HAC-package: Covariate-adjusted Skewed Functional Model

In cSFM: Covariate-adjusted Skewed Functional Model (cSFM)

Description

This package provides functions for functional data analysis, when covariate effect is present and high-moment information is considerred. Skewed normal distributions are used for the pointwise distributions, and the dependence is modeled by a Gaussian copula.

Details

Package:	cSFM
Type:	Package
Version:	1.1
Date:	2014-01-20
License:	GPL-2

The main function cSFM.est applies one of the proposed method cSFM and its variates 2cSFM and cSFM0 to the observed data. The generic functions print, fitted and predict are applicable for summarizing the output, obtaining fitted values (including quantile estimation) and predicting at new data point. See data.simulation for an example of the simulated data where various methods including cSFM and other variantes can be applied to. Kronecker product basis is exploited for bivariate parameter functions. The smoothness is controlled by the number of knots which is selected by minimizing AIC; the function cSFM.est.parallel allows parallel computing for various combinations of knots when the facility is available to the users.

References

[1]. Meng Li, Ana-Maria Staicu and Howard D. Bondell (2013), Incorporating Covariates in Skewed Functional Data Models. http://www.stat.ncsu.edu/information/library/papers/mimeo2654_Li.pdf.

See Also

cSFM.est, cSFM.est.parallel, data.simulation.

cSFM documentation built on May 29, 2017, 6:10 p.m.