Anda belum login :: 23 Nov 2024 04:22 WIB
Detail
ArtikelA Study on the Analysis of Profile Data by Principal Components Analysis  
Oleh: Yasui, Seiichi ; Noguchi, Hidehisa
Jenis: Article from Proceeding
Dalam koleksi: Asian Network for Quality (ANQ) Congress 2011, Ho Chi Minh City, Vietnam, 27-30 September 2011, page 1-13.
Topik: Profile Data; Principal Components Analysis; Empirical Orthogonal Function; Functional Data Analysis; Statistical Process Control
Fulltext: JP41_Seiichi_Yasui_fullpaper.pdf (298.88KB)
Isi artikelTraditionally, approaches for Statistical Process Control (SPC) focused on the single dimensional specification such as distances, weights, roundness, etc. Though SPC by the single dimensional specification is easy, it is ideal to directly control a geometrical characteristic as profile data. There are two approaches for profile data. One is a regression approach and the other is a principal components approach. In the principal components approach, it is often difficult to interpret principal components. In our study, critical points for the principal components approach are considered though analyzing a realistic example and Monte Carlo study. We point out that the principal components approach is basically an analysis of empirical orthogonal function rather than usual multivariate analysis.
Opini AndaKlik untuk menuliskan opini Anda tentang koleksi ini!

Kembali
design
 
Process time: 0.015625 second(s)