All talks licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Talk, IMS International Conference on Statistics and Data Science (ICSDS), Nice, France
I discuss an extension of generalized raking to estimate marginal parameters (e.g., the average treatment effect) and obtain valid inference using machine learning.
Talk, Kaiser Permanente Washington Health Research Institute Seminar, Virtual
I discuss inference for summaries of longitudinal model-agnostic variable importance.
Talk, JSM 2024, Portland, Oregon
In research assessing the effect of an intervention or exposure, a key secondary objective often involves assessing differential effects of this intervention or exposure in subgroups of interest; this is often referred to as assessing effect modification or heterogeneity of treatment effects (HTE). Observed HTE can have important implications for policy, including intervention strategies (e.g., will some patients benefit more from intervention than others?) and prioritizing resources (e.g., to reduce observed health disparities). Analysis of HTE is well understood in studies where the independent unit is an individual. In contrast, in studies where the independent unit is a cluster (e.g., a hospital or school) and a cluster-level outcome is used in the analysis, it is less well understood how to proceed if the HTE analysis of interest involves an individual-level characteristic (e.g., self-reported race) that must be aggregated at the cluster level. Through simulations, we show that only individual-level models have power to detect HTE by individual-level variables; if outcomes must be defined at the cluster level, then there is often low power to detect HTE by the corresponding aggregated variables. We illustrate the challenges inherent to this type of analysis in a study assessing the effect of an intervention on increasing COVID-19 booster vaccination rates at long-term care centers.
I also gave an invited poster presentation on based this talk at the JSM opening mixer on August 4.
Talk, 24th Meeting of New Researchers in Statistics and Probability, Virtual
I discuss inference for summaries of longitudinal model-agnostic variable importance.
Talk, WNAR 2024, Fort Collins, Colorado
In research assessing the effect of an intervention or exposure, a key secondary objective often involves assessing differential effects of this intervention or exposure in subgroups of interest; this is often referred to as assessing effect modification or heterogeneity of treatment effects (HTE). Observed HTE can have important implications for policy, including intervention strategies (e.g., will some patients benefit more from intervention than others?) and prioritizing resources (e.g., to reduce observed health disparities). Analysis of HTE is well understood in studies where the independent unit is an individual. In contrast, in studies where the independent unit is a cluster (e.g., a hospital or school) and a cluster-level outcome is used in the analysis, it is less well understood how to proceed if the HTE analysis of interest involves an individual-level characteristic (e.g., self-reported race) that must be aggregated at the cluster level. Through simulations, we show that only individual-level models have power to detect HTE by individual-level variables; if outcomes must be defined at the cluster level, then there is often low power to detect HTE by the corresponding aggregated variables. We illustrate the challenges inherent to this type of analysis in a study assessing the effect of an intervention on increasing COVID-19 booster vaccination rates at long-term care centers.
Talk, University of Washington Biostatistics 111, Seattle, Washington
Lecture on some of the ways that statistics is used in infectious disease research to students in UW Biostatistics 111.
Talk, Institut Curie Statistics Seminar, Paris, France
In many applications, it is of interest to assess the relative contribution of features (or subsets of features) toward the goal of predicting a response – in other words, to gauge the variable importance of features. In this talk, I will discuss a model-agnostic notion of variable importance and general conditions under which valid inference on the true importance can be obtained, even when machine learning-based techniques are used as part of estimation. We define variable importance as a population-level contrast between the oracle predictiveness of all available features versus all features except those under consideration. I provide several examples of predictiveness measures, including for right-censored outcomes, and illustrate the use of the proposed methods with data from a study of an antibody against HIV-1 infection.
Talk, IMS International Conference on Statistics and Data Science (ICSDS), Lisbon, Portugal
I discuss inference for summaries of longitudinal model-agnostic variable importance.
Talk, Mental Health Research Network Statistical Methods Scientific Interest Group, Virtual
I discuss inference for summaries of longitudinal model-agnostic variable importance.
Talk, University of Washington Biostatistics 111, Seattle, Washington
Lecture on some of the ways that statistics is used in infectious disease research to students in UW Biostatistics 111.
Talk, 15th International Conference of the European Consortium for Informatics and Mathematics Working Group on Computational and Methodological Statistics (CMStatistics), London, United Kingdom
I discuss a framework for inference on general model-agnostic variable importance measures and possible summary measures for longitudinal variable importance.
Talk, Forum on the Integration of Observational and Randomized Data, Washington, DC
I discuss a framework for predicting safety outcomes of interest within the FDA’s Sentinel system using data from electronic health records.
Talk, International Chinese Statistical Association Applied Statistics Symposium, Gainesville, Florida
I discuss a framework for inference on general model-agnostic variable importance measures and possible summary measures for longitudinal variable importance.
Talk, WNAR 2022, Virtual
I discuss a method for model-agnostic variable selection that is robust to model misspecification and valid in settings with missing data.
Talk, University of Washington Department of Biostatistics Seminar Series, Virtual
I discuss a framework for inference on general model-agnostic variable importance measures, and how this framework can be used to perform variable selection. I also briefly discuss several directions of current work, including longitudinal variable importance; a measure of how important variables are for tailoring treatment; and fairness-aware variable importance.
Talk, American Statistical Association Statistical Learning and Data Science Webinar Series, Virtual
I discuss a framework for inference on general model-agnostic variable importance measures.
Talk, Joint Statistical Meetings, Virtual
I gave a talk on work in progress, developing methods for variable selection in settings with missing data that do not rely on (generalized) linear models.
Talk, 3rd Annual Hutch United Symposium, Virtual
Keynote talk at the 3rd annual Hutch United Symposium.
Talk, Kaiser Permanente Washington Health Research Institute Seminar Series, Virtual
I discuss a framework for inference on general model-agnostic variable importance measures.
Talk, Fred Hutchinson Cancer Research Center Biostatistics Program Seminar Series, Virtual
I discuss three approaches towards a more principled use of machine learning: inference on the goodness of fit, inference on variable importance, and containerization.
Talk, Roanoke Valley Governor's School Computational Biology Course, Virtual
Guest lecture on some of the ways that statistics is used in infectious disease research in the Computational Biology course at Roanoke Valley Governor’s School.
Talk, Vanderbilt University Department of Biostatistics Seminar, Virtual
I discuss a framework for inference on general model-agnostic variable importance measures.
Talk, 37th International Conference on Machine Learning, Virtual
We discuss our paper to be published in the Proceedings of the Thirty-seventh International Conference on Machine Learning.
Talk, 27th International Dynamics and Evolution of HIV and Other Human Viruses Meeting, Virtual
Contributed talk at the 27th International Dynamics and Evolution of HIV and Other Human Viruses Meeting on SLAPNAP (see publications).
Talk, Joint Statistical Meetings, Denver, CO
This talk (on a preliminary version of my general variable importance paper published in Journal of the American Statistical Association) was selected for an ASA Nonparametrics Section Travel Award.
Talk, UW Biostatistics Colloquium, Seattle, WA
Invited talk on my dissertation research given at the UW Biostatistics Colloquium.
Talk, Joint Statistical Meetings, Baltimore, Maryland
This talk (on a preliminary version of my R-squared variable importance paper published in Biometrics) was selected for an ASA Biometrics Section Travel Award.
Talk, Thirty-fifth International Conference on Machine Learning, Stockholm, Sweden
Contributed talk at the Thirty-fifth International Conference on Machine Learning.
Talk, WNAR of the International Biometric Society, Santa Fe, New Mexico
This talk (on a preliminary version of my R-squared variable importance paper published in Biometrics) was selected as the Most Outstanding Oral Paper.