Directory Calendar News Careers Alumni Giving

Biostatistics Seminars

Department of Biostatistics Seminar Series

The Department of Biostatistics presents a regular speaker series each semester, generally on Thursday afternoon each week. Diverse experts lecture on their work in biostatistics.

Upcoming Biostats Seminars

Thu 9/20/2018 3:30PM - 4:30PM
Biostatistics at the FDA - Jessica (Jeongsook) Kim, FDA
Public Health Auditorium (G23)

Jessica Kim, Lead Mathematical Statistician, Food and Drug Administration, will present, “Biostatistics at the FDA”.
Thu 9/27/2018 3:30PM - 4:30PM
Hyun Jung (HJ) Park, University of Pittsburgh
Public Health Auditorium (G23)

Hyun Jung (HJ) Park, Department of Human Genetics, University of Pittsburgh, will present, “Insights into RNA Biology from Statistical Modeling for CancerTherapeutics”.
Thu 10/4/2018 3:30PM - 4:30PM
Peter X.K. Song, University of Michigan
Public Health Auditorium (G23)

Peter X.K. Song, Department of Biostatistics, University of Michigan, will present, “HASS: Hybrid Algorithm for Subgroup Search via ADMM and EM Algorithms”.
Thu 10/25/2018 3:30PM - 4:30PM
Dana L. Tudorascu, University of Pittsburgh
Public Health Auditorium (G23)

Thu 11/1/2018 3:30PM - 4:30PM
Jingyi (Jessica) Li, University of California, Los Angeles
Public Health Auditorium (G23)

Thu 11/8/2018 3:30PM - 4:30PM
Hongzhe Li (Lee), University of Pennsylvania
Public Health Auditorium (G23)

Thu 11/29/2018 3:30PM - 4:30PM
Dulal K. Bhaumik, University of Illinois at Chicago
Public Health Auditorium (G23)

Previous Biostats Seminars

Biostatistics Seminar Series

Michael Sohn, University of Pennsylvania

Thursday 1/18 3:30PM - 4:30PM
Public Health Auditorium (G23)

Biostatistics guest speaker, Michael Sohn, University of Pennsylvania, will present, "Statistical Methods in Microbiome Data Analysis."

Microbiome study involves new computational and statistical challenges due to the characteristics of microbiome data: high sparsity, over-dispersion, and high-dimensionality. I am going to present two methods that account for the characteristics of microbiome data: 1) a GLM-based latent variable ordination method and 2) a compositional mediation model.

1) GLM-based latent variable ordination method: Distance-based ordination methods, such as the principal coordinate analysis (PCoA), are incapable of distinguishing between location effect (i.e., the difference in mean) and dispersion effect (i.e., the difference in variation) when there is a strong dispersion effect. In other words, PCoA may falsely display a location effect when there is a strong dispersion effect but no location effect. To resolve this potential problem, I proposed, as an ordination method, a zero-inflated quasi-Poisson factor model whose estimated factor loadings are used to display the similarity of samples.

2) Compositional mediation model: The causal mediation model has been extended to incorporate nonlinearity, treatment-mediation interaction, and multiple mediators. These models, however, are not directly applicable when mediators are components of a composition. I proposed a causal, compositional mediation model utilizing the algebra for compositions in the simplex space and an L1 penalized linear regression for compositional data in high-dimensional settings. The estimators of the direct and indirect (or mediation) effects are defined under the potential outcomes framework to establish causal interpretation. The model involves a novel integration of statistical methods in high dimensional regression analysis, compositional data analysis, and causal inference.

Last Updated On Friday, January 05, 2018 by Kapko, Bernadette E
Created On Friday, January 05, 2018


For information on seminars and events in the department, contact:

Bernadette Kapko

© 2018 by University of Pittsburgh Graduate School of Public Health

Login  |  Sitemap