Bootstrap confidence intervals for three-way methods

Research output: Contribution to journalArticleAcademicpeer-review

35 Citations (Scopus)

Abstract

Results from exploratory three-way analysis techniques such as CANDECOMP/PARAFAC and Tucker3 analysis are usually presented without giving insight into uncertainties due to sampling. Here a bootstrap procedure is proposed that produces percentile intervals for all output parameters. Special adjustments are offered for handling the non-uniqueness of the solutions. The percentile intervals indicate the instability of the sample solutions. By means of a simulation study it is demonstrated that the percentile intervals can fairly well be interpreted as confidence intervals for the output parameters. Copyright (C) 2004 John Wiley Sons, Ltd.

Original languageEnglish
Pages (from-to)22-36
Number of pages15
JournalJournal of Chemometrics
Volume18
Issue number1
DOIs
Publication statusPublished - Jan-2004
EventThree-Way Methods in Chemistry and Psychology (TRICAP 2003) - , Cayman Islands
Duration: 22-Jun-200327-Jun-2003

Keywords

  • confidence intervals
  • bootstrap
  • resampling
  • three-way analysis
  • CANDECOMP/PARAFAC
  • Tucker3
  • PRINCIPAL COMPONENT ANALYSIS
  • 3-MODE FACTOR-ANALYSIS
  • INDIVIDUAL-DIFFERENCES
  • ROTATION
  • JACKKNIFE
  • MODELS

Cite this