arXiv subjects

Sally W. Thurston

Publications and source records attributed to Sally W. Thurston.

7 recordsLinked to original sources

arXiv2026

Inference for relative sparsity

In healthcare, there is much interest in estimating policies, or mappings from covariates to treatment decisions. Recently, there is also interest in constraining these estimated policies to the standard of care, which generated the observed data. A relative sparsity penalty was proposed to derive policies that have sparse, explainable differences from the standard of care, facilitating justification of the new policy. However, the developers of this penalty only considered estimation, not inference. Here, we develop inference for the relative sparsity objective function, because characterizing uncertainty is crucial to applications in medicine. Further, in the relative sparsity work, the authors only considered the single-stage decision case; here, we consider the more general, multi-stage case. Inference is difficult, because the relative sparsity objective depends on the unpenalized value function, which is unstable and has infinite estimands in the binary action case. Further, one must deal with a non-differentiable penalty. To tackle these issues, we nest a weighted Trust Region Policy Optimization function within a relative sparsity objective, implement an adaptive relative sparsity penalty, and propose a sample-splitting framework for post-selection inference. We study the asymptotic behavior of our proposed approaches, perform extensive simulations, and analyze a real, electronic health record dataset.

stat.ME↗

arXiv2025

The Traceplot Thickens: Developing All-Purpose Convergence Diagnostics for any Markov Chain Monte Carlo Algorithm

Markov Chain Monte Carlo (MCMC) algorithms are frequently used to perform inference under a Bayesian modeling framework. Convergence diagnostics, such as traceplots, the Gelman-Rubin potential scale reduction factor, and effective sample size, are used to visualize and monitor how well the sampler has explored the parameter space and the mixing of multiple chains. However, these classic diagnostics can be undefined or ineffective when the sample space of the algorithm varies in dimension or has a large number of discrete parameters. In this article, we develop a novel approach to produce convergence diagnostics in these difficult scenarios by mapping the original sample space to the real-line and then evaluating the convergence diagnostics on the mapped values. The effectiveness of our method is demonstrated on a MCMC algorithm sampling from a Dirichlet process mixture model. The proposed diagnostics are also used to evaluate the performance of a Bayesian kernel machine regression model for estimating the health effect of multi-pollutant mixtures in the Study of Environment, Lifestyle, and Fibroids. Based on diagnostics for the latter dataset, we then explain how we modify the MCMC sampler to improve convergence.

stat.CO↗

arXiv2024

Optimality-based reward learning with applications to toxicology

In toxicology research, experiments are often conducted to determine the effect of toxicant exposure on the behavior of mice, where mice are randomized to receive the toxicant or not. In particular, in fixed interval experiments, one provides a mouse reinforcers (e.g., a food pellet), contingent upon some action taken by the mouse (e.g., a press of a lever), but the reinforcers are only provided after fixed time intervals. Often, to analyze fixed interval experiments, one specifies and then estimates the conditional state-action distribution (e.g., using an ANOVA). This existing approach, which in the reinforcement learning framework would be called modeling the mouse's "behavioral policy," is sensitive to misspecification. It is likely that any model for the behavioral policy is misspecified; a mapping from a mouse's exposure to their actions can be highly complex. In this work, we avoid specifying the behavioral policy by instead learning the mouse's reward function. Specifying a reward function is as challenging as specifying a behavioral policy, but we propose a novel approach that incorporates knowledge of the optimal behavior, which is often known to the experimenter, to avoid specifying the reward function itself. In particular, we define the reward as a divergence of the mouse's actions from optimality, where the representations of the action and optimality can be arbitrarily complex. The parameters of the reward function then serve as a measure of the mouse's tolerance for divergence from optimality, which is a novel summary of the impact of the exposure. The parameter itself is scalar, and the proposed objective function is differentiable, allowing us to benefit from typical results on consistency of parametric estimators while making very few assumptions.

stat.ME↗

arXiv2023

Testing Sparsity Assumptions in Bayesian Networks

Bayesian network (BN) structure discovery algorithms typically either make assumptions about the sparsity of the true underlying network, or are limited by computational constraints to networks with a small number of variables. While these sparsity assumptions can take various forms, frequently the assumptions focus on an upper bound for the maximum in-degree of the underlying graph $\nabla_G$. Theorem 2 in Duttweiler et. al. (2023) demonstrates that the largest eigenvalue of the normalized inverse covariance matrix ($Ω$) of a linear BN is a lower bound for $\nabla_G$. Building on this result, this paper provides the asymptotic properties of, and a debiasing procedure for, the sample eigenvalues of $Ω$, leading to a hypothesis test that may be used to determine if the BN has max in-degree greater than 1. A linear BN structure discovery workflow is suggested in which the investigator uses this hypothesis test to aid in selecting an appropriate structure discovery algorithm. The hypothesis test performance is evaluated through simulations and the workflow is demonstrated on data from a human psoriasis study.

stat.ML↗

arXiv2023

Relative Sparsity for Medical Decision Problems

Existing statistical methods can estimate a policy, or a mapping from covariates to decisions, which can then instruct decision makers (e.g., whether to administer hypotension treatment based on covariates blood pressure and heart rate). There is great interest in using such data-driven policies in healthcare. However, it is often important to explain to the healthcare provider, and to the patient, how a new policy differs from the current standard of care. This end is facilitated if one can pinpoint the aspects of the policy (i.e., the parameters for blood pressure and heart rate) that change when moving from the standard of care to the new, suggested policy. To this end, we adapt ideas from Trust Region Policy Optimization (TRPO). In our work, however, unlike in TRPO, the difference between the suggested policy and standard of care is required to be sparse, aiding with interpretability. This yields ``relative sparsity," where, as a function of a tuning parameter, $λ$, we can approximately control the number of parameters in our suggested policy that differ from their counterparts in the standard of care (e.g., heart rate only). We propose a criterion for selecting $λ$, perform simulations, and illustrate our method with a real, observational healthcare dataset, deriving a policy that is easy to explain in the context of the current standard of care. Our work promotes the adoption of data-driven decision aids, which have great potential to improve health outcomes.

stat.ME↗

arXiv2022

Spectral Bayesian Network Theory

A Bayesian Network (BN) is a probabilistic model that represents a set of variables using a directed acyclic graph (DAG). Current algorithms for learning BN structures from data focus on estimating the edges of a specific DAG, and often lead to many `likely' network structures. In this paper, we lay the groundwork for an approach that focuses on learning global properties of the DAG rather than exact edges. This is done by defining the structural hypergraph of a BN, which is shown to be related to the inverse-covariance matrix of the network. Spectral bounds are derived for the normalized inverse-covariance matrix, which are shown to be closely related to the maximum indegree of the associated BN.

math.CO↗

arXiv2021

Selection of inverse gamma and half-t priors for hierarchical models: sensitivity and recommendations

While the importance of prior selection is well understood, establishing guidelines for selecting priors in hierarchical models has remained an active, and sometimes contentious, area of Bayesian methodology research. Choices of hyperparameters for individual families of priors are often discussed in the literature, but rarely are different families of priors compared under similar models and hyperparameters. Using simulated data, we evaluate the performance of inverse gamma and half-$t$ priors for estimating the standard deviation of random effects in three hierarchical models: the 8-schools model, a random intercepts longitudinal model, and a simple multiple outcomes model. We compare the performance of the two prior families using a range of prior hyperparameters, some of which have been suggested in the literature, and others that allow for a direct comparison of pairs of half-$t$ and inverse-gamma priors. Estimation of very small values of the random effect standard deviation led to convergence issues especially for the half-$t$ priors. For most settings, we found that the posterior distribution of the standard deviation had smaller bias under half-$t$ priors than under their inverse-gamma counterparts. Inverse gamma priors generally gave similar coverage but had smaller interval lengths than their half-$t$ prior counterparts. Our results for these two prior families will inform prior specification for hierarchical models, allowing practitioners to better align their priors with their respective models and goals.

stat.ME↗