Dimension Reduction for Big Data
Hossein Moradi · Open PRAIRIE (South Dakota State University) · 2019
In many research areas, such as health science, environmental sciences, agricultural sciences, etc., it is common to observe data with huge volume. These data could be correlated through space and/or time. Studying the relationship for such complex data calls for a fairly advanced modeling techniques. Reducing the dimensionality of the data in both covariates and response space can help researcher to better handle the computational cost.