The MVPDIAGNOSE procedure is used in conjunction with the MVPMODEL and MVPMONITOR procedures to monitor multivariate process variation over time, to determine whether the process is stable, and to detect and diagnose changes in a stable process. Collectively these three procedures are referred to as the MVP procedures. See Chapter 10: Introduction to Multivariate Process Monitoring Procedures, for a description of how the MVP procedures work together, and Chapter 12: The MVPMODEL Procedure, and Chapter 13: The MVPMONITOR Procedure, for details about the other MVP procedures.
The MVPDIAGNOSE procedure produces the following graphs that can provide insight into the variation in a process:
score plots for pairs of principal components
score plot matrices containing pairwise plots for multiple pairs of principal components
contribution plots for individual observations
paneled contribution plots for multiple observations
Each point in a score plot corresponds to a single observation from the input data set. A contribution plot displays the process variable contributions to a squared prediction error (SPE) or statistic from a single observation in the input data set. Therefore, each observation in the input data is independent in how PROC MVPDIAGNOSE handles it. This enables you to preprocess the input data flexibly by using the DATA step, WHERE expressions, and other SAS language elements to select the data to plot.
Note: ODS Graphics must be enabled (for example, by specifying the ODS GRAPHICS ON statement before invoking the procedure) in order for the MVPDIAGNOSE procedure to produce graphical output.