ABOUT ME
I was born in Xalapa, México. I got my BSc in Actuarial Science from UNAM. Later, I obtained a MSc in Statistics from CIMAT/Universidad de Guanajuato, México. I wrote my thesis under the supervision of Dr. Andrés Christen-Gracia. After getting my degree, I worked for two years as a statistical analyst at MD Anderson Cancer Center; that gave me the opportunity to obtain experience in statistical consulting while being involved in research, more specifically, in Bayesian methods for Pharmacokinetics. In 2005, I decided to pursue a doctorate. I was truly fortunate to work on my PhD under the supervision of Sayan Mukherjee and Robert L. Wolpert at Duke University. My thesis project involved applying ideas of Computational Topology and Random Geometric Graphs to graphical modelling. After getting my PhD, I worked as a postdoctoral fellow at Harvard University with Edoardo M. Airoldi, where I started working on social network data. From 2015 to 2017, I held the position of research associate at University College London, where I was mentored by Patrick Wolfe and Sofia Olhede. I held an appointment as a lecturer at Lancaster University from 2017 to 2021. I started at my current post on January 2022.
RESEARCH INTERESTS
EDUCATION
2009
Duke University
PhD in Statistics
2002
Universidad de Guanajuato/ CIMAT
MSc in Statistics
Social Networks
I am interested in tackling statistical problems involving social networks from a Bayesian perspective, more specifically: I have worked on building population models for networks and helped to create statistical models for hypergraph data.
2001
Universidad Nacional Autónoma de México (UNAM)
BSc in Actuarial Science
Graphical Models
For my PhD dissertation, my mentors and I proposed new parameterizations and representations of graph and hypergraph space in order to specify flexible informative priors and Markov Chain Monte Carlo algorithms for graphical models.
Applications of Geometry and Topology to Statistics
A recurring theme in my reaserch is to find connections between these two fields and Statistics. We have successfully applied tools from Computational Topology to Graphical Models and the task of modelling hypergraph data. Geometric constructions are proving useful in my current work on multivariate models for social networks. On a related note: I am very interested in developing Bayesian models aimed to quantify uncertainty in problems related to topological data analysis.
Shape Theory
It has been quite rewarding to study this topic: at least one of my main projects involved applying ideas that originated from this field to modelling network data.