POIFD: Integrated Depth for Partially Observed Functional Data

In aefdz/depthPoFDA: Partially Observed Integrated Functional Depth

Description

Compute the depth measures of a partially observed functional data set evaluated in a common grid.

Usage

POIFD(data, type = c("MBD", "FMD", "MHRD"), phi)

Arguments

data	matrix p by n, being n the number of functions and p the number of grid points. Rownames are the dense grid x and colnames the identificator of each functional data.
type	choosen depth measure. Fraiman and Muniz depth ("FMD"), Modified band depth ("MBD") or Modified Half Region Depth and Modified Epigraph/Hipograph Index "MHRD")
phi	phi function of weights for the POIFD. The default value is as in the paper, i.e. the proportion of observed functions at each time point.

Value

Ordered vector of depths from the deepest to outward. The names are the functions names (if provided) or the column position.

Examples

data <- gaussian_PoFD(n=100, p=200, type="sparse", observability=0.5)$pofd
poifd <- POIFD(data,  type = c("MBD"))

aefdz/depthPoFDA documentation built on Jan. 8, 2021, 10:16 p.m.