Emma Risner

Background

About Emma Risner

As a Biostatistics Ph.D. student at Boston University, I specialize in leveraging advanced statistical methodologies to address key challenges in public health and medicine. My expertise includes survival analysis, recurrent event modeling, longitudinal analysis, and latent Class Growth analysis (LCGA), with a strong focus on integrating these techniques into time-to-event analyses and patient-reported outcomes research. My work explores the application of LCGA to time-to-event data and Linear Mixed Modeling, enabling the identification of meaningful subgroups and patterns that provide deeper insights into patient trajectories. This approach has been instrumental in uncovering heterogeneity within populations, such as distinct profiles of patient-reported outcomes or variations in risk factors for disease progression. Additionally, I am deeply interested in extending this work into latent transition analysis (LTA) to better understand how individuals transition between states over time and how these transitions influence health outcomes. I have applied a wide range of statistical methods, including extensions of Cox Proportional Hazards models (e.g, Andersen-Gill, Prentice-Williams-Petersen), natural cubic splines, and growth mixture modeling, to topics such as recurrent malaria episodes, associations between recurrent knee replacement, Multiple Sclerosis cognitive scoring, and PROs such as long-term pain outcomes in clinical trials. These projects reflect my commitment to using innovative statistical approaches to answer complex clinical and epidemiological questions. Through internships at Novartis and Regeneron Pharmaceuticals, I gained hands-on experience with clinical trial data, survival modeling, and interdisciplinary collaboration. Beyond my research, I am passionate about mentoring underrepresented students, supporting their development in data science and biostatistics. My ultimate goal is to bridge innovative statistical methodologies, such as LCA, LCGA, and LTA with, real-world applications in time-to-event analyses, advancing our understanding of patient-reported outcomes and improving clinical and regulatory decision-making.