scan.nn: Determine nearest neighbors with population constraint

In jpfrench81/smerc: Statistical Methods for Regional Counts

Determine nearest neighbors with population constraint

Description

scan.nn determines the nearest neighbors for a set of observations based on the distance matrix according to a population-based upperbound.

Usage

nnpop(d, pop, ubpop)

scan.nn(d, pop, ubpop)

Arguments

d	An n\times n square distance matrix containing the intercentroid distance between the n region centroids.
pop	The population size associated with each region.
ubpop	The upperbound of the proportion of the total population to consider for a cluster.

Details

This function determines the nearest neighbors of each centroid based on the intercentroid distance. The number of nearest neighbors is limited by the sum of the population values among the nearest neighbors. The set of nearest neighbors can contain no more than ubpop * sum(pop) members of the population. The nearest neighbors are ordered from nearest to farthest.

Value

Returns the indices of the nearest neighbors as a list. For each element of the list, the indices are ordered from nearest to farthest from each centroid.

Author(s)

Joshua French

Examples

data(nydf)
coords <- as.matrix(nydf[, c("longitude", "latitude")])
d <- as.matrix(dist(coords))
nn <- scan.nn(d, pop = nydf$pop, ubpop = 0.1)

jpfrench81/smerc documentation built on Jan. 13, 2024, 4:30 a.m.