José Bayoán Santiago Calderón is a research economist in the national economic accounts research group at the Bureau of Economic Analysis. Before joining the federal statistical system, Dr. Santiago Calderón had years of experience in the private sector as a research scientist at various companies. Bayoán also held academic appointments with the Biocomplexity Institute and Initiative at the University of Virginia, where he started his career in public service. His research has centered on improving decision-making, emphasizing the public good (e.g., science policy). His transdisciplinary research approach has enabled him to routinely collaborate across disciplines and develop a diverse set of domain knowledge and methodological toolset. He also participates in various open-source software communities (e.g., JuliaLang) and civic activism (e.g., Code4PR, Mentes Puertorriqueñas en Accion).
🇵🇷 de pura cepa. I read quite a bit of manga, manhwa & manhua as well as watching anime, donghua and KDramas. Sometimes, I even have time and energy to play some videogames. Check out the relevant profiles: PSN Profiles, MyAnimeList, MyDramaList.
Scalable Data Analysis
Julia, R, SQL, Git, Linux
Scientific Computing, Software Development
High-Performance Computing, Cloud Computing
Agent-Based Modeling (ABM)
Social Network Analysis
Geographic Information Systems (GIS)
Text Mining, Natural Language Processing (NLP)
Worked on multiple projects with federal and state agencies helping them meet their missions. These included:
Assisted the infrastructure team on helping the team best use UVA computing resources (e.g., high-performance computing) and best practices (e.g., version control).
Served as project lead and instructor for the Data Science for the Public Good Young Scholars Program (DSPG).
Supervisor: Sallie Ann Keller, PhD
Developed the module for bioequivalence (BE) analysis in the Pumas ecosystem. This included the design, implementation, testing, documentation, maintanence, and coordination with the other components of the ecosystem.
Assisted the consulting branch working on various projects for our clients.
Assisted the data collection and analysis of several experiments. Some tasks included recruitment, training, running experiments (human and animal subjects). Some of the methods for the data collection and analysis included computer laboratory experiments, drug studies (e.g., alcohol, testosterone), biometric research such as electroencephalogram (EGG) and electrocardiogram (ECG), eye-tracking, and blood work. Several of the tools used included z-Tree and iMotions-BIOPAC.
Supervisor: Paul Joseph Zak, PhD
Summer intern through the Agents of Change Empowerment and Retention Program (PARACa) fellowship, a Mentes Puertorriqueñas en Acción initiative. Worked on the annual report to the state senate on the status of the K-12 public education system titled “El estado actual de las escuelas públicas en Plan de Mejoramiento en Puerto Rico, año escolar 2010-2011”. Assisted the Coalition for Equity and High Quality Education (CECE, for its Spanish acronym) and members of the school community in the choosing and design of the advocacy plan for the year 2011-2012.
Supervisor: David Ortiz
This paper studies community formation in OSS collaboration networks. While most current work examines the emergence of small-scale OSS projects, our approach draws on a large-scale historical dataset of 1.8 million GitHub users and their repository contributions. OSS collaborations are characterized by small groups of users that work closely together, leading to the presence of communities defined by short cycles in the underlying network structure. To understand the impact of this phenomenon, we apply a pre-processing step that accounts for the cyclic network structure by using Renewal-Nonbacktracking Random Walks (RNBRW) and the strength of pairwise collaborations before implementing the Louvain method to identify communities within the network. Equipping Louvain with RNBRW and the contribution strength provides a more assertive approach for detecting small-scale teams and reveals nontrivial differences in community detection such as users' tendencies toward preferential attachment to more established collaboration communities. Using this method, we also identify key factors that affect community formation, including the effect of users' location and primary programming language, which was determined using a comparative method of contribution activities. Overall, this paper offers several promising methodological insights for both open-source software experts and network scholars interested in studying team formation.
Econometrics.jl is a package for econometrics analysis. It provides a series of most common routines for applied econometrics such as models for continuous, nominal, and ordinal outcomes, longitudinal estimators, variable absorption, and support for convenience functionality such as weights, rank deficient, and robust variance covariance estimators. This study complements the package through a discussion of the motivation, placing the contribution within the Julia ecosystem and econometrics software in general, and provides insights on current gaps and ways the Julia ecosystem can evolve.
Cluster robust models are a kind of statistical models that attempt to estimate parameters considering potential heterogeneity in treatment effects. Absent heterogeneity in treatment effects, the partial and average treatment effect are the same. When heterogeneity in treatment effects occurs, the average treatment effect is a function of the various partial treatment effects and the composition of the population of interest. The first chapter explores the performance of common estimators as a function of the presence of heterogeneity in treatment effects and other characteristics that may influence their performance for estimating average treatment effects. The second chapter examines various approaches to evaluating and improving cluster structures as a way to obtain cluster-robust models. Both chapters are intended to be useful to practitioners as a how-to guide to examine and think about their applications and relevant factors. Empirical examples are provided to illustrate theoretical results, showcase potential tools, and communicate a suggested thought process.
Puerto Rico is an U.S. unincorporated territory and its political situation, economic downturn, significant migration to the U.S. mainland, and technological capabilities create a very unique combination of challenges and opportunities for the healthcare system in the country. Some of them are related to incorporating healthcare information technology (HIT) best practices from the U.S. with the local culture in mind. The current study aims at investigating the current state of technology adoption in Puerto Rican healthcare and provides some policy recommendations for improving the implementation process. We argue that a more technologically advanced healthcare system will improve clinical decision support, will increase prevention, and will ultimately provide better health outcomes for Puerto Ricans. We draw upon some best practices in HIT implementation in the U.S. but we suggest that the local context and culture be taken into consideration in order to achieve more effectiveness and more positive results.