Our lab aims to develop and evaluate new methods for analyzing high-dimensional genetic data using statistical learning algorithms. Our goal is to improve the power of genome-wide studies to detect genetic variants associated with complex psychological outcomes. Currently we focus on random forests, gradient boosting, and the development of statistical learning methods for multivariate outcomes.
- Charles Laurin
- Stephen Tueller
- Raymond Walters
If you are interested in joining the Genetics and Statistical Learning Lab (GSSL), or would like more information about our current research, please contact Gitta Lubke by email at: firstname.lastname@example.org.