arXiv subjects

Qixuan Chen

Publications and source records attributed to Qixuan Chen.

9 recordsLinked to original sources

arXiv2026

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become increasingly complex and existing probabilistic programming systems remain limited in model support, extensibility, and composability. We introduce \textbf{AI4BayesCode}, an extensible LLM-driven system that translates natural-language Bayesian model descriptions into runnable, validated MCMC samplers. To improve reliability, AI4BayesCode adopts a modular design that decomposes models into modular sampling blocks and maps each block to a built-in sampling component, reducing the need to implement complex sampling algorithms from scratch. Reliability is further improved through pre-generation validation of model specifications and post-generation validation of generated sampler code. AI4BayesCode also introduces a novel recursively stateful coding paradigm for MCMC, allowing modular sampling components, potentially developed by different contributors, to be composed coherently within larger MCMC procedures. We develop a benchmark suite to evaluate AI4BayesCode for sampler-generation. Experiments show that AI4BayesCode can implement a wide range of Bayesian models from natural-language descriptions alone. As an open-ended system, its capability can continue to expand with improvements in the underlying AI agent and the addition of new built-in blocks. The software is available at https://ai4bayescode.com/.

stat.CO↗

arXiv2026

Improving Survey Inference in Two-phase Designs Using Bayesian Machine Learning

The two-phase sampling design is a cost-effective strategy widely used in public health research. Analyzing the Phase II sample often involves creating subsample-specific weights. However, these weights can be highly variable, leading to unstable weighted analyses. Alternatively, the rich data collected during the first phase can be leveraged to improve survey inference for the Phase II sample. In this paper, we propose a Bayesian tree-based multiple imputation (MI) approach for estimating population means using the Phase II sample, where the parent survey was conducted using a complex survey design. The design features of the parent survey, such as strata and clusters, are incorporated into the tree-based imputation models. Through simulations, we demonstrate that the tree-based MI method outperforms traditional weighted estimators, yielding smaller bias, lower root mean squared error, and narrower 95% confidence intervals, with coverage rates closer to the nominal level. Furthermore, we show that Rubin's variance estimation method provides valid statistical inference for population mean estimation in our setting. We illustrate the application of the proposed tree-based MI method using data from a cellphone survey on COVID-19 vaccination in Uganda, which represents a subcohort sample drawn from the 2020 Uganda Population-based HIV Impact Assessment Survey.

stat.ME↗

arXiv2026

When Bayes goes bad: Weakly-regularized covariate adjustment leads to a biased estimate of prevalence

When estimating population prevalence from a non-random sample, it is important to adjust for differences between sample and population. However, adjustment for multiple factors requires analysis that can be difficult to understand and validate. In this manuscript, we explore an unexpected downward trend of estimates when covariates are added sequentially to a Bayesian hierarchical model for the estimation of the prevalence of SARS-CoV-2 specific antibodies in an Australian city in late 2020. We compare our data analysis to results from a simulation study to understand four potential contributors to this effect: (i) correction for differences between sample and population, (ii) rare-events bias in logistic regression, (iii) inclusion of the uncertainty of test sensitivity and specificity in a multilevel model, and (iv) increasing model dimensionality. We find that weak prior distributions on the logistic regression coefficients lead to a systematic increase in the amount of partial pooling across adjustment cells-the prior becomes stronger as model dimensionality increases-which in turn feeds through to the estimated assay specificity, which then feeds back to the model and results in lowering the estimated prevalence. Our paper contributes three elements: (i) immediate and longer-term recommendations for using these types of models, (ii) simulation studies to explore the impact of the contributors to this effect, and (iii) a worked example of investigation of unexpected results in a model with multiple adjustment factors.

stat.ME↗

arXiv2026

Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge

Recent advances in Large Language Models (LLMs) have incentivized the development of LLM-as-a-judge, an application of LLMs where they are used as judges to decide the quality of a certain piece of text given a certain context. However, previous studies have demonstrated that LLM-as-a-judge can be biased towards different aspects of the judged texts, which often do not align with human preference. One of the identified biases is language bias, which indicates that the decision of LLM-as-a-judge can differ based on the language of the judged texts. In this paper, we study two types of language bias in pairwise LLM-as-a-judge: (1) performance disparity between languages when the judge is prompted to compare options from the same language, and (2) bias towards options written in major languages when the judge is prompted to compare options of two different languages. We find that for same-language judging, there exist significant performance disparities across language families, with European languages consistently outperforming African languages, and this bias is more pronounced in culturally-related subjects. For inter-language judging, we observe that most models favor English answers, and that this preference is influenced more by answer language than question language. Finally, we investigate whether language bias is in fact caused by low-perplexity bias, a previously identified bias of LLM-as-a-judge, and we find that while perplexity is slightly correlated with language bias, language bias cannot be fully explained by perplexity only.

cs.CL↗

arXiv2025

Bayesian MI-LASSO for Variable Selection on Multiply-Imputed Data

Multiple imputation is widely used for handling missing data in real-world applications. For variable selection on multiply-imputed datasets, however, if selection is performed on each imputed dataset separately, it can result in different sets of selected variables across datasets. MI-LASSO, one of the most commonly used approaches to this problem, regards the same variable across all separate imputed datasets as a group variable and exploits the group LASSO to yield a consistent variable selection across all the multiply-imputed datasets. In this paper, we extend MI-LASSO to a Bayesian framework and propose four Bayesian MI-LASSO models for variable selection on multiply-imputed data, including three shrinkage prior-based and one Spike-Slab prior-based methods. To further support robust variable selection, we develop a four-step projection predictive variable selection procedure that avoids ad hoc thresholding and facilitates valid post-selection inference. Simulation studies showed that the Bayesian MI-LASSO outperformed MI-LASSO and other alternative approaches, achieving higher specificity and lower mean squared error across a range of settings. We further demonstrated these methods via a case study using a multiply-imputed dataset from the University of Michigan Dioxin Exposure Study. The R package BMIselect is available on CRAN.

stat.ME↗

arXiv2022

Using leave-one-out cross-validation (LOO) in a multilevel regression and poststratification (MRP) workflow: A cautionary tale

In recent decades, multilevel regression and poststratification (MRP) has surged in popularity for population inference. However, the validity of the estimates can depend on details of the model, and there is currently little research on validation. We explore how leave-one-out cross-validation (LOO) can be used to compare Bayesian models for MRP. We investigate two approximate calculations of LOO, the Pareto smoothed importance sampling (PSIS-LOO) and a survey-weighted alternative (WTD-PSIS-LOO). Using two simulation designs, we examine how accurately these two criteria recover the correct ordering of model goodness at predicting population and small area level estimands. Focusing first on variable selection, we find that neither PSIS-LOO nor WTD-PSIS-LOO correctly recovers the models' order for an MRP population estimand (although both criteria correctly identify the best and worst model). When considering small-area estimation, the best model differs for different small areas, highlighting the complexity of MRP validation. When considering different priors, the models' order seems slightly better at smaller area levels. These findings suggest that while not terrible, PSIS-LOO-based ranking techniques may not be suitable to evaluate MRP as a method. We suggest this is due to the aggregation stage of MRP, where individual-level prediction errors average out. These results show that in practice, PSIS-LOO-based model validation tools need to be used with caution and might not convey the full story when validating MRP as a method.

stat.ME↗

arXiv2021

Bivariate Hierarchical Bayesian Model for Combining Summary Measures and their Uncertainties from Multiple Sources

It is often of interest to combine available estimates of a similar quantity from multiple data sources. When the corresponding variances of each estimate are also available, a model should take into account the uncertainty of the estimates themselves as well as the uncertainty in the estimation of variances. In addition, if there exists a strong association between estimates and their variances, the correlation between these two quantities should also be considered. In this paper, we propose a bivariate hierarchical Bayesian model that jointly models the estimates and their estimated variances assuming a correlation between these two measures. We conduct simulations to explore the performance of the proposed bivariate Bayesian model and compare it to other commonly used methods under different correlation scenarios. The proposed bivariate Bayesian model has a wide range of applications. We illustrate its application in three very different areas: PET brain imaging studies, meta-analysis, and small area estimation.

stat.ME↗

arXiv2021

Inference from Non-Random Samples Using Bayesian Machine Learning

We consider inference from non-random samples in data-rich settings where high-dimensional auxiliary information is available both in the sample and the target population, with survey inference being a special case. We propose a regularized prediction approach that predicts the outcomes in the population using a large number of auxiliary variables such that the ignorability assumption is reasonable while the Bayesian framework is straightforward for quantification of uncertainty. Besides the auxiliary variables, inspired by Little & An (2004), we also extend the approach by estimating the propensity score for a unit to be included in the sample and also including it as a predictor in the machine learning models. We show through simulation studies that the regularized predictions using soft Bayesian additive regression trees yield valid inference for the population means and coverage rates close to the nominal levels. We demonstrate the application of the proposed methods using two different real data applications, one in a survey and one in an epidemiology study.

stat.ME↗

arXiv2021

Modeling Heterogeneity and Missing Data of Multiple Longitudinal Outcomes in Electronic Health Records

In electronic health records (EHRs), latent subgroups of patients may exhibit distinctive patterning in their longitudinal health trajectories. For such data, growth mixture models (GMMs) enable classifying patients into different latent classes based on individual trajectories and hypothesized risk factors. However, the application of GMMs is hindered by the special missing data problem in EHRs, which manifests two patient-led missing data processes: the visit process and the response process for an EHR variable conditional on a patient visiting the clinic. If either process is associated with the process generating the longitudinal outcomes, then valid inferences require accounting for a nonignorable missing data mechanism. We propose a Bayesian shared parameter model that links GMMs of multiple longitudinal health outcomes, the visit process, and the response process of each outcome given a visit using a discrete latent class variable. Our focus is on multiple longitudinal health outcomes for which there can be a clinically prescribed visit schedule. We demonstrate our model in EHR measurements on early childhood weight and height z-scores. Using data simulations, we illustrate the statistical properties of our method with respect to subgroup-specific or marginal inferences. We built the R package EHRMiss for model fitting, selection, and checking.

stat.ME↗