability of censoring weighting (IPCW). This paper evaluates the performance of these two methods in terms of the power to detect group differences through a simple example dataset and computer simulations. The simple example illustrates the intuitive behavior of the two methods. With the method using pseudo-survival times, it is difficult to interpret the pseudo-values. We confirm that the pseudo-survival times are different from the actual data obtained in a primary biliary cholangitis clinical trial because of the many censored data. In the simulations, the method using IPCW is found to be more powerful. Even in the case of group differences with respect to the censor incidence rates and covariates, the method using IPCW maintains a nominal significance level for the type-1 error rate. We conclude that the IPCW method should be used to estimate the restricted mean survival time when adjusting the covariates.

stat.ME↗