Academy of Mathematics and Systems Science, CAS
Colloquia & Seminars

Speaker:	Assistant Professor CHAO HUANG，Florida State University
Inviter:	潘文亮
Title:	Shape-on-Scalar Regression Models: Going Beyond Prealigned Non-Euclidean Responses
Language:	English
Time & Venue:	2022.11.30 10:00-11:00 腾讯会议：848-249-616
Abstract:	https://meeting.tencent.com/dm/p7cO0RPg1sVj The problem of using covariates to predict shapes of objects in a regression setting is important in many fields. A formal statistical approach, termed geodesic regression model, is commonly used for modeling and analyzing relationships between Euclidean predictors and shape responses. Despite its popularity, this model faces several key challenges, including (i) misalignment of shapes due to pre-processing steps, (ii) difficulties in shape alignment due to imaging heterogeneity, and (iii) lack of spatial correlation in shape structures. We propose a comprehensive geodesic factor regression model that addresses all these challenges. Instead of using shapes as extracted from pre-registered data, it takes a more fundamental approach, incorporating alignment step within the proposed regression model and learns them using both pre-shape and covariate data. Additionally, it specifies spatial correlation structures using low-dimensional representations, including latent factors on the tangent space and isotropic error terms. Furthermore, the geodesic factor regression model is extended to a mixture of geodesic factor regression model, which can cluster objects and recover the underlying sub-group structure according to their shapes and covariates in Euclidean space. Both simulation studies and real data analysis are conducted to compare the performance of our proposed method with other existing methods.