Maximal autocorrelation functions in functional data analysis
This paper proposes a new factor rotation for the context of functional principal components analysis. This rotation seeks to re-express a functional subspace in terms of directions of decreasing smoothness as represented by a generalized smoothing metric. The rotation can be implemented simply and we show on two examples that this rotation can improve the interpretability of the leading components.
KeywordsFactor rotation Functional data Interpretability Principal components analysis
Giles Hooker was supported in part by NSF Grants DMS-1053252 and DEB-1353039. Steven Roberts was supported in part by ARC Grant DP140100551.
- Cunningham, J.P., Ghahramani, Z.: Unifying linear dimensionality reduction. arXiv preprint arXiv:1406.0873 (2014)
- Ramsay, J.O., Wickham, H., Graves, S., Hooker, G.: fda: functional data analysis, r package version 2.4.0. (2013)Google Scholar
- Shang, H.L., Hyndman, R.J.: fds: functional data sets, r package version 1.7. (2013)Google Scholar
- Shapiro, D., Switzer, P.: Extracting time trends from multiple monitoring sites: Dept. of Statistics, Tech. rep., Stanford University, Tech. Rep. 132. (1989)Google Scholar
- Switzer, P., Green, A.: Min/max autocorrelation factors for multivariate spatial imagery: Dept. of Statistics, Tech. rep., Stanford University, Tech. Rep. 6. (1984)Google Scholar