arXiv subjects

Daniel L. Gillen

Publications and source records attributed to Daniel L. Gillen.

10 recordsLinked to original sources

arXiv2024

Choosing the Right Approach at the Right Time: A Comparative Analysis of Causal Effect Estimation using Confounder Adjustment and Instrumental Variables

In observational studies, potential unobserved confounding is a major barrier in isolating the average causal effect (ACE). In these scenarios, two main approaches are often used: confounder adjustment for causality (CAC) and instrumental variable analysis for causation (IVAC). Nevertheless, both are subject to untestable assumptions and, therefore, it may be unclear which assumption violation scenarios one method is superior in terms of mitigating inconsistency for the ACE. Although general guidelines exist, direct theoretical comparisons of the trade-offs between CAC and the IVAC assumptions are limited. Using ordinary least squares (OLS) for CAC and two-stage least squares (2SLS) for IVAC, we analytically compare the relative inconsistency for the ACE of each approach under a variety of assumption violation scenarios and discuss rules of thumb for practice. Additionally, a sensitivity framework is proposed to guide analysts in determining which approach may result in less inconsistency for estimating the ACE with a given dataset. We demonstrate our findings both through simulation and by revisiting Card's analysis of the effect of educational attainment on earnings, which has been the subject of previous discussion on instrument validity. The implications of our findings on causal inference practice are discussed, providing guidance for analysts to judge whether CAC or IVAC may be more appropriate for a given situation.

stat.ME↗

arXiv2024

Non-parametric Replication of Instrumental Variable Estimates Across Studies

Replicating causal estimates across different cohorts is crucial for increasing the integrity of epidemiological studies. However, strong assumptions regarding unmeasured confounding and effect modification often hinder this goal. By employing an instrumental variable (IV) approach and targeting the local average treatment effect (LATE), these assumptions can be relaxed to some degree; however, little work has addressed the replicability of IV estimates. In this paper, we propose a novel survey weighted LATE (SWLATE) estimator that incorporates unknown sampling weights and leverages machine learning for flexible modeling of nuisance functions, including the weights. Our approach, based on influence function theory and cross-fitting, provides a doubly-robust and efficient framework for valid inference, aligned with the growing "double machine learning" literature. We further extend our method to provide bounds on a target population ATE. The effectiveness of our approach, particularly in non-linear settings, is demonstrated through simulations and applied to a Mendelian randomization analysis of the relationship between triglycerides and cognitive decline.

stat.ME↗

arXiv2023

Frameworks for Estimating Causal Effects in Observational Settings: Comparing Confounder Adjustment and Instrumental Variables

To estimate causal effects, analysts performing observational studies in health settings utilize several strategies to mitigate bias due to confounding by indication. There are two broad classes of approaches for these purposes: use of confounders and instrumental variables (IVs). Because such approaches are largely characterized by untestable assumptions, analysts must operate under an indefinite paradigm that these methods will work imperfectly. In this tutorial, we formalize a set of general principles and heuristics for estimating causal effects in the two approaches when the assumptions are potentially violated. This crucially requires reframing the process of observational studies as hypothesizing potential scenarios where the estimates from one approach are less inconsistent than the other. While most of our discussion of methodology centers around the linear setting, we touch upon complexities in non-linear settings and flexible procedures such as target minimum loss-based estimation (TMLE) and double machine learning (DML). To demonstrate the application of our principles, we investigate the use of donepezil off-label for mild cognitive impairment (MCI). We compare and contrast results from confounder and IV methods, traditional and flexible, within our analysis and to a similar observational study and clinical trial.

stat.ME↗

arXiv2021

Adjustment for Biased Sampling Using NHANES Derived Propensity Weights

The Consent-to-Contact (C2C) registry at the University of California, Irvine collects data from community participants to aid in the recruitment to clinical research studies. Self-selection into the C2C likely leads to bias due in part to enrollees having more years of education relative to the US general population. Salazar et al. (2020) recently used the C2C to examine associations of race/ethnicity with participant willingness to be contacted about research studies. To address questions about generalizability of estimated associations we estimate propensity for self-selection into the convenience sample weights using data from the National Health and Nutrition Examination Survey (NHANES). We create a combined dataset of C2C and NHANES subjects and compare different approaches (logistic regression, covariate balancing propensity score, entropy balancing, and random forest) for estimating the probability of membership in C2C relative to NHANES. We propose methods to estimate the variance of parameter estimates that account for uncertainty that arises from estimating propensity weights. Simulation studies explore the impact of propensity weight estimation on uncertainty. We demonstrate the approach by repeating the analysis by Salazar et al. with the deduced propensity weights for the C2C subjects and contrast the results of the two analyses. This method can be implemented using our estweight package in R available on GitHub.

stat.ME↗

arXiv2021

A Measurement of In-Betweenness and Inference Based on Shape Theories

We propose a statistical framework to investigate whether a given subpopulation lies between two other subpopulations in a multivariate feature space. This methodology is motivated by a biological question from a collaborator: Is a newly discovered cell type between two known types in several given features? We propose two in-betweenness indices (IBI) to quantify the in-betweenness exhibited by a random triangle formed by the summary statistics of the three subpopulations. Statistical inference methods are provided for triangle shape and IBI metrics. The application of our methods is demonstrated in three examples: the classic Iris data set, a study of risk of relapse across three breast cancer subtypes, and the motivating neuronal cell data with measured electrophysiological features.

stat.ME↗

arXiv2020

Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning

Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds. In this paper we explore how this affects hyperparameter optimization when the goal is to find hyperparameter settings that perform well across random seeds. In particular, we benchmark whether it is better to explore a large quantity of hyperparameter settings via pruning of bad performers, or if it is better to aim for quality of collected results by using repetitions. For this we consider the Successive Halving, Random Search, and Bayesian Optimization algorithms, the latter two with and without repetitions. We apply these to tuning the PPO2 algorithm on the Cartpole balancing task and the Inverted Pendulum Swing-up task. We demonstrate that pruning may negatively affect the optimization and that repeated sampling does not help in finding hyperparameter settings that perform better across random seeds. From our experiments we conclude that Bayesian optimization with a noise robust acquisition function is the best choice for hyperparameter optimization in reinforcement learning tasks.

cs.LG↗

arXiv2018

Assessing Health Care Interventions via an Interrupted Time Series Model: Study Power and Design Considerations

The delivery and assessment of quality health care is complex with many interacting and interdependent components. In terms of research design and statistical analysis, this complexity and interdependency makes it difficult to assess the true impact of interventions designed to improve patient health care outcomes. Interrupted time series (ITS) is a quasi-experimental design developed for inferring the effectiveness of a health policy intervention while accounting for temporal dependence within a single system or unit. Current standardized ITS methods do not simultaneously analyze data for several units, nor are there methods to test for the existence of a change point and to assess statistical power for study planning purposes in this context. To address this limitation we propose the `Robust Multiple ITS' (R-MITS) model, appropriate for multi-unit ITS data, that allows for inference regarding the estimation of a global change point across units in the presence of a potentially lagged (or anticipatory) treatment effect. Under the R-MITS model, one can formally test for the existence of a change point and estimate the time delay between the formal intervention implementation and the over-all-unit intervention effect. We conducted empirical simulation studies to assess the type one error rate of the testing procedure, power for detecting specified change-point alternatives, and accuracy of the proposed estimating methodology. R-MITS is illustrated by analyzing patient satisfaction data from a hospital that implemented and evaluated a new care delivery model in multiple units.

stat.ME↗

arXiv2018

A Flexible Joint Longitudinal-Survival Modeling Framework for Incorporating Multiple Longitudinal Biomarkers

We are interested in survival analysis of hemodialysis patients for whom several biomarkers are recorded over time. Motivated by this challenging problem, we propose a general framework for multivariate joint longitudinal-survival modeling that can be used to examine the association between several longitudinally recorded covariates and a time-to-event endpoint. Our method allows for simultaneous modeling of longitudinal covariates by taking their correlation into account. This leads to a more efficient method for modeling their trajectories over time, and hence, it can better capture their relationship to the survival outcomes.

stat.ME↗

arXiv2018

A Flexible Joint Longitudinal-Survival Model for Analysis of End-Stage Renal Disease Data

We propose a flexible joint longitudinal-survival framework to examine the association between longitudinally collected biomarkers and a time-to-event endpoint. More specifically, we use our method for analyzing the survival outcome of end-stage renal disease patients with time-varying serum albumin measurements. Our proposed method is robust to common parametric assumptions in that it avoids explicit distributional assumptions on longitudinal measures and allows for subject-specific baseline hazard in the survival component. Fully joint estimation is performed to account for the uncertainty in the estimated longitudinal biomarkers included in the survival model.

stat.AP↗

arXiv2018

A Bayesian Framework for Non-Collapsible Models

In this paper, we discuss the non-collapsibility concept and propose a new approach based on Dirichlet process mixtures to estimate the conditional effect of covariates in non-collapsible models. Using synthetic data, we evaluate the performance of our proposed method and examine its sensitivity under different settings. We also apply our method to real data on access failure among hemodialysis patients.

stat.ME↗