Testing for lack of dependence in the functional linear model
- 1 June 2008
- journal article
- research article
- Published by Wiley in Canadian Journal of Statistics
- Vol. 36 (2) , 207-222
Abstract
The authors consider the linear model Yn = ψXn + ϵn relating a functional response with explanatory variables. They propose a simple test of the nullity of ψ based on the principal component decomposition. The limiting distribution of their test statistic is chi‐squared, but this distribution is also an excellent approximation in finite samples. The authors illustrate their method using data from terrestrial magnetic observatories.Keywords
This publication has 17 references indexed in Scilit:
- Portmanteau Test of Independence for Functional ObservationsJournal of the American Statistical Association, 2007
- Diagnostics for functional regression via residual processesComputational Statistics & Data Analysis, 2007
- Prediction in functional linear regressionThe Annals of Statistics, 2006
- Functional Data Analysis2005
- Intense space storms: Critical issues and open disputesJournal of Geophysical Research, 2003
- Testing Hypotheses in the Functional Linear ModelScandinavian Journal of Statistics, 2003
- Linear Regression Analysis2003
- Linear functional regression: The case of fixed design and functional responseCanadian Journal of Statistics, 2002
- Linear Processes in Function Spaces2000
- The Scree Test For The Number Of FactorsMultivariate Behavioral Research, 1966