reduceNeighbours: Selecting the strongest correlated neighbours

In spcopula: Copula Driven Analysis - Multivariate, Spatial, Spatio-Temporal

Description

A function selecting the strongest correlated neighbours from a larger set of neighbours

Usage

reduceNeighbours(stNeigh, stDepFun, n,
                 prediction=stNeigh@prediction, dropEmpty=!prediction)

Arguments

stNeigh	the proxy neighbourhood to be investigated
stDepFun	a spatio-temporal dependence function that return correlation estimates based on a spatial and temporal distance
n	the number of neighbours to be selected.
prediction	whether the neighbourhood is used for prediction (the data slot does not provide the central location's data)
dropEmpty	whether empty neighbourhoods (i.e. neighbourhoods with NA's at the central location) shall be dropped.

Value

A spatio-temporal neighbourhood stNeighbourhood with fewer neighbours.

Author(s)

Benedikt Graeler

See Also

getStNeighbours

Examples

library("sp")
library("spacetime")

sp <- SpatialPoints(matrix(c(181000,181100,333500,333600),2))
time <- as.POSIXct("2014-03-18")+60*60*24*c(0,1,2,3,4)
data <- data.frame(var1=runif(10))

stData <- STFDF(sp, time, data)

stNeigh <- getStNeighbours(stData, spSize=2, tlags=-(0:2))

reduceNeighbours(stNeigh, function(h,delta) return(1/h/delta), 2)

spcopula documentation built on May 2, 2019, 4:49 p.m.