Neural Networks for Longitudinal Data Analysis

Longitudinal data (or panel data) arise when observations are recorded on the same individuals at multiple points in time.

rstudio::conf 2020 modeling

Neural Networks for Longitudinal Data Analysis

January 31, 2020
Longitudinal data (or panel data) arise when observations are recorded on the same individuals at multiple points in time. For example, a longitudinal baseball study might track individual player characteristics (team affiliation, age, height, weight, etc.) and outcomes (batting average, stolen bases, runs, strikeouts, etc.) over multiple seasons, where the number of seasons could vary across players. Neural network frameworks such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) can flexibly accommodate this data structure while preserving and exploiting temporal relationships. In this presentation, we highlight the use of neural networks for longitudinal data analysis with tensorflow and keras in R.

About the speaker

Sydeaka Watson
/

Dr. Sydeaka Watson is a native of New Orleans, Louisiana and currently lives in Dallas, Texas. She is Founder and Owner of Korelasi Data Insights, LLC and a Senior Data Scientist at Elicit Insights, LLC. In these roles, Sydeaka uses predictive analytics and visual tools to draw insights from diverse datasets. Sydeaka earned a Ph.D. in Statistics from Baylor University and has several years of teaching experience. In her 5 years as Research Assistant Professor in The University of Chicago Biostatistics Laboratory, she consulted with over 110 biomedical research teams in The University of Chicago Medical Center, specializing in statistical analysis and experimental design for clinical research studies. Her current research interests include applications of (1) image recognition for computer vision and (2) data science for social justice. Sydeaka currently serves as Organizer of the R-Ladies Dallas Chapter. She also volunteers in the Dallas chapters of Girls Who Code and Black Girls Code.