Bailey Fosdick - Colloquium Speaker

Associate Professor, Department of Statistics, Colorado State University
Thursday, April 29, 2021 - 3:15pm
Colloquium Title: 
Network Regression with Exchangeable or Block-exchangeable Errors


Relational arrays represent measures of association between pairs of actors, often in varied contexts or over time. Such data appear as trade flows between countries, contact frequencies between school children in classrooms, and dynamic protein-protein interactions. Elements of a relational array are often modeled as a linear function of observable covariates, where the regression coefficients are the subjects of inference. The structure of the relational array engenders dependence among relations that involve the same actor. Uncertainty estimates for regression coefficient estimators — and ideally the coefficient estimators themselves — must account for this relational dependence. Existing estimators of standard errors that recognize such relational dependence rely on estimating extremely complex, heterogeneous structure across actors. In this talk I introduce a new class of parsimonious coefficient and standard error estimators for regressions of relational arrays. We leverage an exchangeability assumption to derive standard error estimators that pool information across actors and are substantially more accurate than existing estimators in a variety of settings. This exchangeability assumption is pervasive in network and array models in the statistics literature, but not previously considered when adjusting for dependence in a regression setting with relational data. In cases when a homogeneity error assumption is inappropriate, we propose an extension of our method that captures critical clustering of the actors, often seen in data with natural community structure.


Everyone is welcome to join! Please note that the meeting opens at 3:15pm, and the presentation is at 3:30-4:20pm. There will be time afterward for Q&A with the speaker.

Topic: Colloquia: Department of Statistics and Actuarial Science, The University of Iowa

Time: Apr 29, 2021 03:15 PM Central Time (US and Canada)

Join Zoom Meeting

Meeting ID: 949 5289 2803

One tap mobile

+13126266799,,94952892803# US (Chicago)

+16468769923,,94952892803# US (New York)

Dial by your location

        +1 312 626 6799 US (Chicago)

        +1 646 876 9923 US (New York)

        +1 301 715 8592 US (Washington DC)

        +1 346 248 7799 US (Houston)

        +1 669 900 6833 US (San Jose)

        +1 253 215 8782 US (Tacoma)

Meeting ID: 949 5289 2803

Find your local number:

Join by SIP

Join by H.323 (US West) (US East) (India Mumbai) (India Hyderabad) (Amsterdam Netherlands) (Germany) (Australia Sydney) (Australia Melbourne) (Brazil) (Canada Toronto) (Canada Vancouver) (Japan Tokyo) (Japan Osaka)

Meeting ID: 949 5289 2803