Quantifying individual differences from complex datasets in developmental psychology

April 23, 2019

The Data Science Institute is delighted to award postdoctoral matching funds to Drs. Darko Odic (Psychology), Cristina Conati (Computer Science), and Lang Wu (Statistics) for their project "Quantifying Individual Differences from Complex Datasets in Developmental Psychology". This project seeks to leverage new machine learning and statistical techniques to work woth messy, hetergenous data sets with missing values to better understand development psychology. The project summary is below.

Developmental psychology fundamentally relies on the robust measurement of individual differences - capturing variables at an individual participant level - in order to formulate hypotheses about what children know, how their psychology changes over time, and to characterize the best predictors of their long-term educational, health, and psychological outcomes. But, newborns, infants, and young children are notoriously difficult experiment participants, leading to two major challenges in data analysis: (1) developmental data can be complex and multivariate but simultaneously limited by the need for short testing sessions that collect sparse data (e.g., neural recordings on the scalp for durations of 15 minutes or less); and (2) data are often censored or missing, as many children may stop paying attention to the task, may need to be fed, might create too many motion artifacts, etc. Our goal is to capitalize on hundreds of existing data points from the UBC Department of Psychology developmental psychology labs - including eye-tracking and neuroimaging data from infants and toddlers - to leverage existing solutions in machine learning and statistical survival analysis and develop novel analytical pipelines for measuring individual differences in these heterogeneous datasets.