Sparse Integrative Discriminant Analysis for Multi-view Structured Data
Sandra E. Safo, Eun Jeong Min, and Lillian Haine , Sparse Linear Discriminant Analysis for Multi-view Structured Data, Biometrics, 2021
The SIDA package implements the SIDA and SIDANet algorithms for joint association and classification studies.
The algorithms consider the overall association between multi-view data, and the separation within each view when
choosing discriminant vectors that are associated and optimally separate subjects.
SIDANet incorporates prior structural information in joint association and classification studies.
It uses the normalized Laplacian of a graph to smooth coefficients of predictor variables, thus encouraging selection
of predictors that are connected and behave similarly.
Please refer to SIDA-manual.pdf for how to implement SIDA.