Multiblock Orthogonal Component Analysis (MOCA) – A Novel Tool for Data Integration
Time: 15.00-16.00 (CEST)
Sartorius Stedim Data Analytics (SSDA) invites to a webinar on the Umetrics® Suite and a preview of the novel MOCA tool in SIMCA® 16.
Multiblock Orthogonal Component Analysis (MOCA) is a new data analytics tool, which is designed to be fast and transparent when analyzing multiple blocks of data registered for the same basis set of observations. MOCA is similar in scope to O2PLS in cases involving only two matrices, but generalises to situations involving more than two matrices without giving preference to any particular block of data.
MOCA will extract two sets of components; joint and unique components. More specifically, the components may express globally joint information, locally joint information, and unique information:
* Globally joint information is systematic structure found in all data blocks being analyzed;
* Locally joint information is systematic structure found in a subset of the data blocks; and
* Unique information is additional systematic structure found only in one, single data block.
Attend this webinar and learn how MOCA can be used to disentangle the information in complex multi-block data analytics problems.
Topics for this webinar
- Objective of MOCA
- MOCA and its relationship to PCA and O2PLS
- Model structure
- Joint and Unique components
- Dedicated plots
Click here to register