arXiv subjects

Ethan M. Alt

Publications and source records attributed to Ethan M. Alt.

8 recordsLinked to original sources

arXiv2026

NP-LEAP: Nonparametric Latent Exchangeability Prior for Model-Lean Borrowing from Historical Data

Bayesian dynamic borrowing (BDB) methods leverage historical data to reduce treatment effect uncertainty, yet existing approaches rely on parametric outcome models susceptible to misspecification. We propose the nonparametric latent exchangeability prior (NP-LEAP), an outcome-agnostic, assumption-lean framework to borrow information from historical data. The NP-LEAP performs individual-level exchangeability assessment, inducing Bayesian model averaging over all possible partitions of the historical data into exchangeable and nonexchangeable subsets. Although applicable to a variety of data types with choice of appropriate kernel, the NP-LEAP is particularly well-suited for studies with time-to-event outcomes, where parametric BDB is potentially triply misspecified - imposing a parametric baseline hazard, the proportional hazards structure, and blanket exchangeability. We establish posterior consistency under mild regularity conditions. Simulation studies demonstrate favorable operating characteristics relative to parametric borrowing methods and nonborrowing semiparametric frequentist methods. We illustrate the method by augmenting the control arm in a randomized trial of patients with non-small cell lung cancer.

stat.ME↗

arXiv2025

Cure Rate Joint Model for Time-to-Event Data and Longitudinal Tumor Burden with Potential Change Points

In non-small cell lung cancer (NSCLC) clinical trials, tumor burden (TB) is a key longitudinal biomarker for assessing treatment effects. Typically, standard-of-care (SOC) therapies and some novel interventions initially decrease TB; however, many patients subsequently experience an increase-indicating disease progression-while others show a continuous decline. In patients with an eventual TB increase, the change point marks the onset of progression and must occur before the time of the event. To capture these distinct dynamics, we propose a novel joint model that integrates time-to-event and longitudinal TB data, classifying patients into a change-point group or a stable group. For the change-point group, our approach flexibly estimates an individualized change point by leveraging time-to-event information. We use a Monte Carlo Expectation-Maximization (MCEM) algorithm for efficient parameter estimation. Simulation studies demonstrate that our model outperforms traditional approaches by accurately capturing diverse disease progression patterns and handling censoring complexities, leading to robust marginal TB outcome estimates. When applied to a Phase 3 NSCLC trial comparing cemiplimab monotherapy to SOC, the treatment group shows prolonged TB reduction and consistently lower TB over time, highlighting the clinical utility of our approach. The implementation code is publicly available on https://github.com/quyixiang/JoCuR.

stat.ME↗

arXiv2025

hdbayes: An R Package for Bayesian Analysis of Generalized Linear Models Using Historical Data

There has been increased interest in the use of historical data to formulate informative priors in regression models. While many such priors for incorporating historical data have been proposed, adoption is limited due to access to software. Where software does exist, the implementations between different methods could be vastly different, making comparisons between methods difficult. In this paper, we introduce the R package hdbayes, an implementation of the power prior, normalized power prior, Bayesian hierarchical model, robust meta-analytic prior, commensurate prior, and latent exchangeability prior for generalized linear models. The bulk of the package is written in the Stan programming language, with user-friendly R wrapper functions to call samplers.

stat.ME↗

arXiv2025

Improved computational efficiency and stability when imputing censored covariates: Analytic and numerical approaches

Imputation is a popular approach to handling censored, missing, and error-prone covariates -- all coarsened data types for which the true values are unknown. However, there are nuances to imputing these different data types based on the mechanism dominating the unobserved values and other available information. For example, in prospective studies, the time to a disease diagnosis will be incompletely observed if only some patients are diagnosed by the end of the follow-up. Some will be randomly right-censored, and patients' disease-free follow-up times must be incorporated into their imputed values. Assuming noninformative censoring, censored values are replaced with their conditional means, which are calculated by estimating the conditional survival function of the censored covariate and then integrating over it. Semiparametric approaches are common, which estimate the survival with a Cox model and then the integral with the trapezoidal rule. While these approaches offer robustness, they come at the cost of computational efficiency and stability in numerically approximating an improper integral. After modeling the survival function parametrically, we derive analytic solutions for conditional mean imputed values under many common distributions. We define stabilized calculations for other distributions. Parametric imputation using various distributions and calculations is implemented in the R package, speedyCMI.

stat.ME↗

arXiv2024

Jointly modeling time-to-event and longitudinal data with individual-specific change points: a case study in modeling tumor burden

In oncology clinical trials, tumor burden (TB) stands as a crucial longitudinal biomarker, reflecting the toll a tumor takes on a patient's prognosis. With certain treatments, the disease's natural progression shows the tumor burden initially receding before rising once more. Biologically, the point of change may be different between individuals and must have occurred between the baseline measurement and progression time of the patient, implying a random effects model obeying a bound constraint. However, in practice, patients may drop out of the study due to progression or death, presenting a non-ignorable missing data problem. In this paper, we introduce a novel joint model that combines time-to-event data and longitudinal data, where the latter is parameterized by a random change point augmented by random pre-slope and post-slope dynamics. Importantly, the model is equipped to incorporate covariates across for the longitudinal and survival models, adding significant flexibility. Adopting a Bayesian approach, we propose an efficient Hamiltonian Monte Carlo algorithm for parameter inference. We demonstrate the superiority of our approach compared to a longitudinal-only model via simulations and apply our method to a data set in oncology.

stat.ME↗

arXiv2023

LEAP: The latent exchangeability prior for borrowing information from historical data

It is becoming increasingly popular to elicit informative priors on the basis of historical data. Popular existing priors, including the power prior, commensurate prior, and robust meta-analytic prior provide blanket discounting. Thus, if only a subset of participants in the historical data are exchangeable with the current data, these priors may not be appropriate. In order to combat this issue, propensity score (PS) approaches have been proposed. However, PS approaches are only concerned with the covariate distribution, whereas exchangeability is typically assessed with parameters pertaining to the outcome. In this paper, we introduce the latent exchangeability prior (LEAP), where observations in the historical data are classified into exchangeable and non-exchangeable groups. The LEAP discounts the historical data by identifying the most relevant subjects from the historical data. We compare our proposed approach against alternative approaches in simulations and present a case study using our proposed prior to augment a control arm in a phase 3 clinical trial in plaque psoriasis with an unbalanced randomization scheme.

stat.ME↗

arXiv2021

A hierarchical prior for generalized linear models based on predictions for the mean response

There has been increased interest in using prior information in statistical analyses. For example, in rare diseases, it can be difficult to establish treatment efficacy based solely on data from a prospective study due to low sample sizes. To overcome this issue, an informative prior for the treatment effect may be elicited. We develop a novel extension of the conjugate prior of Chen and Ibrahim (2003) that enables practitioners to elicit a prior prediction for the mean response for generalized linear models, treating the prediction as random. We refer to the hierarchical prior as the hierarchical prediction prior. For i.i.d. settings and the normal linear model, we derive cases for which the hyperprior is a conjugate prior. We also develop an extension of the HPP in situations where summary statistics from a previous study are available, drawing comparisons with the power prior. The HPP allows for discounting based on the quality of individual level predictions, having the potential to provide efficiency gains (e.g., lower MSE) where predictions are incompatible with the data. An efficient Markov chain Monte Carlo algorithm is developed. Applications illustrate that inferences under the HPP are more robust to prior-data conflict compared to selected non-hierarchical priors.

stat.ME↗

arXiv2020

Bayesian Multivariate Probability of Success Using Historical Data with Strict Control of Family-wise Error Rate

Given the cost and duration of phase III and phase IV clinical trials, the development of statistical methods for go/no-go decisions is vital. In this paper, we introduce a Bayesian methodology to compute the probability of success based on the current data of a treatment regimen for the multivariate linear model. Our approach utilizes a Bayesian seemingly unrelated regression model, which allows for multiple endpoints to be modeled jointly even if the covariates between the endpoints are different. Correlations between endpoints are explicitly modeled. This Bayesian joint modeling approach unifies single and multiple testing procedures under a single framework. We develop an approach to multiple testing that asymptotically guarantees strict family-wise error rate control, and is more powerful than frequentist approaches to multiplicity. The method effectively yields those of Ibrahim et al. and Chuang-Stein as special cases, and, to our knowledge, is the only method that allows for robust sample size determination for multiple endpoints and/or hypotheses and the only method that provides strict family-wise type I error control in the presence of multiplicity.

stat.ME↗