Module fof_regression 

Function-on-function regression.

Model: Y(s) = α(s) + ∫ β(s,t) X(t) dt + ε(s)

Uses double FPCA: decompose both response Y and predictor X into FPC scores, regress Y-scores on X-scores, then reconstruct β(s,t) and fitted curves.

References

• Ramsay, J. O. & Silverman, B. W. (2005). Functional Data Analysis, Ch. 16-17.
• Yao, F., Müller, H.-G. & Wang, J.-L. (2005). Functional linear regression analysis for longitudinal data. Annals of Statistics, 33(6), 2873–2903.
• Ivanescu, A. E., Staicu, A.-M., Scheipl, F. & Greven, S. (2015). Penalized function-on-function regression. Computational Statistics, 30(2), 539–568.

Structs

FofCvResult

Result of function-on-function cross-validation.

FofResult

Result of function-on-function regression.

Functions

fof_cv

K-fold cross-validation for function-on-function regression.

fof_regression

Function-on-function regression via double FPCA.

predict_fof

Predict functional responses from new functional predictors.