About

Alexander Franks is an Associate Professor in the Department of Statistics and Applied Probability at the University of California, Santa Barbara. His research spans several areas within statistics, including causal inference and sensitivity analysis, covariance estimation, missing data and measurement error, high-throughput applications in biology, Bayesian statistics, and sports analytics. He focuses on developing interpretable and flexible methods to assess sensitivity to untestable assumptions in causal inference and missing data problems. His recent work explores the intersection of multivariate analysis and causal inference, particularly causal inference with multiple concurrent treatments and multiple outcomes, as well as how dependencies can inform sensitivity analysis. Additionally, he investigates partial identification and sensitivity analysis within the Bayesian framework.

Research topics

• Biology
• Computational biology
• Computer Science
• Chemistry
• Biochemistry
• Neuroscience
• Data science
• Business
• Bioinformatics

Selected publications

• Abortion Bans and Maternal, Pregnancy-Related, and Pregnancy-Associated Mortality in 14 US States, 2016-2023: Estimated Impacts Amid Substantial Measurement Challenges.

  PubMed · 2026-06-01

  articleOpen access

  . 2026;116(6):819-828. https://doi.org/10.2105/AJPH.2026.308465).

  PublisherOA PDFDOI

• Methodological considerations for investigating the impact of abortion restrictions on outcomes using aggregate panel data

  American Journal of Epidemiology · 2026-02-12 · 1 citations

  article

  Dramatic changes in the US abortion policy landscape have led to growing interest in studying the health and social impacts of abortion bans. Many studies of population-level impacts necessarily rely on panel designs using aggregate state-level data to strengthen causal inference, yet such analyses risk pitfalls if they apply generic evaluation frameworks that overlook the complexity of the US abortion context and relevant outcomes. This commentary provides practical guidance for researchers engaged in panel studies of abortion policy, as well as for peer reviewers who may be less familiar with the methodological and substantive considerations in this area. Drawing from recent work, we highlight abortion-specific challenges that require attention, including time-varying confounding and violation of parallel trends, COVID-era disruptions, data suppression, spillover effects, and subgroup heterogeneity. We further recommend assessing sensitivity to including Texas, given its earlier implementation of abortion restrictions and potential outsized influence on results. Ultimately, we emphasize that rigorous evaluation of abortion policies requires thoughtful study design, context-specific considerations, and collaboration between methodologists and subject-matter experts.

  PublisherDOI

• Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap

  ArXiv.org · 2026-04-01

  articleOpen access

  Overlap, also known as positivity, is a key condition for causal treatment effect estimation. Many popular estimators suffer from high variance and become brittle when features differ strongly across treatment groups. This is especially challenging in high dimensions: the curse of dimensionality can make overlap implausible. To address this, we propose a class of feature representations called deconfounding scores, which preserve both identification and the target of estimation; the classical propensity and prognostic scores are two special cases. We characterize the problem of finding a representation with better overlap as minimizing an overlap divergence under a deconfounding score constraint. We then derive closed-form expressions for a class of deconfounding scores under a broad family of generalized linear models with Gaussian features and show that prognostic scores are overlap-optimal within this class. We conduct extensive experiments to assess this behavior empirically.

  PublisherOA PDF

• Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap

  arXiv (Cornell University) · 2026-04-01

  preprintOpen access

  Overlap, also known as positivity, is a key condition for causal treatment effect estimation. Many popular estimators suffer from high variance and become brittle when features differ strongly across treatment groups. This is especially challenging in high dimensions: the curse of dimensionality can make overlap implausible. To address this, we propose a class of feature representations called deconfounding scores, which preserve both identification and the target of estimation; the classical propensity and prognostic scores are two special cases. We characterize the problem of finding a representation with better overlap as minimizing an overlap divergence under a deconfounding score constraint. We then derive closed-form expressions for a class of deconfounding scores under a broad family of generalized linear models with Gaussian features and show that prognostic scores are overlap-optimal within this class. We conduct extensive experiments to assess this behavior empirically.

  PublisherDOI

• US Abortion Bans and Fertility

  JAMA · 2025-02-13 · 27 citations

  letterOpen access

  Importance: Abortion bans may lead to births among those who are unable to overcome barriers to abortion. The population-level effects of these policies, particularly their unequal impacts across subpopulations in the US, remain unclear. Objective: To assess heterogeneity in the association of abortion bans with changes in fertility in the US, within and across states. Design, Setting, and Participants: Drawing from birth certificate and US Census Bureau data from 2012 through 2023 for all 50 states and the District of Columbia, this study used a bayesian panel data model to evaluate state-by-subgroup-specific changes in fertility associated with complete or 6-week abortion bans in 14 US states. The average percent and absolute change in the fertility rate among females aged 15 through 44 years was estimated overall and by state, and within and across states by age, race and ethnicity, marital status, education, and insurance payer. Exposure: Complete or 6-week abortion ban. Main outcome and Measures: Fertility rate (births per 1000 reproductive-aged females) overall and by subgroups. Results: There were an estimated 1.01 (95% credible interval [CrI], 0.45-1.64) additional births above expectation per 1000 females aged 15 through 44 years (reproductive age) in states following adoption of abortion bans (60.55 observed vs 59.54 expected; 1.70% increase; 95% CrI, 0.75%-2.78%), equivalent to 22 180 excess births, with evidence of variation by state and subgroup. Estimated differences above expectation were largest for racially minoritized individuals (≈2.0%), unmarried individuals (1.79%), individuals younger than 35 years (≈2.0%), Medicaid beneficiaries (2.41%), and those without college degrees (high school diploma, 2.36%; some college, 1.58%), particularly in southern states. Differences in race and ethnicity and education across states explain most of the variability in the state-level association between abortion bans and fertility rates. Conclusion and Relevance: These findings provide evidence that fertility rates in states with abortion bans were higher than would have been expected in the absence of these policies, with the largest estimated differences among subpopulations experiencing the greatest structural disadvantages and in states with among the worst maternal and child health and well-being outcomes.

  PublisherOA PDFDOI

• KGR-SKATER: Spatially Clustered Kernel Graph Regression for Counting Processes

  SSRN Electronic Journal · 2025-01-01

  preprintOpen accessSenior author
  PublisherDOI

• US Abortion Bans and Infant Mortality

  JAMA · 2025-02-13 · 46 citations

  letterOpen access

  Importance: The impact of recent abortion bans on infant mortality is not fully understood. There is also limited evidence on how these bans may interact with long-standing racial and ethnic disparities in infant health. Objective: To examine the association of abortion bans with changes in infant mortality and to compare this association in racial and ethnic groups based on analyses within and across states. Design, Setting, and Participants: This population-based, serial, cross-sectional study used a bayesian panel model to examine infant mortality rates in 14 states that implemented complete or 6-week abortion bans and compared them with predictions of infant mortality rates based on pre-ban mortality rates and states without bans. Data included all live births and infant deaths from all 50 US states and the District of Columbia for 2012 through 2023. Models accounted for temporal trends and state-specific factors, with analyses stratified by race and ethnicity, timing of death, and cause of death. Exposure: Complete or 6-week abortion bans. Main Outcome and Measures: Infant mortality rate, analyzed overall and by subgroups. Results: The analysis found higher than expected infant mortality in states after adoption of abortion bans (observed vs expected, 6.26 vs 5.93 per 1000 live births; absolute increase, 0.33 [95% credible interval (CrI), 0.14-0.51]; relative increase, 5.60% [95% CrI, 2.43%-8.73%]). This resulted in an estimated 478 excess infant deaths in the 14 states with bans during the months affected by bans. The estimated increases were higher among non-Hispanic Black infants compared with other racial and ethnic groups, with 11.81 observed vs 10.66 expected infant deaths per 1000 live births, an absolute increase of 1.15 (95% CrI, 0.53-1.81) and relative increase of 10.98% (95% CrI, 4.87%-17.89%). The observed infant mortality rate due to congenital anomalies was 1.37 vs 1.24 expected (absolute increase, 0.13 [95% CrI, 0.04-0.21]; relative increase, 10.87% [95% CrI, 3.39%-18.08%]), while the rate not due to congenital anomalies was 4.89 observed vs 4.69 expected (absolute increase, 0.20 [95% CrI, 0.02-0.38]; relative increase, 4.23% [95% CrI, 0.49%-8.23%]). Texas had a dominant influence on the overall results and there were larger increases in southern vs nonsouthern states. Conclusions: US states that adopted abortion bans had higher than expected infant mortality after the bans took effect. The estimated relative increases in infant mortality were larger for deaths with congenital causes and among groups that had higher than average infant mortality rates at baseline, including Black infants and those in southern states.

  PublisherOA PDFDOI

• Principles of protein abundance regulation across single cells in a mammalian tissue

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-09-20 · 3 citations

  preprintOpen access

  Protein synthesis and clearance are major regulatory steps of gene expression, but their in vivo regulatory roles across the cells comprising complex tissues remains unexplored. Here, we systematically quantify protein synthesis and clearance across over 4,200 cells from a primary tissue. Through integration with single-cell transcriptomics, we report the first quantitative analysis of how individual cell types regulate their proteomes across the continuum of gene expression. Our analysis quantifies the relative contributions of RNA abundance, translation, and protein clearance to the abundance variation of thousands of proteins. These results reveal a putative organizing principle: The contributions of both translation and protein clearance are linearly dependent on the cell growth rate. Further, we find that some proteins are primarily regulated by one mechanism (RNA abundance, translation, or clearance) across all cell types while the dominant regulation of other proteins is cell-type specific. Age related changes in protein abundance are cell-type specific and correlated to changes in protein clearance. Our reliable multimodal measurements enabled quantifying and functionally interpreting molecular variation across single cells from the same cell type. The protein-protein correlations are substantially stronger than the mRNA-mRNA ones both for directly interacting proteins and for functional protein sets. This difference is mediated by protein clearance regulation. Further, the protein correlations allow identifying cell-type specific functional clusters. These clusters vary across cell types, revealing differences in metabolic processes coordination, partially regulated by protein degradation. Our approach reveals organizing principles determining the relative contributions of translation and protein clearance and provides a scalable framework for investigating protein regulation in mammalian tissues.

  PublisherOA PDFDOI

• Robust Statistical Approaches to Understanding the Causal Effect of Air Pollution Mixtures.

  PubMed · 2025-12-01

  articleOpen access

  INTRODUCTION: Most existing epidemiological evidence on the health effects of air pollution has focused on single-pollutant analyses, although recent research has increasingly emphasized estimating the effects of multiple exposures simultaneously. In this report, we used causal inference methodology to highlight four impediments to analyses with multiple exposures: (1) there is little information in the data to estimate effects typically of interest, (2) the effects of air pollution mixtures can be heterogeneous, (3) exposure assessment using an individual's home location can be problematic when daily mobility takes them to areas of different exposure levels, and (4) bias due to unmeasured confounding. The objectives of this report were to address these four concerns through the development of rigorous statistical methodology and to provide a corresponding case study that examines the health effects of air pollution in the Medicare cohort in the United States. METHODS: The statistical methodology developed in this report improves the analysis of environmental mixtures in two distinct ways. First, our results highlight inherent difficulties, which require careful consideration in any study of the health effects of multiple exposures. Second, we developed a statistical methodology that broadens the scope of questions that can be answered in analyses of air pollution mixtures and can increase the policy relevance of evidence obtained from epidemiological studies using multiple exposures. Additionally, we illustrated the aforementioned approaches in a nationwide study of the health effects of air pollution in the US Medicare population, extending the existing evidence on the health effects of air pollution within this cohort. RESULTS: ) components are heterogeneous and that these effects are more pronounced in areas with lower socioeconomic status. Specific aim 3 studied the mobility of individuals and found that ignoring mobility can bias health effects, although typically toward the null of no exposure effect. Incorporating mobility in the Medicare cohort did not lead to substantially different findings; however, accounting for mobility tended to increase the magnitude of estimated health effects. In specific aim 4, we developed a methodology for assessing robustness of health effects to unmeasured confounding bias and found that there is robust evidence overall of a harmful effect of pollution on public health. CONCLUSIONS: Our studies provide strong evidence of air pollution effects on public health, and our methodology gives new insights into key issues about this effect. Specifically, the effects of air pollution are heterogeneous and affect certain subgroups of the population more than others, and these effects are moderately robust to unmeasured confounding bias. Future studies can incorporate the ideas and approaches developed in this report to address important questions in analyses with multiple exposures.

  PublisherOA PDF

• A Latent Factor Panel Approach to Spatiotemporal Causal Inference

  ArXiv.org · 2025-09-13

  preprintOpen accessSenior author

  Unmeasured confounding can severely bias causal effect estimates from spatiotemporal observational data, especially when the confounders do not vary smoothly in time and space. In this work, we develop a method for addressing unmeasured confounding in spatiotemporal contexts by building on models from the panel data literature and methods in multivariate causal inference. Our method is based on a factor confounding assumption, which posits that effects of unmeasured confounders on exposures and outcomes can be captured by a shared latent factor model. Factor confounding is sufficient to partially identify causal effects, even when there is interference between units. Additional assumptions that limit the degree of spatiotemporal interference, reasonable in most applications, are sufficient to point identify the effects. Simulation studies demonstrate that the proposed approach can substantially reduce omitted variable bias relative to other spatial smoothing and panel data baselines. We illustrate our method in a case study of the effect of prenatal PM2.5 exposure on birth weight in California.

  PublisherOA PDFDOI

Frequent coauthors

• Edoardo M. Airoldi

  Temple University

  34 shared

• Florian Markowetz

  University of Cambridge

  18 shared

• Alexander D’Amour

  Google (United States)

  13 shared

• Shu‐Ching Hu

  11 shared

• Elaine R. Peskind

  11 shared

• Cyrus P. Zabetian

  University of Washington

  11 shared

• Joseph F. Quinn

  VA Portland Health Care System

  9 shared

• Daniel Promislow

  University of Washington

  9 shared

Labs

• Center for Financial Mathematics and Actuarial ResearchPI

Education

• Ph.D., Statistics

  Harvard University

  2015

• Sc.M., Applied Math

  Brown University

  2010

• Sc.B.

  Brown University

  2009