Skip to main content

Elena A. Erosheva


Professor, Statistics

Research Interests

Statistical Methodology, Discrete Data Analysis, Latent Variable Models, Disability in Elderly People


Joint Position with School of Social Work I am a statistician whose research focuses on the development and application of modern statistical methods for addressing complex substantive questions in the social, medical and health sciences. Ongoing methodological research focuses on latent variable and mixed membership models, multivariate and longitudinal data analysis, text and network analysis. I received the 2013 Mitchell Prize from the International Society of Bayesian Analysis and the first prize from the National Institutes of Health's Peer Review Challenge. I currently serve as an Associate Editor of the Journal of the American Statistical Association and of the Annals of Applied Statistics. My PhD is from Carnegie Mellon University (2002).


A Unified Statistical Learning Model for Rankings and Scores with Application to Grant Panel Review
Michael Pearce, Elena A. Erosheva
Rankings and scores are two common data types used by judges to express preferences and/or perceptions of quality in a collection of objects. Numerous models…

Bayesian Rank-Clustering
Michael Pearce, Elena A. Erosheva
In a traditional analysis of ordinal comparison data, the goal is to infer an overall ranking of objects from best to worst with each object having a unique…

A Diagnostic Tool for Functional Causal Discovery
Shreya Prakash, Fan Xia, Elena Erosheva
Causal discovery methods aim to determine the causal direction between variables using observational data. Functional causal discovery methods, such as those…

Gender-based homophily in collaborations across a heterogeneous scholarly landscape
Y. Samuel Wang, Carole J. Lee, Jevin D. West, Carl T. Bergstrom, Elena A. Erosheva
In this article, we investigate the role of gender in collaboration patterns by analyzing gender-based homophily -- the tendency for researchers to co-author…

Modeling Preferences: A Bayesian Mixture of Finite Mixtures for Rankings and Ratings
Michael Pearce, Elena A. Erosheva
Rankings and ratings are commonly used to express preferences but provide distinct and complementary information. Rankings give ordinal and scale-free…

Dimension-Grouped Mixed Membership Models for Multivariate Categorical Data
Yuqi Gu, Elena A. Erosheva, Gongjun Xu, David B. Dunson
Mixed Membership Models (MMMs) are a popular family of latent structure models for complex multivariate data. Instead of forcing each subject to belong to a…

Co-clustering of time-dependent data via Shape Invariant Model
Alessandro Casa, Charles Bouveyron, Elena Erosheva, Giovanna Menardi
Multivariate time-dependent data, where multiple features are observed over time for a set of individuals, are increasingly widespread in many application…

On the use of bootstrap with variational inference: Theory, interpretation, and a two-sample test example
Yen-Chi Chen, Y. Samuel Wang, Elena A. Erosheva
Variational inference is a general approach for approximating complex density functions, such as those arising in latent variable models, popular in machine…

A Variational EM Method for Mixed Membership Models with Multivariate Rank Data: an Analysis of Public Policy Preferences
Y. Samuel Wang, Ross Matsueda, Elena A. Erosheva
In this article, we consider modeling ranked responses from a heterogeneous population. Specifically, we analyze data from the Eurobarometer 34.1 survey…

On the relationship between set-based and network-based measures of gender homophily in scholarly publications
Y. Samuel Wang, Elena A. Erosheva
There is an increased interest in the scientific community in the problem of measuring gender homophily in co-authorship on scholarly publications (Eisen, 2016…

A semiparametric approach to mixed outcome latent variable models: Estimating the association between cognition and regional brain volumes
Jonathan Gruhl, Elena A. Erosheva, Paul K. Crane
Multivariate data that combine binary, categorical, count and continuous outcomes are common in the social and health sciences. We propose a semiparametric…

Describing disability through individual-level mixture models for multivariate binary data
Elena A. Erosheva, Stephen E. Fienberg, Cyrille Joutard
Data on functional disability are of widespread policy interest in the United States, especially with respect to planning for Medicare and Social Security for…