What’s New in SAS/QC 9.3

Overview

SAS/QC 9.3 includes two new experimental procedures for multivariate process monitoring and enhancements to the CAPABILITY, FACTEX, and RELIABILITY procedures.
The new MVPMODEL and MVPMONITOR procedures are used together to monitor multivariate process variation over time in order to determine whether the process is stable or to detect changes in a stable process.

New MVPMODEL Procedure (Experimental)

The MVPMODEL procedure provides computational and graphical tools for building a principal components model from multivariate process data in which the measured variables are continuous and correlated. This model then serves as input to the MVPMONITOR procedure.
The MVPMODEL procedure implements principal components analysis (PCA) techniques which evolved in the field of chemometrics for monitoring hundreds or even thousands of correlated process variables; refer to Kourti and MacGregor (1995,1996 ) for an introduction. These techniques differ from the classical multivariate T2 chart in which Hotelling’s T2 statistic is computed as a distance from the multivariate mean scaled by the covariance matrix of the variables; refer to Alt 1985(). Instead, principal component methods compute T2 based on a small number of principal components that model most of the variation in the data.
The principal components approach offers several advantages over the construction of the classical T2 chart:
  • It avoids computational issues that arise when the process variables are collinear and their covariance matrix is nearly singular.
  • It offers diagnostic tools for interpreting unusual values of T2 .
  • By projecting the data to a low-dimensional subspace, a principal components model more adequately describes the variation in a multivariate process, which is often driven by a small number of underlying factors which are not directly observable.

New MVPMONITOR Procedure (Experimental)

The MVPMONITOR procedure produces control charts for multivariate process data. It reads output data sets that contain statistics and principal components model information and that were created by the MVPMODEL procedure. The MVPMONITOR procedure creates two multivariate control charts: T2 charts and SPE (squared prediction error) charts. It can also create contribution plots, in addition to score plots in some cases.
Multivariate control charts detect unusual variation that would not be uncovered by individually monitoring the variables with univariate control charts, such as Shewhart charts. A major impetus in the development of multivariate control charts is the inadequacy of individual univariate control charts when working with correlated measurement variables. A multivariate control chart can detect changes in the linear relationships of the variables in addition to their marginal means and variances.

CAPABILITY Procedure Enhancements

The CAPABILITY procedure supports five new fitted distributions for SAS/QC 9.3:
  • Gumbel distribution
  • inverse Gaussian distribution
  • generalized Pareto distribution
  • power function distribution
  • Rayleigh distribution
These new distributions are available in the CDFPLOT, HISTOGRAM, PROBPLOT, PPPLOT, and QQPLOT statements.

FACTEX Procedure Enhancements

In the FACTEX procedure, the MAXCLEAR option has been added to the MODEL statement for SAS/QC 9.3. The MAXCLEAR option requests "a design that maximizes the number of clear interactions, those which are not aliased with any other effects that are either required to be estimable or assumed to be nonnegligible." In the context of resolution 4 designs, a MaxClear design maximizes the number of two-factor interactions that are unaliased with any other interaction.

RELIABILITY Procedure Enhancements

The RELIABILITY procedure for SAS/QC 9.3 includes enhancements related to fitting parametric models for lifetime and recurrent events data. The RELIABLITY procedure now enables you to do the following:
  • estimate parameters and construct probability plots for the three parameter Weibull distribution
  • estimate the parameters of nonhomogeneous Poisson process models for recurrent events data and plot the cumulative mean and intensity functions

References

Alt, F. (1985), “Multivariate Quality Control,” Encyclopedia of Statistical Sciences, Volume 6.
Kourti, T. and MacGregor, J. F. (1995), “Process Analysis, Monitoring and Diagnosis, Using Multivariate Projection Methods,” Chemometrics and Intelligent Laboratory Systems, 28, 3-21.
Kourti, T. and MacGregor, J. F. (1996), “Multivariate SPC Methods for Process and Product Monitoring,” Journal of Quality Technology, 28, 409-428.
Copyright © SAS Institute Inc. All rights reserved.