We propose a procedure to test complicated ANOVA designs for functional data. The procedure is effective, flexible, easy to compute and does not require a heavy computational effort. It is based on the analysis of randomly chosen one-dimensional projections. The paper contains some theoretical results as well as some simulations and the analysis of some real data sets. Functional data include multidimensional data, so the paper contains a comparison between the proposed procedure and some usual MANOVA tests.
KeywordsANOVA Functional data Random projections Testing Two-way ANOVA
Mathematics Subject Classification (2000)62H15 62J10
Unable to display preview. Download preview PDF.
- Angelini C, Vidakovic B (2002) Some novel methods in wavelet data analysis: Wavelet ANOVA, F-test shrinkage and Γ-minimax wavelet shrinkage. Istituto per le Applicazioni del Calcolo “Mauro Picone.” Rapporti Tecnici RT 256/02 Google Scholar
- Cuesta-Albertos JA, Nieto-Reyes A (2007) An infinite dimensional depth: The random Tukey depth. Technical Report Google Scholar
- Faraway JJ (1997) Regression analysis for a functional response. J R Stat Soc B 64:887–898 Google Scholar
- R Development Core Team (2007) R: a language and environment for statistical computing, Vienna, Austria. ISBN 3-900051-07-0, http://www.R-project.org
- Ramsay JO, Silverman BW (2005) Functional data analysis, 2nd edn. Springer, New York Google Scholar