Analyzing Complicated Data Sets by PCA and PLS

Article

Wold, Svante; Kettaneh, Nouna   (1998, ASQ)   Umeå University, Umeå, Sweden; Umetrics Inc., Kinnelon, NJ

Annual Quality Congress, Philadelphia, PA    Vol. 52    No. 0
QICID: 10664    May 1998    pp. 70-72
List $10.00
Member $5.00

FOR A LIMITED TIME, ACCESS TO THIS CONTENT IS FREE!
You will need to be signed in.
New to ASQ? Register here.

Article Abstract

Projection methods like PCA (principle components analysis) and PLS (projections to latent structures) are useful for modeling complex data arranged in matrices. An example applies PCA and PLS to a data set of 33 variables in 92 values. PCA and PLS analyses can produce graphic displays, such as MSPC, EWMA, and cusum charts. In a PLS geometric approach, the Y matrix acts as a focusing matrix for X. This permits display of each observation's residual standard deviation and the distance from the observation to the model plane.

Keywords

Data analysis,Graphics,Statistical process control (SPC),Process control,Process analysis


Browse QIC Articles Chronologically:     Previous Article     Next Article

New Search

Featured advertisers





ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.