Multivariate functional principal component analysis: A normalization approach
By Jeng-Min Chiou, Ya-Fang Yang, Yu-Ting Chen. 2014
191 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/b7c2b7b26bda4f426856f6122bc8a2680fa117cd
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yehua Li
- Sonja Greven
- Raymond K. Wong
- H. Muller
- Clara Happ
- Alexander Petersen
- Sang-Yun Oh
- Javier Zapata
In Statistics and Probability
- Raymond K. Wong
- Yehua Li
- H. Muller
- Sonja Greven
- Alexander Petersen
- Sang-Yun Oh
- Javier Zapata
- Clara Happ
Citations in the corpus
- Partially Linear Functional Additive Models for Multivariate Functional Data (2018, methodology): “To extract information more efficiently, we jointly model these predictors as a multivariate functional predictor, and perform dimension reduction using multivariate FPCA (mFPCA) (Ramsay and Silverman 2005; Chiou et al. 2014).”
- Partial Separability and Functional Graphical Models for Multivariate Gaussian Processes (2019, background): “Prominent examples include longitudinal behavioral tracking (Chiou & M¨uller 2014), blood protein levels (Dubin & M¨uller 2005), traffic measurements (Chiou et al. 2014, 2016), and neuroimaging data (Petersen & M¨uller 2016, Happ & Greven 2018), for which dimensionality reduction and regression have…”
- Principal component analysis for functional data on Riemannian manifolds and spheres (2017, methodology): “A practically tractable optimality criterion to obtain manifold principal components is then to minimize FV (VK) = E(‖V −Π(V,VK)‖2) (4) over all K-dimensional linear subspaces VK(ψ1, . . . , ψK) = { ∑K k=1 akψk | ak ∈ R} for ψk ∈ H, ψk(t) ∈ TµM(t), and k = 1, . . . ,K. Minimizing (4) is immediately ”
- Multivariate Functional Principal Component Analysis for Data Observed on Different (Dimensional) Domains (2015, methodology): “d a sensible choice depends on the specic application and the question of interest. They canbe pre-specied or estimated from the data, e.g. based on the variation in each element (see references in Chiou et al. 2014). A practical solution is proposed in Section 5, where the new method is applied to ”